An automated knowledge base that made information retrieval 80% faster and halved onboarding, keeping documentation in step with the code.
80% faster information retrieval
95% documentation accuracy
50% onboarding time cut
Documentation drifted: answers lived across repos and went stale the moment the code moved on.
Manual upkeep didn't scale, and a search that returns stale docs is worse than no search.
I built a context pipeline over the documentation: embed on change, semantic search across every repo's docs, consistency checks between them, and automated updates triggered by the code itself.
Information retrieval got 80% faster, documentation accuracy reached 95%, and onboarding time dropped by half.
Architecture
Repos code + docs
on change
Sync consistency checks
Vector index embeddings
Semantic search ranked answers
// docs update when the code does, not when someone remembers
Tradeoffs
—Automated doc updates still ran through consistency checks — trust in the corpus mattered more than update speed.
—A vector index is one more piece of infrastructure to run; 80% faster retrieval paid for it, but it isn't free.