:hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP.
Python ab-testingai-analyticsanalyticscdpdata-warehouseexperimentsfeature-flagsjavascriptproduct-analyticspythonreactsession-replaysurveystypescriptweb-analytics
chore(skills): add contents to four long skill references (#126112)
posthog[bot]79384f34a637
diff --git a/products/aeo/skills/analyzing-ai-citations/references/ai-traffic-join.md b/products/aeo/skills/analyzing-ai-citations/references/ai-traffic-join.mdindex 322f606901a6..90a76843e574 100644--- a/products/aeo/skills/analyzing-ai-citations/references/ai-traffic-join.md+++ b/products/aeo/skills/analyzing-ai-citations/references/ai-traffic-join.md@@ -8,6 +8,13 @@ from different tables and mean different things; report them separately.| AI referral session | `sessions` | `$channel_type = 'AI'` | A person clicked through from an AI product to the site || AI agent request | `events` | `$virt_traffic_type = 'AI Agent'` | An AI assistant, AI search engine or AI crawler fetched a page |+## Contents++- [AI referral sessions](#ai-referral-sessions)+- [AI agent requests](#ai-agent-requests)+- [The loop per cited path](#the-loop-per-cited-path)+- [Reading the loop](#reading-the-loop)+## AI referral sessions`$channel_type` on `sessions` is derived from the entry referrer and UTM parameters. Thediff --git a/products/aeo/skills/analyzing-ai-citations/references/citation-queries.md b/products/aeo/skills/analyzing-ai-citations/references/citation-queries.mdindex 45059d1ff110..bc489b2990bd 100644--- a/products/aeo/skills/analyzing-ai-citations/references/citation-queries.md+++ b/products/aeo/skills/analyzing-ai-citations/references/citation-queries.md@@ -3,6 +3,21 @@HogQL recipes over `system.aeo_citation_checks`, one row per prompt x engine x run. Everyquery runs through `posthog:execute-sql`. All of them follow the three papercuts below.+## Contents++- [Papercuts](#papercuts)+- [Citation rate per engine](#citation-rate-per-engine)+- [Citation rate by topic](#citation-rate-by-topic)+- [Daily citation rate per engine](#daily-citation-rate-per-engine)+- [Top cited domains across the set, own domain marked](#top-cited-domains-across-the-set-own-domain-marked)+- [Prompts answered but never cited in N days](#prompts-answered-but-never-cited-in-n-days)+- [Latest result per prompt and engine](#latest-result-per-prompt-and-engine)+- [Which of our pages get cited](#which-of-our-pages-get-cited)+- [Searches the engines ran](#searches-the-engines-ran)+- [Position when cited](#position-when-cited)+- [Brand sentiment per engine](#brand-sentiment-per-engine)+- [Runner health](#runner-health)+## Papercuts| Wrong | Right | Why |diff --git a/products/aeo/skills/analyzing-ai-citations/references/search-console-join.md b/products/aeo/skills/analyzing-ai-citations/references/search-console-join.mdindex 1e406cfca862..97377c171238 100644--- a/products/aeo/skills/analyzing-ai-citations/references/search-console-join.md+++ b/products/aeo/skills/analyzing-ai-citations/references/search-console-join.md@@ -4,6 +4,15 @@ Search Console data reaches PostHog through a `GoogleSearchConsole` data warehouOnce synced, its tables are plain HogQL tables and join to `system.aeo_citation_checks` andto `sessions` like any other.+## Contents++- [Find the tables](#find-the-tables)+- [Tables and columns](#tables-and-columns)+- [Recipe: how do our cited pages rank on Google?](#recipe-how-do-our-cited-pages-rank-on-google)+- [Recipe: do engine searches match the queries we rank for?](#recipe-do-engine-searches-match-the-queries-we-rank-for)+- [Recipe: topic scorecard](#recipe-topic-scorecard)+- [What this join cannot tell you](#what-this-join-cannot-tell-you)+## Find the tables1. `posthog:external-data-sources-list` and keep sources with `source_type` equal todiff --git a/products/ai_observability/skills/exploring-ai-failures/references/finding-traces.md b/products/ai_observability/skills/exploring-ai-failures/references/finding-traces.mdindex 32cce9f32cac..48d2649a49b8 100644--- a/products/ai_observability/skills/exploring-ai-failures/references/finding-traces.md+++ b/products/ai_observability/skills/exploring-ai-failures/references/finding-traces.md@@ -3,6 +3,16 @@Concrete queries for each strategy in Step 2. Property names (`$ai_is_error`, `$ai_input_tokens`, …) arethe standard AI event properties; confirm the exact ones for this project with `read-data-schema`.+## Contents++- [Where heavy content lives: `events` vs `ai_events`](#where-heavy-content-lives-events-vs-ai_events)+- [Discover the trace taxonomy](#discover-the-trace-taxonomy)+- [Code errors](#code-errors)+- [Metric outliers](#metric-outliers)+- [Manual review of a stratified batch](#manual-review-of-a-stratified-batch)+- [Existing-eval spikes](#existing-eval-spikes)+- [Counting failure modes](#counting-failure-modes)+## Where heavy content lives: `events` vs `ai_events`The `events` table keeps only lightweight metadata: token counts, costs, model, provider,