Agentic Blueprints 3

Retrieval that doesn't trust its first search: it grades the results, rewrites the query when they're weak, and only answers once the context is good.

A failed data job triggers three probes in parallel, then a fixer and verifier loop on a patch until it passes a dry run — and open a PR.

Runs your health queries on a schedule, compares against normal ranges, and posts to Slack with enough context to know if it actually matters.