RAG

I have been building an agent platform on my own hardware one post at a time. This is the whole thing in one place: how a job gets dispatched, which model runs it, and what it has to prove before I believe it.

Two passes over the memory layer my AI tools search. First, an audit of how eight knowledge bases preserve working transcripts, which ended with part of the index quarantined and a refusal to backfill history. Then importing 708 conversations from a cloud account into that same layer without publishing things to myself that should stay private.

Every mode of my study assistant returned a server error before the model was ever called. The context packet's fixed part had grown past the safety limit on its own, and one unbounded field guaranteed it would keep growing. The fix went into the shared layer three different callers depend on, with caps chosen by measurement and a degrade path before any error.

A small domain knowledge base built from an official document and three books, with a coverage gate that reports its own holes instead of hiding them. The useful part was the second pass: of eight apparent gaps, three turned out to be my own bad phrasing and five survived as real, and telling those apart is the whole job.

The redaction fix from the day before had quietly made my search index 21% bigger. The cause was one line in the wrong order, the fix was two changes that were useless alone, and the proof was a measurement that matched the prediction to the character.

Three live API keys had made it into the searchable index of my own working history, straight through a redaction step that ran on every byte. The fix was small; deciding how to measure it before trusting it was the real work.

My notes could answer what I decided but not what I actually did, so I built a second searchable layer over the working history itself, and a rule for when it is allowed to be used.

Prospect got meaning-based search fused with its keyword search, and a semantic check for reposted listings. Both had to be designed so they could fail without taking anything down, and the duplicate threshold was calibrated on a copy before it touched the real database.

I taught my notes to answer questions by meaning, so I can ask what I decided about X and why and land on the right note even without remembering a single word from it.