Data & AI
Retrieval quality beats model choice
Teams spend weeks comparing models and days on their retrieval pipeline. The ratio should be reversed.
S. Haddad26 May 20269 min read
In almost every RAG system we have reviewed, the dominant error source was retrieval, not generation.
S. Haddad
VP, Data & AI
Writes about data platforms and putting AI into production.
Keep reading
Related articles
Data & AI
You cannot ship an LLM feature without an eval suite
Manual spot-checking does not scale past the demo. Offline evals are the difference between a prototype and a product.
Data & AI
Why your data team spends its week firefighting
Untested transformations and undefined ownership produce a permanent incident queue.
Ready when you are
Let's scope your next platform
Tell us what you are building. A principal engineer joins the first call — not a sales rep.