vault / agents / agents.md

Agents

Agents & LLMs 52 words 3 outgoing 1 backlinks

In the assistant described in my posts, a model chooses steps while retrieval supplies the evidence. That creates several ways to fail: a poor tool choice, missing documents, or an answer that goes beyond them. A fluent reply alone does not show that the loop worked.

Read the full example: related post.

LINKS IN THIS NOTE

[[ RAG ]] Retrieval-augmented generation searches a document collection, then writes an answer using the retrieved context. Keep retrieval and answer quality separate: finding the right document does not guarantee the model uses it, and a plausible answer does not prove the document... [[ Evaluation-driven development ]] Compare relevance, retrieval recall, groundedness and latency against a baseline. Inspect examples as well as scores. In my current workflow, evaluation produces a report for engineers rather than an automatic deployment gate. That is a description of this system, not... [[ Feedback triage ]] A thumbs-down starts an investigation, not a diagnosis. The workflow I built replays the question, collects evidence, distinguishes a content gap from a configuration issue, and routes the case to an owner. Routing is ordinary code; the model proposes the...