AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.
Rust agent-memoryai-agentsbm25claude-codeclicode-searchcursordatabaseelasticsearchfull-text-searchhybrid-searchjsonllocal-firstmcpmcp-servermodel-context-protocolragrustsearch-enginevector-search
fix(case-study): lead with the current one-line prompt; keep the measured prompt labeled as such
xerj-org3c75a2197fde
diff --git a/landing/case-studies/reference-coding.html b/landing/case-studies/reference-coding.htmlindex 66d5d9640..5057599fa 100644--- a/landing/case-studies/reference-coding.html+++ b/landing/case-studies/reference-coding.html@@ -68,6 +68,11 @@<section class="scene-section" style="border-top:0; padding-top:0;"><div class="opener"><div class="lbl">◆ Paste this into Claude Code to turn it on</div>+ <pre>Install XERJ (docs: https://xerj.org/llms.txt), index this project's sources, and+set up reference coding: clone and index the open-source repos closest to what+we're building, and search how they solved a problem before writing code.</pre>+ <div class="hint">That is the current one-line setup — <a href="https://xerj.org/llms.txt" rel="external" style="color:var(--accent);">llms.txt</a> walks the agent through the full loop. The measurement below ran the study's original long-form prompt.</div>+ <div class="lbl" style="margin-top:18px;">◆ The exact prompt the study measured</div><pre>Set me up for reference-coding with XERJ and then use it automatically for therest of our work, so I stop burning output tokens re-deriving APIs I could justlook up.