Shownotes
Legal research tools built on retrieval and on some of the best document collections in any industry still hallucinated on 17% to 33% of test queries. This episode explains where retrieval breaks and what a production agent needs on top of it.
In this episode:
- What the Stanford and Yale study of AI legal research tools found
- Why similarity search fails on multi-document and corpus-wide questions
- Three layers: better retrieval, graph structure and agent memory, with the cost of each
- What the GraphRAG evidence shows, and what an independent benchmark added
- The case that long context…
Website: podcasters.spotify.com

