See the retrieval layer
Capture web-search queries explicitly surfaced by ChatGPT, Claude and Google Search in a local side-panel trace.
Open-source Chrome extension
See the queries behind AI search.
Open Queries shows the web-search queries surfaced by ChatGPT, Claude and Google AI Overviews in a local Chrome side panel—and unlocks the query trace and on-demand fan-out estimates after you accept the privacy setting.
Queries, not conversations · Observed stays observed · AGPL-3.0
Open AI search field guide
Start with evidence. Follow it to the workflow.
Query fan-out
What are fan-out queries?
A practical explanation of the narrower searches answer engines can use to retrieve evidence before responding.
11 min readAEO / GEOWhy AEO and GEO need query data
How human demand, observed retrieval queries and estimated fan-outs support different AEO and GEO decisions.
12 min readEvidence methodObserved vs. estimated AI search queries
How Open Queries labels direct interface evidence and controlled model reconstructions without mixing them.
11 min readTechnical methodologyEstimating fan-out queries with log probabilities
A mathematical account of provider-native inverse perplexity, token alignment, repeated sampling and the limits of closed-model reconstruction.
18 min readIntent pillars
Build the complete AI search evidence chain.
Practical workflow
AI search optimization
Connect human demand, retrieval evidence, one canonical and measurable outcomes without AI-only gimmicks.
Read the practical guideAI visibilityAI search visibility
Connect observed retrieval queries with citations, referrals and measurable visibility work.
Read the practical guideGEOGenerative engine optimization
Build retrieval-friendly, evidence-led content without pretending that model visibility is a fixed rank.
Read the practical guideAEOAnswer engine optimization
Turn answerable questions, source evidence and query language into a practical AEO framework.
Read the practical guideRetrieval vocabularyFan-out queries
See how one broad information need can become several narrower evidence searches.
Read the practical guideThe open retrieval layer
Useful to inspect. Rigorous enough to audit.
Open Queries keeps direct observations and probabilistic estimates separate from capture through aggregation.
Estimate with native evidence
Accept the privacy setting, then request plausible fan-outs ranked by each provider’s own token probabilities—or repeated native samples when logprobs are unavailable.
Audit the whole system
Extension, Worker, schemas and methodology are public under AGPL-3.0-or-later. No black-box ranking layer.
A narrow data contract
Transparent without surveillance.
- No chat messages, titles, account identity or conversation URLs
- Privacy starts unaccepted; accepting it reveals queries and unlocks fan-out estimates
- Sensitive-pattern filtering runs locally and at the Worker edge
- Eligible observed queries are written directly to D1
- Estimated fan-outs are never stored as observed queries
Make AI search transparent
Build the query history AI search is missing.
Install, accept privacy and inspect. Every layer stays open.