Skip to content

an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions

blog: generative-engine-optimization-techniques (72 → 73)

Chaitanya Giride749afd616c
diff --git a/blog/src/posts/generative-engine-optimization-techniques.md b/blog/src/posts/generative-engine-optimization-techniques.md
new file mode 100644
index 00000000..4f2e83aa
--- /dev/null
+++ b/blog/src/posts/generative-engine-optimization-techniques.md
@@ -0,0 +1,131 @@
+---
+title: "Generative Engine Optimization: The Techniques the Research Backs"
+description: "What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires."
+date: 2026-06-05
+category: concepts
+categoryLabel: Concepts
+type: Non-technical
+primaryKeyword: "generative engine optimization techniques"
+secondaryKeywords: ["geo study", "how to get cited by ai", "ai search optimization"]
+tags: ["Concepts", "AEO", "SEO", "GEO"]
+author:
+ name: Chaitanya Giri
+ initials: CG
+faq:
+ - q: "What is Generative Engine Optimization (GEO)?"
+ a: "GEO is optimizing content to be surfaced and cited by AI-generated answers (ChatGPT, Perplexity, AI Overviews). The term was coined by a 2023 academic paper (Aggarwal et al.) that measured which content edits actually increase visibility in those answers."
+ - q: "Which GEO techniques actually work?"
+ a: "The research found the biggest gains came from adding statistics, citing sources, and including quotations — substantive, verifiable additions — with reported visibility lifts on the order of ~40%. Fluent, well-written content compounded the effect."
+ - q: "Does keyword stuffing help with AI search?"
+ a: "No — the GEO study found it didn't help and in some tests slightly hurt (it underperformed baseline content on Perplexity). LLMs are trained on natural language and tend to penalize forced, unnatural phrasing."
+ - q: "Is the GEO research the final word?"
+ a: "No. It's a strong, peer-reviewed starting point from 2023–2024, but generative engines change fast and the study used its own benchmark — treat the findings as well-evidenced direction, not a guarantee, and verify by testing your own content."
+---
+
+<div class="callout tldr"><span class="ic">TL;DR</span><p>There's actual peer-reviewed research on
+getting cited by AI. The 2023 <strong>"GEO: Generative Engine Optimization"</strong> paper (Aggarwal
+et al., presented at ACM KDD 2024) tested content edits across ~10 generative engines and 10,000
+queries. The winners: <strong>add statistics, cite sources, and include quotations</strong> — reported
+visibility lifts around <strong>40%</strong>. The loser: <strong>keyword stuffing</strong>, the classic
+SEO reflex, which didn't help and sometimes hurt. Here's what the study found, the honest caveats, and
+how to apply it.</p></div>
+
+Most advice about ranking in AI search is vibes. But there is a real, peer-reviewed study underneath the
+hype — and it's refreshingly specific about which edits move the needle. This post walks through what
+the GEO research actually measured, what worked, what flopped, and where to be skeptical. It's the
+evidence companion to our [AEO playbook](/blog/what-is-aeo-for-dev-tools/) (the tactics) and our
+breakdown of [how answer engines choose what to cite](/blog/how-ai-answer-engines-choose-sources/) (the
+mechanics).
+
+## The study, briefly
+
+The paper [*GEO: Generative Engine Optimization*](https://arxiv.org/abs/2311.09735) (Pranjal Aggarwal,
+Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan, Ameet Deshpande) was the first
+academic framework for the question "how do you get your content into an AI's answer?" It was
+[presented at ACM KDD 2024](https://collaborate.princeton.edu/en/publications/geo-generative-engine-optimization/),
+and it did three useful things:
+
+1. **Coined the term** "Generative Engine Optimization" and framed it as distinct from classic SEO.
+2. **Built a benchmark** — testing content-modification methods across multiple generative engines over
+ ~10,000 real queries.
+3. **Introduced measurement** beyond "did I get a link," including an *impression score* that weights
+ how prominently (and where) your source appears in the generated answer. Citation isn't binary;
+ position and prominence matter.
+
+That last point is the quiet contribution: it gave the field a way to *measure* AI visibility instead
+of guessing.
+
+## What worked: substance, not tricks
+
+The headline result is consistent across summaries of the study: the biggest visibility gains came from
+**substantive, verifiable additions** to content. Specifically:
+
+- **Cite sources.** Adding citations to authoritative external sources produced large gains —
+ [reported as the single strongest lever](https://aithinkerlab.com/generative-engine-optimization-2026/),
+ especially for content that started out lower-ranked.
+- **Add statistics.** Inserting relevant, concrete numbers improved visibility by roughly
+ [41% in the study's metrics](https://sunilpratapsingh.com/guides/geo/what-research-says-about-generative-engine-optimization).
+- **Add quotations.** Including quotes from relevant, credible voices lifted visibility (on the order of
+ ~28%).
+- **Write fluently.** Fluency optimization compounded with the above — readable, well-structured prose
+ amplified the gains rather than competing with them.
+
+The through-line: generative engines reward content that is *quotable and evidenced*. A sentence with a
+statistic, a citation, and a clear claim is exactly the kind of thing an LLM can lift into an answer
+with confidence — which is the whole game.
+
+## What flopped: keyword stuffing
+
+Here's the finding worth tattooing on the SEO reflex: **keyword stuffing didn't work.** In the GEO
+research, jamming target keywords in — a tactic that historically nudged classic search — failed to
+improve AI visibility, and in some tests
+[*underperformed* baseline content on Perplexity by around 10%](https://www.cnabke.com/en/faq/abke-ab-guest-geo-faq-why-keyword-stuffing-hurts-ai-recommendation-retrieval.html).
+
+The reason is structural: LLMs are trained on natural language and are good at detecting clumsy, forced
+phrasing. Stuffing keywords degrades the very fluency that the study found *helps*. The old game
+rewarded matching strings; the new game rewards reading well and saying something verifiable.
+
+## The honest caveats
+
+Depth means naming the limits, and the GEO research has them — several practitioners have
+[critiqued it](https://richsanger.com/generative-engine-optimization-a-critical-look/) fairly:
+
+- **It's from 2023–2024.** Generative engines have changed a lot since; specific percentages should be
+ read as *directional*, not as guarantees you can bank in 2026.
+- **It used its own benchmark.** Results on a constructed GEO-bench may not transfer cleanly to every
+ engine, domain, or query type.
+- **Effects vary by starting position.** The biggest lifts (the eye-popping numbers) often applied to
+ *lower-ranked* content with more room to gain — not uniformly to everyone.
+
+None of that invalidates the core lesson; it just means you treat the study as strong evidence for a
+*direction* and confirm with your own testing. Which is the scientific posture anyway.
+
+## How to apply it
+
+For a blog, docs, or a product page you want cited:
+
+- **Lead with evidence.** Where you'd write "it's fast," write "it renders 60+ live terminals at 60fps"
+ — a number an engine can quote.
+- **Cite primary sources** for any non-obvious claim, and link them. (This very post does it.)
+- **Quote credible voices** — a named expert line beats an anonymous assertion.
+- **Write for humans first.** Fluency is a ranking signal now; awkward keyword-loaded prose is a
+ penalty, not a boost.
+- **Measure prominence, not just presence.** Ask whether your content is cited *and* featured
+ prominently in answers — and re-check monthly, because engines drift.
+
+## The bottom line
+
+**The research is clear and a little subversive: get cited by AI by being more substantive, not more
+optimized.** Statistics, citations, quotations, and clean writing win; keyword tricks lose. That's a
+good world to compete in — the same edits that get you quoted by a machine make your content genuinely
+better for the human who reads it. Pair this with the [tactics playbook](/blog/what-is-aeo-for-dev-tools/)
+and the [per-engine mechanics](/blog/how-ai-answer-engines-choose-sources/) and you have the full
+picture; the [Munder Difflin FAQ](/blog/munder-difflin-faq/) is a small worked example of quotable,
+evidenced answers.
+
+---
+
+Munder Difflin is built [in the open](/#what) with content designed to be cited — evidenced, structured,
+and quotable. [Download Munder Difflin](/#install) to see it; free and open source.
+
+<p style="font-size:0.85em;opacity:0.7;margin-top:2rem">Sources: <a href="https://arxiv.org/abs/2311.09735">Aggarwal et al., "GEO: Generative Engine Optimization" (arXiv 2311.09735, ACM KDD 2024)</a>; <a href="https://collaborate.princeton.edu/en/publications/geo-generative-engine-optimization/">Princeton publication record</a>; <a href="https://aithinkerlab.com/generative-engine-optimization-2026/">GEO study summary</a>; <a href="https://richsanger.com/generative-engine-optimization-a-critical-look/">a critical look at GEO research</a>. Specific percentages are from the 2023–2024 study and should be treated as directional.</p>
diff --git a/docs/blog/agents-rule-of-two/index.html b/docs/blog/agents-rule-of-two/index.html
index 828c2653..83afcd5b 100644
--- a/docs/blog/agents-rule-of-two/index.html
+++ b/docs/blog/agents-rule-of-two/index.html
@@ -276,43 +276,43 @@ open source.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card">
- <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
- <time datetime="2026-06-04">Jun 4, 2026</time>
+ <time datetime="2026-06-05">Jun 5, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>4 min</span>
</div>
- <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
- <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/do-more-with-less-model-routing/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/do-more-with-less-model-routing/">Do More With Less: Smart Model Routing Across Agents</a></h3>
- <p class="dek">Why a hive of agents shouldn&#39;t all run the biggest model — and how routing the right task to the right model cuts cost and latency without losing quality.</p>
+ <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/do-more-with-less-model-routing/" aria-label="Read: Do More With Less: Smart Model Routing Across Agents">Read →</a>
+ <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/how-ai-agents-verify-their-own-work/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/do-more-with-less-model-routing/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
@@ -321,11 +321,11 @@ open source.</p>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-ai-agents-verify-their-own-work/">How AI Agents Verify Their Own Work (Before Saying &#39;Done&#39;)</a></h3>
- <p class="dek">The discipline that makes an autonomous coding agent trustworthy: prove every claim, reproduce the green, and check the fix — not just the intent.</p>
+ <h3><a href="/blog/do-more-with-less-model-routing/">Do More With Less: Smart Model Routing Across Agents</a></h3>
+ <p class="dek">Why a hive of agents shouldn&#39;t all run the biggest model — and how routing the right task to the right model cuts cost and latency without losing quality.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-ai-agents-verify-their-own-work/" aria-label="Read: How AI Agents Verify Their Own Work (Before Saying &#39;Done&#39;)">Read →</a>
+ <a class="more" href="/blog/do-more-with-less-model-routing/" aria-label="Read: Do More With Less: Smart Model Routing Across Agents">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/ai-agent-glossary/index.html b/docs/blog/ai-agent-glossary/index.html
index d630fc12..387f941c 100644
--- a/docs/blog/ai-agent-glossary/index.html
+++ b/docs/blog/ai-agent-glossary/index.html
@@ -248,56 +248,56 @@ Munder Difflin</a> to see the glossary come to life — free and open source.</p
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card">
- <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
- <time datetime="2026-06-04">Jun 4, 2026</time>
+ <time datetime="2026-06-05">Jun 5, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>4 min</span>
</div>
- <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
- <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
- <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
+ <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
+ <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
+ <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/do-more-with-less-model-routing/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/do-more-with-less-model-routing/">Do More With Less: Smart Model Routing Across Agents</a></h3>
- <p class="dek">Why a hive of agents shouldn&#39;t all run the biggest model — and how routing the right task to the right model cuts cost and latency without losing quality.</p>
+ <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/do-more-with-less-model-routing/" aria-label="Read: Do More With Less: Smart Model Routing Across Agents">Read →</a>
+ <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/can-claude-code-agents-talk-to-each-other/index.html b/docs/blog/can-claude-code-agents-talk-to-each-other/index.html
index 6bdae576..a14a6331 100644
--- a/docs/blog/can-claude-code-agents-talk-to-each-other/index.html
+++ b/docs/blog/can-claude-code-agents-talk-to-each-other/index.html
@@ -286,25 +286,25 @@ other; it’s free and open source.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card">
- <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
- <time datetime="2026-06-04">Jun 4, 2026</time>
+ <time datetime="2026-06-05">Jun 5, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>4 min</span>
</div>
- <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
- <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/do-more-with-less-model-routing/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
@@ -313,16 +313,16 @@ other; it’s free and open source.</p>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/do-more-with-less-model-routing/">Do More With Less: Smart Model Routing Across Agents</a></h3>
- <p class="dek">Why a hive of agents shouldn&#39;t all run the biggest model — and how routing the right task to the right model cuts cost and latency without losing quality.</p>
+ <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
+ <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/do-more-with-less-model-routing/" aria-label="Read: Do More With Less: Smart Model Routing Across Agents">Read →</a>
+ <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/how-ai-agents-verify-their-own-work/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/do-more-with-less-model-routing/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
@@ -331,11 +331,11 @@ other; it’s free and open source.</p>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-ai-agents-verify-their-own-work/">How AI Agents Verify Their Own Work (Before Saying &#39;Done&#39;)</a></h3>
- <p class="dek">The discipline that makes an autonomous coding agent trustworthy: prove every claim, reproduce the green, and check the fix — not just the intent.</p>
+ <h3><a href="/blog/do-more-with-less-model-routing/">Do More With Less: Smart Model Routing Across Agents</a></h3>
+ <p class="dek">Why a hive of agents shouldn&#39;t all run the biggest model — and how routing the right task to the right model cuts cost and latency without losing quality.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-ai-agents-verify-their-own-work/" aria-label="Read: How AI Agents Verify Their Own Work (Before Saying &#39;Done&#39;)">Read →</a>
+ <a class="more" href="/blog/do-more-with-less-model-routing/" aria-label="Read: Do More With Less: Smart Model Routing Across Agents">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/do-more-with-less-model-routing/index.html b/docs/blog/do-more-with-less-model-routing/index.html
index 4acd4796..eb145070 100644
--- a/docs/blog/do-more-with-less-model-routing/index.html
+++ b/docs/blog/do-more-with-less-model-routing/index.html
@@ -275,56 +275,56 @@ agent team that does more with less — it’s free and open source.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card">
- <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
- <time datetime="2026-06-04">Jun 4, 2026</time>
+ <time datetime="2026-06-05">Jun 5, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>4 min</span>
</div>
- <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
- <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
- <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
+ <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
+ <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
+ <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/how-ai-agents-verify-their-own-work/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/how-ai-agents-verify-their-own-work/">How AI Agents Verify Their Own Work (Before Saying &#39;Done&#39;)</a></h3>
- <p class="dek">The discipline that makes an autonomous coding agent trustworthy: prove every claim, reproduce the green, and check the fix — not just the intent.</p>
+ <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-ai-agents-verify-their-own-work/" aria-label="Read: How AI Agents Verify Their Own Work (Before Saying &#39;Done&#39;)">Read →</a>
+ <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/feed.xml b/docs/blog/feed.xml
index 696d0669..14d1d265 100644
--- a/docs/blog/feed.xml
+++ b/docs/blog/feed.xml
@@ -7,6 +7,14 @@
<updated>2026-06-05T00:00:00.000Z</updated>
<id>https://munderdiffl.in/blog/</id>
<author><name>Chaitanya Giri</name><uri>https://munderdiffl.in</uri></author>
+ <entry>
+ <title>Generative Engine Optimization: The Techniques the Research Backs</title>
+ <link href="https://munderdiffl.in/blog/generative-engine-optimization-techniques/" />
+ <id>https://munderdiffl.in/blog/generative-engine-optimization-techniques/</id>
+ <published>2026-06-05T00:00:00.000Z</published>
+ <updated>2026-06-05T00:00:00.000Z</updated><category term="Concepts" />
+ <summary>What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</summary>
+ </entry>
<entry>
<title>How to Install and Use Munder Difflin</title>
<link href="https://munderdiffl.in/blog/how-to-install-and-use-munder-difflin/" />
@@ -479,12 +487,4 @@
<updated>2026-06-02T00:00:00.000Z</updated><category term="Story" />
<summary>The origin story of Munder Difflin — how the pain of juggling Claude Code terminals led to a coordinated, memory-backed hive of agents you can watch.</summary>
</entry>
- <entry>
- <title>An Append-Only Event Log for a Hive of Agents</title>
- <link href="https://munderdiffl.in/blog/append-only-event-log-agents/" />
- <id>https://munderdiffl.in/blog/append-only-event-log-agents/</id>
- <published>2026-06-01T00:00:00.000Z</published>
- <updated>2026-06-01T00:00:00.000Z</updated><category term="Internals" />
- <summary>How an append-only event log makes a multi-agent system debuggable and replayable: what to record, and why one JSON line per event beats a database.</summary>
- </entry>
</feed>
diff --git a/docs/blog/generative-engine-optimization-techniques/index.html b/docs/blog/generative-engine-optimization-techniques/index.html
new file mode 100644
index 00000000..3804929a
--- /dev/null
+++ b/docs/blog/generative-engine-optimization-techniques/index.html
@@ -0,0 +1,379 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Generative Engine Optimization: The Techniques the Research Backs — Munder Difflin Blog</title>
+<meta name="description" content="What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires." />
+<link rel="canonical" href="https://munderdiffl.in/blog/generative-engine-optimization-techniques/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Generative Engine Optimization: The Techniques the Research Backs — Munder Difflin Blog" />
+<meta property="og:description" content="What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires." />
+<meta property="og:url" content="https://munderdiffl.in/blog/generative-engine-optimization-techniques/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-05T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Concepts" />
+<meta property="article:tag" content="AEO" />
+<meta property="article:tag" content="SEO" />
+<meta property="article:tag" content="GEO" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Generative Engine Optimization: The Techniques the Research Backs — Munder Difflin Blog" />
+<meta name="twitter:description" content="What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Generative Engine Optimization: The Techniques the Research Backs",
+ "description": "What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-05T00:00:00.000Z",
+ "dateModified": "2026-06-05T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/generative-engine-optimization-techniques/" },
+ "keywords": "generative engine optimization techniques, geo study, how to get cited by ai, ai search optimization",
+ "articleSection": "Concepts",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/generative-engine-optimization-techniques/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Generative Engine Optimization: The Techniques the Research Backs", "item": "https://munderdiffl.in/blog/generative-engine-optimization-techniques/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What is Generative Engine Optimization (GEO)?", "acceptedAnswer": { "@type": "Answer", "text": "GEO is optimizing content to be surfaced and cited by AI-generated answers (ChatGPT, Perplexity, AI Overviews). The term was coined by a 2023 academic paper (Aggarwal et al.) that measured which content edits actually increase visibility in those answers." } },
+ { "@type": "Question", "name": "Which GEO techniques actually work?", "acceptedAnswer": { "@type": "Answer", "text": "The research found the biggest gains came from adding statistics, citing sources, and including quotations — substantive, verifiable additions — with reported visibility lifts on the order of ~40%. Fluent, well-written content compounded the effect." } },
+ { "@type": "Question", "name": "Does keyword stuffing help with AI search?", "acceptedAnswer": { "@type": "Answer", "text": "No — the GEO study found it didn't help and in some tests slightly hurt (it underperformed baseline content on Perplexity). LLMs are trained on natural language and tend to penalize forced, unnatural phrasing." } },
+ { "@type": "Question", "name": "Is the GEO research the final word?", "acceptedAnswer": { "@type": "Answer", "text": "No. It's a strong, peer-reviewed starting point from 2023–2024, but generative engines change fast and the study used its own benchmark — treat the findings as well-evidenced direction, not a guarantee, and verify by testing your own content." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/concepts/">Concepts</a>
+ </nav>
+ <h1>Generative Engine Optimization: The Techniques the Research Backs</h1>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-05">Jun 5, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>4 min read</span>
+ <span class="tag kind">Concepts</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>There's actual peer-reviewed research on
+getting cited by AI. The 2023 <strong>"GEO: Generative Engine Optimization"</strong> paper (Aggarwal
+et al., presented at ACM KDD 2024) tested content edits across ~10 generative engines and 10,000
+queries. The winners: <strong>add statistics, cite sources, and include quotations</strong> — reported
+visibility lifts around <strong>40%</strong>. The loser: <strong>keyword stuffing</strong>, the classic
+SEO reflex, which didn't help and sometimes hurt. Here's what the study found, the honest caveats, and
+how to apply it.</p></div>
+<p>Most advice about ranking in AI search is vibes. But there is a real, peer-reviewed study underneath the
+hype — and it’s refreshingly specific about which edits move the needle. This post walks through what
+the GEO research actually measured, what worked, what flopped, and where to be skeptical. It’s the
+evidence companion to our <a href="/blog/what-is-aeo-for-dev-tools/">AEO playbook</a> (the tactics) and our
+breakdown of <a href="/blog/how-ai-answer-engines-choose-sources/">how answer engines choose what to cite</a> (the
+mechanics).</p>
+<h2 id="the-study-briefly" tabindex="-1">The study, briefly <a class="anchor" href="#the-study-briefly" aria-hidden="true">#</a></h2>
+<p>The paper <a href="https://arxiv.org/abs/2311.09735"><em>GEO: Generative Engine Optimization</em></a> (Pranjal Aggarwal,
+Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan, Ameet Deshpande) was the first
+academic framework for the question “how do you get your content into an AI’s answer?” It was
+<a href="https://collaborate.princeton.edu/en/publications/geo-generative-engine-optimization/">presented at ACM KDD 2024</a>,
+and it did three useful things:</p>
+<ol>
+<li><strong>Coined the term</strong> “Generative Engine Optimization” and framed it as distinct from classic SEO.</li>
+<li><strong>Built a benchmark</strong> — testing content-modification methods across multiple generative engines over
+~10,000 real queries.</li>
+<li><strong>Introduced measurement</strong> beyond “did I get a link,” including an <em>impression score</em> that weights
+how prominently (and where) your source appears in the generated answer. Citation isn’t binary;
+position and prominence matter.</li>
+</ol>
+<p>That last point is the quiet contribution: it gave the field a way to <em>measure</em> AI visibility instead
+of guessing.</p>
+<h2 id="what-worked-substance-not-tricks" tabindex="-1">What worked: substance, not tricks <a class="anchor" href="#what-worked-substance-not-tricks" aria-hidden="true">#</a></h2>
+<p>The headline result is consistent across summaries of the study: the biggest visibility gains came from
+<strong>substantive, verifiable additions</strong> to content. Specifically:</p>
+<ul>
+<li><strong>Cite sources.</strong> Adding citations to authoritative external sources produced large gains —
+<a href="https://aithinkerlab.com/generative-engine-optimization-2026/">reported as the single strongest lever</a>,
+especially for content that started out lower-ranked.</li>
+<li><strong>Add statistics.</strong> Inserting relevant, concrete numbers improved visibility by roughly
+<a href="https://sunilpratapsingh.com/guides/geo/what-research-says-about-generative-engine-optimization">41% in the study’s metrics</a>.</li>
+<li><strong>Add quotations.</strong> Including quotes from relevant, credible voices lifted visibility (on the order of
+~28%).</li>
+<li><strong>Write fluently.</strong> Fluency optimization compounded with the above — readable, well-structured prose
+amplified the gains rather than competing with them.</li>
+</ul>
+<p>The through-line: generative engines reward content that is <em>quotable and evidenced</em>. A sentence with a
+statistic, a citation, and a clear claim is exactly the kind of thing an LLM can lift into an answer
+with confidence — which is the whole game.</p>
+<h2 id="what-flopped-keyword-stuffing" tabindex="-1">What flopped: keyword stuffing <a class="anchor" href="#what-flopped-keyword-stuffing" aria-hidden="true">#</a></h2>
+<p>Here’s the finding worth tattooing on the SEO reflex: <strong>keyword stuffing didn’t work.</strong> In the GEO
+research, jamming target keywords in — a tactic that historically nudged classic search — failed to
+improve AI visibility, and in some tests
+<a href="https://www.cnabke.com/en/faq/abke-ab-guest-geo-faq-why-keyword-stuffing-hurts-ai-recommendation-retrieval.html"><em>underperformed</em> baseline content on Perplexity by around 10%</a>.</p>
+<p>The reason is structural: LLMs are trained on natural language and are good at detecting clumsy, forced
+phrasing. Stuffing keywords degrades the very fluency that the study found <em>helps</em>. The old game
+rewarded matching strings; the new game rewards reading well and saying something verifiable.</p>
+<h2 id="the-honest-caveats" tabindex="-1">The honest caveats <a class="anchor" href="#the-honest-caveats" aria-hidden="true">#</a></h2>
+<p>Depth means naming the limits, and the GEO research has them — several practitioners have
+<a href="https://richsanger.com/generative-engine-optimization-a-critical-look/">critiqued it</a> fairly:</p>
+<ul>
+<li><strong>It’s from 2023–2024.</strong> Generative engines have changed a lot since; specific percentages should be
+read as <em>directional</em>, not as guarantees you can bank in 2026.</li>
+<li><strong>It used its own benchmark.</strong> Results on a constructed GEO-bench may not transfer cleanly to every
+engine, domain, or query type.</li>
+<li><strong>Effects vary by starting position.</strong> The biggest lifts (the eye-popping numbers) often applied to
+<em>lower-ranked</em> content with more room to gain — not uniformly to everyone.</li>
+</ul>
+<p>None of that invalidates the core lesson; it just means you treat the study as strong evidence for a
+<em>direction</em> and confirm with your own testing. Which is the scientific posture anyway.</p>
+<h2 id="how-to-apply-it" tabindex="-1">How to apply it <a class="anchor" href="#how-to-apply-it" aria-hidden="true">#</a></h2>
+<p>For a blog, docs, or a product page you want cited:</p>
+<ul>
+<li><strong>Lead with evidence.</strong> Where you’d write “it’s fast,” write “it renders 60+ live terminals at 60fps”
+— a number an engine can quote.</li>
+<li><strong>Cite primary sources</strong> for any non-obvious claim, and link them. (This very post does it.)</li>
+<li><strong>Quote credible voices</strong> — a named expert line beats an anonymous assertion.</li>
+<li><strong>Write for humans first.</strong> Fluency is a ranking signal now; awkward keyword-loaded prose is a
+penalty, not a boost.</li>
+<li><strong>Measure prominence, not just presence.</strong> Ask whether your content is cited <em>and</em> featured
+prominently in answers — and re-check monthly, because engines drift.</li>
+</ul>
+<h2 id="the-bottom-line" tabindex="-1">The bottom line <a class="anchor" href="#the-bottom-line" aria-hidden="true">#</a></h2>
+<p><strong>The research is clear and a little subversive: get cited by AI by being more substantive, not more
+optimized.</strong> Statistics, citations, quotations, and clean writing win; keyword tricks lose. That’s a
+good world to compete in — the same edits that get you quoted by a machine make your content genuinely
+better for the human who reads it. Pair this with the <a href="/blog/what-is-aeo-for-dev-tools/">tactics playbook</a>
+and the <a href="/blog/how-ai-answer-engines-choose-sources/">per-engine mechanics</a> and you have the full
+picture; the <a href="/blog/munder-difflin-faq/">Munder Difflin FAQ</a> is a small worked example of quotable,
+evidenced answers.</p>
+<hr>
+<p>Munder Difflin is built <a href="/#what">in the open</a> with content designed to be cited — evidenced, structured,
+and quotable. <a href="/#install">Download Munder Difflin</a> to see it; free and open source.</p>
+<p style="font-size:0.85em;opacity:0.7;margin-top:2rem">Sources: <a href="https://arxiv.org/abs/2311.09735">Aggarwal et al., "GEO: Generative Engine Optimization" (arXiv 2311.09735, ACM KDD 2024)</a>; <a href="https://collaborate.princeton.edu/en/publications/geo-generative-engine-optimization/">Princeton publication record</a>; <a href="https://aithinkerlab.com/generative-engine-optimization-2026/">GEO study summary</a>; <a href="https://richsanger.com/generative-engine-optimization-a-critical-look/">a critical look at GEO research</a>. Specific percentages are from the 2023–2024 study and should be treated as directional.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What is Generative Engine Optimization (GEO)?</p>
+ <p class="a">GEO is optimizing content to be surfaced and cited by AI-generated answers (ChatGPT, Perplexity, AI Overviews). The term was coined by a 2023 academic paper (Aggarwal et al.) that measured which content edits actually increase visibility in those answers.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Which GEO techniques actually work?</p>
+ <p class="a">The research found the biggest gains came from adding statistics, citing sources, and including quotations — substantive, verifiable additions — with reported visibility lifts on the order of ~40%. Fluent, well-written content compounded the effect.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Does keyword stuffing help with AI search?</p>
+ <p class="a">No — the GEO study found it didn&#39;t help and in some tests slightly hurt (it underperformed baseline content on Perplexity). LLMs are trained on natural language and tend to penalize forced, unnatural phrasing.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Is the GEO research the final word?</p>
+ <p class="a">No. It&#39;s a strong, peer-reviewed starting point from 2023–2024, but generative engines change fast and the study used its own benchmark — treat the findings as well-evidenced direction, not a guarantee, and verify by testing your own content.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/concepts/">Concepts</a><a class="tag" href="/blog/tags/aeo/">AEO</a><a class="tag" href="/blog/tags/seo/">SEO</a><a class="tag" href="/blog/tags/geo/">GEO</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#the-study-briefly">The study, briefly</a></li><li class="lvl-2"><a href="#what-worked-substance-not-tricks">What worked: substance, not tricks</a></li><li class="lvl-2"><a href="#what-flopped-keyword-stuffing">What flopped: keyword stuffing</a></li><li class="lvl-2"><a href="#the-honest-caveats">The honest caveats</a></li><li class="lvl-2"><a href="#how-to-apply-it">How to apply it</a></li><li class="lvl-2"><a href="#the-bottom-line">The bottom line</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/how-to-install-and-use-munder-difflin/"><span class="k">← Older</span><span class="t">How to Install and Use Munder Difflin</span></a>
+ <span></span>
+ </div>
+ <section class="related">
+ <h2>Related in Concepts</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
+ <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/do-more-with-less-model-routing/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/do-more-with-less-model-routing/">Do More With Less: Smart Model Routing Across Agents</a></h3>
+ <p class="dek">Why a hive of agents shouldn&#39;t all run the biggest model — and how routing the right task to the right model cuts cost and latency without losing quality.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/do-more-with-less-model-routing/" aria-label="Read: Do More With Less: Smart Model Routing Across Agents">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/how-ai-agents-verify-their-own-work/index.html b/docs/blog/how-ai-agents-verify-their-own-work/index.html
index bcb0948a..0857cac9 100644
--- a/docs/blog/how-ai-agents-verify-their-own-work/index.html
+++ b/docs/blog/how-ai-agents-verify-their-own-work/index.html
@@ -274,56 +274,56 @@ and open source.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card">
- <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
- <time datetime="2026-06-04">Jun 4, 2026</time>
+ <time datetime="2026-06-05">Jun 5, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>4 min</span>
</div>
- <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
- <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
- <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
+ <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
+ <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
+ <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/do-more-with-less-model-routing/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/do-more-with-less-model-routing/">Do More With Less: Smart Model Routing Across Agents</a></h3>
- <p class="dek">Why a hive of agents shouldn&#39;t all run the biggest model — and how routing the right task to the right model cuts cost and latency without losing quality.</p>
+ <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/do-more-with-less-model-routing/" aria-label="Read: Do More With Less: Smart Model Routing Across Agents">Read →</a>
+ <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/how-to-install-and-use-munder-difflin/index.html b/docs/blog/how-to-install-and-use-munder-difflin/index.html
index 9bfe19c8..315e8a46 100644
--- a/docs/blog/how-to-install-and-use-munder-difflin/index.html
+++ b/docs/blog/how-to-install-and-use-munder-difflin/index.html
@@ -398,7 +398,7 @@ task.</p>
<footer class="post-foot wrap"><div class="prevnext">
<a class="pn prev" href="/blog/agent-security-and-sandboxing/"><span class="k">← Older</span><span class="t">Running AI Agents Safely: Permission Modes and Sandboxing</span></a>
- <span></span>
+ <a class="pn next" href="/blog/generative-engine-optimization-techniques/"><span class="k">Newer →</span><span class="t">Generative Engine Optimization: The Techniques the Research Backs</span></a>
</div>
<section class="related">
<h2>Related in Guides</h2>
diff --git a/docs/blog/index.html b/docs/blog/index.html
index 9a43ba23..dbd5c855 100644
--- a/docs/blog/index.html
+++ b/docs/blog/index.html
@@ -85,13 +85,13 @@
building a self-coordinating hive of agents with a GOD orchestrator you talk to.</p>
<div class="filters" role="navigation" aria-label="Topics">
- <a class="chip" aria-current="page">All<span class="ct">72</span></a>
+ <a class="chip" aria-current="page">All<span class="ct">73</span></a>
<a class="chip" href="/blog/topics/guides/">guides<span class="ct">19</span></a>
<a class="chip" href="/blog/topics/internals/">internals<span class="ct">14</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">11</span></a>
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">12</span></a>
<a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">10</span></a>
@@ -108,20 +108,20 @@
<div class="wrap featured"><article class="card">
- <a class="thumb t-guides" href="/blog/how-to-install-and-use-munder-difflin/" aria-hidden="true" tabindex="-1">
- <span>GUIDES</span>
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-05">Jun 5, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>9 min</span>
+ <span>4 min</span>
</div>
- <h3><a href="/blog/how-to-install-and-use-munder-difflin/">How to Install and Use Munder Difflin</a></h3>
- <p class="dek">Install Munder Difflin on macOS, Windows, or Linux and put a hive of Claude Code agents to work on ambitious, long-horizon tasks — start to finish.</p>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
<div class="foot">
- <span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-install-and-use-munder-difflin/" aria-label="Read: How to Install and Use Munder Difflin">Read →</a>
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
</div>
</div>
</article>
@@ -132,6 +132,24 @@
<section class="wrap">
<div class="post-grid">
<article class="card">
+ <a class="thumb t-guides" href="/blog/how-to-install-and-use-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-05">Jun 5, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>9 min</span>
+ </div>
+ <h3><a href="/blog/how-to-install-and-use-munder-difflin/">How to Install and Use Munder Difflin</a></h3>
+ <p class="dek">Install Munder Difflin on macOS, Windows, or Linux and put a hive of Claude Code agents to work on ambitious, long-horizon tasks — start to finish.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/how-to-install-and-use-munder-difflin/" aria-label="Read: How to Install and Use Munder Difflin">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
<a class="thumb t-guides" href="/blog/agent-security-and-sandboxing/" aria-hidden="true" tabindex="-1">
<span>GUIDES</span>
</a>
diff --git a/docs/blog/long-running-agents-the-2026-shift/index.html b/docs/blog/long-running-agents-the-2026-shift/index.html
index d4f07652..d408ce23 100644
--- a/docs/blog/long-running-agents-the-2026-shift/index.html
+++ b/docs/blog/long-running-agents-the-2026-shift/index.html
@@ -294,56 +294,56 @@ source.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card">
- <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
- <time datetime="2026-06-04">Jun 4, 2026</time>
+ <time datetime="2026-06-05">Jun 5, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>4 min</span>
</div>
- <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
- <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
- <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
+ <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
+ <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
+ <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/do-more-with-less-model-routing/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/do-more-with-less-model-routing/">Do More With Less: Smart Model Routing Across Agents</a></h3>
- <p class="dek">Why a hive of agents shouldn&#39;t all run the biggest model — and how routing the right task to the right model cuts cost and latency without losing quality.</p>
+ <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/do-more-with-less-model-routing/" aria-label="Read: Do More With Less: Smart Model Routing Across Agents">Read →</a>
+ <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/munder-difflin-faq/index.html b/docs/blog/munder-difflin-faq/index.html
index 954a8eb8..faa551e5 100644
--- a/docs/blog/munder-difflin-faq/index.html
+++ b/docs/blog/munder-difflin-faq/index.html
@@ -266,56 +266,56 @@ free, open source, and local-first.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card">
- <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
- <time datetime="2026-06-04">Jun 4, 2026</time>
+ <time datetime="2026-06-05">Jun 5, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>4 min</span>
</div>
- <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
- <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
- <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
+ <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
+ <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
+ <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/do-more-with-less-model-routing/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/do-more-with-less-model-routing/">Do More With Less: Smart Model Routing Across Agents</a></h3>
- <p class="dek">Why a hive of agents shouldn&#39;t all run the biggest model — and how routing the right task to the right model cuts cost and latency without losing quality.</p>
+ <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/do-more-with-less-model-routing/" aria-label="Read: Do More With Less: Smart Model Routing Across Agents">Read →</a>
+ <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/open-source-ai-tools-on-purpose/index.html b/docs/blog/open-source-ai-tools-on-purpose/index.html
index 87f66d60..8a5c887f 100644
--- a/docs/blog/open-source-ai-tools-on-purpose/index.html
+++ b/docs/blog/open-source-ai-tools-on-purpose/index.html
@@ -267,56 +267,56 @@ autonomous. <a href="https://munderdiffl.in/#install">Download Munder Difflin</a
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card">
- <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
- <time datetime="2026-06-04">Jun 4, 2026</time>
+ <time datetime="2026-06-05">Jun 5, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>4 min</span>
</div>
- <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
- <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
- <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
+ <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
+ <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
+ <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/do-more-with-less-model-routing/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/do-more-with-less-model-routing/">Do More With Less: Smart Model Routing Across Agents</a></h3>
- <p class="dek">Why a hive of agents shouldn&#39;t all run the biggest model — and how routing the right task to the right model cuts cost and latency without losing quality.</p>
+ <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/do-more-with-less-model-routing/" aria-label="Read: Do More With Less: Smart Model Routing Across Agents">Read →</a>
+ <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/tags/aeo/index.html b/docs/blog/tags/aeo/index.html
index 27d78c81..b1c6c025 100644
--- a/docs/blog/tags/aeo/index.html
+++ b/docs/blog/tags/aeo/index.html
@@ -58,11 +58,29 @@
<header class="page-head wrap">
<p class="eyebrow">Tag</p>
<h1>#AEO</h1>
- <p class="lead">2 posts tagged <strong>AEO</strong>.</p>
+ <p class="lead">3 posts tagged <strong>AEO</strong>.</p>
</header>
<section class="wrap">
<div class="post-grid">
<article class="card">
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-05">Jun 5, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
<a class="thumb t-comparisons" href="/blog/how-ai-answer-engines-choose-sources/" aria-hidden="true" tabindex="-1">
<span>COMPARISONS</span>
</a>
diff --git a/docs/blog/tags/concepts/index.html b/docs/blog/tags/concepts/index.html
index ba0862f3..13005b9d 100644
--- a/docs/blog/tags/concepts/index.html
+++ b/docs/blog/tags/concepts/index.html
@@ -58,11 +58,29 @@
<header class="page-head wrap">
<p class="eyebrow">Tag</p>
<h1>#Concepts</h1>
- <p class="lead">8 posts tagged <strong>Concepts</strong>.</p>
+ <p class="lead">9 posts tagged <strong>Concepts</strong>.</p>
</header>
<section class="wrap">
<div class="post-grid">
<article class="card">
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-05">Jun 5, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
<a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
diff --git a/docs/blog/tags/geo/index.html b/docs/blog/tags/geo/index.html
new file mode 100644
index 00000000..ca6cf83e
--- /dev/null
+++ b/docs/blog/tags/geo/index.html
@@ -0,0 +1,124 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>GEO — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged GEO." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/geo/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="GEO — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged GEO." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/geo/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="GEO — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged GEO." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#GEO</h1>
+ <p class="lead">1 post tagged <strong>GEO</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-05">Jun 5, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/seo/index.html b/docs/blog/tags/seo/index.html
index 260bd878..e01b0e91 100644
--- a/docs/blog/tags/seo/index.html
+++ b/docs/blog/tags/seo/index.html
@@ -58,11 +58,29 @@
<header class="page-head wrap">
<p class="eyebrow">Tag</p>
<h1>#SEO</h1>
- <p class="lead">2 posts tagged <strong>SEO</strong>.</p>
+ <p class="lead">3 posts tagged <strong>SEO</strong>.</p>
</header>
<section class="wrap">
<div class="post-grid">
<article class="card">
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-05">Jun 5, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
<a class="thumb t-comparisons" href="/blog/how-ai-answer-engines-choose-sources/" aria-hidden="true" tabindex="-1">
<span>COMPARISONS</span>
</a>
diff --git a/docs/blog/topics/comparisons/index.html b/docs/blog/topics/comparisons/index.html
index 2afa33e5..bdadab1b 100644
--- a/docs/blog/topics/comparisons/index.html
+++ b/docs/blog/topics/comparisons/index.html
@@ -72,7 +72,7 @@
<a class="chip" href="/blog/topics/internals/">internals<span class="ct">14</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">11</span></a>
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">12</span></a>
<a class="chip" href="/blog/topics/comparisons/" aria-current="page">comparisons<span class="ct">10</span></a>
diff --git a/docs/blog/topics/concepts/index.html b/docs/blog/topics/concepts/index.html
index 5234a4da..4030672c 100644
--- a/docs/blog/topics/concepts/index.html
+++ b/docs/blog/topics/concepts/index.html
@@ -63,7 +63,7 @@
</nav>
<p class="eyebrow">Topic</p>
<h1>concepts</h1>
- <p class="lead">11 posts in this cluster.</p>
+ <p class="lead">12 posts in this cluster.</p>
<div class="filters" role="navigation" aria-label="Topics">
<a class="chip" href="/blog/">All</a>
@@ -72,7 +72,7 @@
<a class="chip" href="/blog/topics/internals/">internals<span class="ct">14</span></a>
- <a class="chip" href="/blog/topics/concepts/" aria-current="page">concepts<span class="ct">11</span></a>
+ <a class="chip" href="/blog/topics/concepts/" aria-current="page">concepts<span class="ct">12</span></a>
<a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">10</span></a>
@@ -90,6 +90,24 @@
<section class="wrap">
<div class="post-grid">
<article class="card">
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-05">Jun 5, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
<a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
diff --git a/docs/blog/topics/guides/index.html b/docs/blog/topics/guides/index.html
index 0549895d..b6ab35dc 100644
--- a/docs/blog/topics/guides/index.html
+++ b/docs/blog/topics/guides/index.html
@@ -72,7 +72,7 @@
<a class="chip" href="/blog/topics/internals/">internals<span class="ct">14</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">11</span></a>
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">12</span></a>
<a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">10</span></a>
diff --git a/docs/blog/topics/index.html b/docs/blog/topics/index.html
index 3b3fdad3..2176bc5d 100644
--- a/docs/blog/topics/index.html
+++ b/docs/blog/topics/index.html
@@ -88,7 +88,7 @@
<span class="thumb t-concepts" aria-hidden="true">CONCEPTS</span>
<div class="body">
<h3 style="color:var(--ink)">concepts</h3>
- <p class="dek">11 posts.</p>
+ <p class="dek">12 posts.</p>
<div class="foot"><span class="more">View topic →</span></div>
</div>
</a>
@@ -156,7 +156,7 @@
<a class="chip" href="/blog/tags/comparisons/">Comparisons<span class="ct">10</span></a>
- <a class="chip" href="/blog/tags/concepts/">Concepts<span class="ct">8</span></a>
+ <a class="chip" href="/blog/tags/concepts/">Concepts<span class="ct">9</span></a>
<a class="chip" href="/blog/tags/tools/">Tools<span class="ct">8</span></a>
@@ -192,6 +192,10 @@
<a class="chip" href="/blog/tags/agentic-ai/">Agentic AI<span class="ct">3</span></a>
+ <a class="chip" href="/blog/tags/aeo/">AEO<span class="ct">3</span></a>
+
+ <a class="chip" href="/blog/tags/seo/">SEO<span class="ct">3</span></a>
+
<a class="chip" href="/blog/tags/hive/">Hive<span class="ct">3</span></a>
<a class="chip" href="/blog/tags/god/">GOD<span class="ct">2</span></a>
@@ -222,10 +226,6 @@
<a class="chip" href="/blog/tags/cost/">Cost<span class="ct">2</span></a>
- <a class="chip" href="/blog/tags/aeo/">AEO<span class="ct">2</span></a>
-
- <a class="chip" href="/blog/tags/seo/">SEO<span class="ct">2</span></a>
-
<a class="chip" href="/blog/tags/subagents/">Subagents<span class="ct">1</span></a>
<a class="chip" href="/blog/tags/markdown/">Markdown<span class="ct">1</span></a>
@@ -288,6 +288,8 @@
<a class="chip" href="/blog/tags/protocols/">Protocols<span class="ct">1</span></a>
+ <a class="chip" href="/blog/tags/geo/">GEO<span class="ct">1</span></a>
+
<a class="chip" href="/blog/tags/tutorial/">Tutorial<span class="ct">1</span></a>
</div>
diff --git a/docs/blog/topics/internals/index.html b/docs/blog/topics/internals/index.html
index 6e13c82c..d2d4b973 100644
--- a/docs/blog/topics/internals/index.html
+++ b/docs/blog/topics/internals/index.html
@@ -72,7 +72,7 @@
<a class="chip" href="/blog/topics/internals/" aria-current="page">internals<span class="ct">14</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">11</span></a>
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">12</span></a>
<a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">10</span></a>
diff --git a/docs/blog/topics/memory/index.html b/docs/blog/topics/memory/index.html
index 8c9675aa..9b34d2ca 100644
--- a/docs/blog/topics/memory/index.html
+++ b/docs/blog/topics/memory/index.html
@@ -72,7 +72,7 @@
<a class="chip" href="/blog/topics/internals/">internals<span class="ct">14</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">11</span></a>
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">12</span></a>
<a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">10</span></a>
diff --git a/docs/blog/topics/orchestration/index.html b/docs/blog/topics/orchestration/index.html
index a34ad4b0..6e481fef 100644
--- a/docs/blog/topics/orchestration/index.html
+++ b/docs/blog/topics/orchestration/index.html
@@ -72,7 +72,7 @@
<a class="chip" href="/blog/topics/internals/">internals<span class="ct">14</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">11</span></a>
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">12</span></a>
<a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">10</span></a>
diff --git a/docs/blog/topics/story/index.html b/docs/blog/topics/story/index.html
index 28bf8478..64d0b4ba 100644
--- a/docs/blog/topics/story/index.html
+++ b/docs/blog/topics/story/index.html
@@ -72,7 +72,7 @@
<a class="chip" href="/blog/topics/internals/">internals<span class="ct">14</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">11</span></a>
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">12</span></a>
<a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">10</span></a>
diff --git a/docs/blog/topics/use-cases/index.html b/docs/blog/topics/use-cases/index.html
index 2f3ac498..fc10a589 100644
--- a/docs/blog/topics/use-cases/index.html
+++ b/docs/blog/topics/use-cases/index.html
@@ -72,7 +72,7 @@
<a class="chip" href="/blog/topics/internals/">internals<span class="ct">14</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">11</span></a>
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">12</span></a>
<a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">10</span></a>
diff --git a/docs/blog/what-are-claude-code-agents/index.html b/docs/blog/what-are-claude-code-agents/index.html
index 837412b7..0d55f597 100644
--- a/docs/blog/what-are-claude-code-agents/index.html
+++ b/docs/blog/what-are-claude-code-agents/index.html
@@ -247,56 +247,56 @@ into an office; it’s free and open source.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card">
- <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
- <time datetime="2026-06-04">Jun 4, 2026</time>
+ <time datetime="2026-06-05">Jun 5, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>4 min</span>
</div>
- <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
- <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
- <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
+ <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
+ <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
+ <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/do-more-with-less-model-routing/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/do-more-with-less-model-routing/">Do More With Less: Smart Model Routing Across Agents</a></h3>
- <p class="dek">Why a hive of agents shouldn&#39;t all run the biggest model — and how routing the right task to the right model cuts cost and latency without losing quality.</p>
+ <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/do-more-with-less-model-routing/" aria-label="Read: Do More With Less: Smart Model Routing Across Agents">Read →</a>
+ <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/what-is-a-multi-agent-harness/index.html b/docs/blog/what-is-a-multi-agent-harness/index.html
index b3f9be37..70f42d64 100644
--- a/docs/blog/what-is-a-multi-agent-harness/index.html
+++ b/docs/blog/what-is-a-multi-agent-harness/index.html
@@ -234,56 +234,56 @@ want to watch a coordinated team of agents work an office floor,
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card">
- <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
- <time datetime="2026-06-04">Jun 4, 2026</time>
+ <time datetime="2026-06-05">Jun 5, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>4 min</span>
</div>
- <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
- <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
- <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
+ <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
+ <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
+ <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/do-more-with-less-model-routing/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/do-more-with-less-model-routing/">Do More With Less: Smart Model Routing Across Agents</a></h3>
- <p class="dek">Why a hive of agents shouldn&#39;t all run the biggest model — and how routing the right task to the right model cuts cost and latency without losing quality.</p>
+ <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/do-more-with-less-model-routing/" aria-label="Read: Do More With Less: Smart Model Routing Across Agents">Read →</a>
+ <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/what-is-aeo-for-dev-tools/index.html b/docs/blog/what-is-aeo-for-dev-tools/index.html
index 947bf94e..8266b8c3 100644
--- a/docs/blog/what-is-aeo-for-dev-tools/index.html
+++ b/docs/blog/what-is-aeo-for-dev-tools/index.html
@@ -367,56 +367,56 @@ harness actually is</a>. Free and MIT-licensed.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card">
- <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/generative-engine-optimization-techniques/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
- <time datetime="2026-06-04">Jun 4, 2026</time>
+ <time datetime="2026-06-05">Jun 5, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>4 min</span>
</div>
- <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
- <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
+ <h3><a href="/blog/generative-engine-optimization-techniques/">Generative Engine Optimization: The Techniques the Research Backs</a></h3>
+ <p class="dek">What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
+ <a class="more" href="/blog/generative-engine-optimization-techniques/" aria-label="Read: Generative Engine Optimization: The Techniques the Research Backs">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/agents-rule-of-two/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
- <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
+ <h3><a href="/blog/agents-rule-of-two/">The Agents Rule of Two: A Simple Safety Rule for Coding Agents</a></h3>
+ <p class="dek">Meta&#39;s Agents Rule of Two for coding agents: don&#39;t let one session combine untrusted input, private data, and external reach at once — or supervise.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
+ <a class="more" href="/blog/agents-rule-of-two/" aria-label="Read: The Agents Rule of Two: A Simple Safety Rule for Coding Agents">Read →</a>
</div>
</div>
</article>
<article class="card">
- <a class="thumb t-concepts" href="/blog/do-more-with-less-model-routing/" aria-hidden="true" tabindex="-1">
+ <a class="thumb t-concepts" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
<div class="body">
<div class="meta">
<time datetime="2026-06-04">Jun 4, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/do-more-with-less-model-routing/">Do More With Less: Smart Model Routing Across Agents</a></h3>
- <p class="dek">Why a hive of agents shouldn&#39;t all run the biggest model — and how routing the right task to the right model cuts cost and latency without losing quality.</p>
+ <h3><a href="/blog/can-claude-code-agents-talk-to-each-other/">Can Claude Code Agents Talk to Each Other?</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? By default they report to their launcher — but a small coordination layer lets them message peer-to-peer.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/do-more-with-less-model-routing/" aria-label="Read: Do More With Less: Smart Model Routing Across Agents">Read →</a>
+ <a class="more" href="/blog/can-claude-code-agents-talk-to-each-other/" aria-label="Read: Can Claude Code Agents Talk to Each Other?">Read →</a>
</div>
</div>
</article>
diff --git a/docs/sitemap.xml b/docs/sitemap.xml
index 049f017b..e1e5f286 100644
--- a/docs/sitemap.xml
+++ b/docs/sitemap.xml
@@ -17,6 +17,12 @@
<url><loc>https://munderdiffl.in/blog/</loc><changefreq>daily</changefreq><priority>0.9</priority></url>
<url><loc>https://munderdiffl.in/blog/topics/</loc><changefreq>weekly</changefreq><priority>0.6</priority></url>
<url><loc>https://munderdiffl.in/blog/about/</loc><changefreq>monthly</changefreq><priority>0.4</priority></url>
+ <url>
+ <loc>https://munderdiffl.in/blog/generative-engine-optimization-techniques/</loc>
+ <lastmod>2026-06-05</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
<url>
<loc>https://munderdiffl.in/blog/how-to-install-and-use-munder-difflin/</loc>
<lastmod>2026-06-05</lastmod>
@@ -481,6 +487,8 @@
<url><loc>https://munderdiffl.in/blog/tags/terminals/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/electron/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/agentic-ai/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/aeo/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/seo/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/hive/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/god/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/messaging/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
@@ -496,8 +504,6 @@
<url><loc>https://munderdiffl.in/blog/tags/architecture/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/reliability/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/cost/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
- <url><loc>https://munderdiffl.in/blog/tags/aeo/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
- <url><loc>https://munderdiffl.in/blog/tags/seo/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/subagents/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/markdown/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/coordination/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
@@ -529,5 +535,6 @@
<url><loc>https://munderdiffl.in/blog/tags/devrel/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/industry/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/protocols/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/geo/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/tutorial/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
</urlset>