SCORESearch & retrieval
Why Didn't AI Cite Me?
Hrishabh Jain@hrishabh_hj
0:42This tool analyzes AI-generated answers and their citations to determine why a specific webpage was or was not used as a source, comparing its content against the AI's output.
asked AI for the best whey protein in india 🏋️
the protein brand from a very famous roast show? not cited. not even mentioned. millions of views, zero AI love.
the winner was the brand that wrote a page called "Best Whey Protein in India". comparison tables, FAQ, 2k+ words. the AI just… used it.
that's GEO in a nutshell: being the page the AI answer is built from, not just the brand everyone's heard of
so i built a lil tool: Why Didn't AI Cite Me?
→ grabs the real AI answer + citations
→ reads their pages and yours
→ Jev compares them
Jev is @typesafeai's "System One" model, and it's perfect for this. instead of an LLM writing a long report (and making up reasons), it answers lots of tiny typed questions like "does this page directly answer the query?", each with a confidence score. 10 dimensions per page, fast, and plain code does the math.
the result here? direct answer: 14 vs 96 💀
hype gets you noticed. a clear answer page gets you cited.
github: github.com/HrishabhCodes/geo-citation-diag
Related builds
Vectorless RAG with Jev
This project introduces a novel approach to Retrieval Augmented Generation (RAG) that replaces traditional embedding methods with a structured, table-of-contents-based navigation system, significantly improving speed and reducing costs by offloading non-generative tasks to Jev.
