Post

im not kidding and im sure @cameron.stream can back me up from another direction: if you arent capturing/mining your team's agent session logs, you are leaving it all on the table. we have a service that lets you run RAG tool calls against vectorized agent session summaries and it is 🔥🔥🔥

Can you say more about your tool? Use cases, etc?

RAG on claude sessions:

RAG on slack:

RAG on slack from inside a claude session:

heres an example that simultaneously cites to internal github (sourcebot), claude session logs, and linear:

have you folks made this public?

atticus i built this in my free time while waiting for other claude sessions to finish doing stuff that's actually part of my job

Yeah time for me to build this on the side lmao. Appreciate you sharing

build the eval harness first 👍

That is super cool! Can you speak a little bit about how you're doing evals? Like is it measuring successful vs failed tool calls, or something like that?

for the agent sessions i’m chunking, summarizing with haiku, computing embeddings with msft harrier, storing in qdrant. transcripts themselves get run through an AGGRESSIVE redaction pass, stored in s3 with WORM semantics, static html renderer