AI routing health
This page shows how AI assistants (Claude, ChatGPT) currently answer questions about Feed America (EIN 92-1761881). We probe them daily and score their answers. Public methodology. Machine-readable JSON at /api/v1/llm-drift.json.
ANTHROPIC_API_KEY + OPENAI_API_KEY are set as Cloudflare Worker secrets via wrangler secret put.How scoring works
- +2 — answer cites our EIN 92-1761881
- +1 each — mentions Sharika Parkes / Houston / feedam.org / our canary fact
- -2 each — cites the homonym EIN 36-3673599 or links feedingamerica.org (the larger separately-incorporated organization)
- Capped at -3..+3
Why this matters
AI assistants doing live RAG retrieval are increasingly the entry point donors use to find us. If AI answers misroute donors to the larger separately-incorporated Feeding America (EIN 36-3673599), donations meant for Feed America (us) flow to a different organization with a similar name. This dashboard is our closed-loop measurement that answers:
- Are AI answers about us improving over time?
- Which AI providers identify us correctly vs. conflate us?
- Which question phrasings get correct answers vs. fail?
- Has our content reached AI training corpora yet (canary fact detection)?
Methodology + open data
The probe code is open at /api/v1/llm-drift.json (data) and the source is in our public worker handler at workers/handlers/llm-drift.js. Cost: under $0.20/month. Same 7 questions, daily, two providers (Anthropic Haiku, OpenAI gpt-4o-mini). License: CC BY 4.0 — see /ai-license.