#rag
Every post tagged "rag".
16 posts · showing 1–10
-
Retrieval Returned Zero Rows and the Agent Cited a Policy Doc Anyway
Empty retrieval results are the only tool failure that arrives as a success — status 200, results [] — and a model asked to answer from sources will invent one to fill the hole. Two boundary fixes: a loud typed empty, and citation IDs validated in code.
-
Append or Supersede? What to Do When New Information Contradicts Agent Memory
Most agent memory systems only know how to add. The moment a fact changes, the store holds both versions and the retriever picks whichever one scores higher — which is why a scheduling agent keeps booking a room that was decommissioned last month.
-
Your Retriever Returned 12 Chunks. The Agent Only Really Read 3 of Them.
The correct passage was in the prompt and the agent wrote around it anyway. That's not a retrieval bug — it's a placement bug, and there's a one-minute test that tells the two apart before you touch your embeddings.
-
Should Your Agent Remember That, or Just Look It Up Again?
Two questions sort every fact an agent encounters into "write it down" or "fetch it fresh" — and getting the sort wrong is how an assistant ends up confidently quoting a meeting that moved last week.
-
Was It Retrieval or Reasoning? Diagnosing a Wrong Answer
A day spent rewriting the prompt for a wrong policy answer, when the policy document was never retrieved. Three checks in the right order, and one log field that separates "ignored it" from "never saw it."
-
Budgeting the Context Window: Dividing a Fixed Space
The window wasn't full and the constraints still vanished — because six claimants compete for one space and nobody allocated it. Making history the residual rather than a claimant is what makes the scheme work.
-
The Documentation Problem Agents Create
Documentation has two audiences with different needs, and generated docs that restate the code become negative value the moment they drift — a confident wrong answer with an authoritative source attached.
-
Data Work Gets More Valuable, Not Less
The buffer between bad data and consequences was a person who noticed the number looked wrong. Agents act on it — which turns data quality from an analytical property into an operational one.
-
One Query Is Rarely Enough: Iterative Retrieval for Agents
The search wasn't broken — it answered the question as typed, which isn't the question that was asked. Making retrieval a tool the agent calls repeatedly needs one signal most retrievers refuse to give.
-
The Sales-Research Agent and the Problem of Stale Facts
Every fact in the brief had been true. None was labelled with when — so someone opened a call congratulating a person on a role they'd left a year ago.