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

it is deeply unnerving that a tech demo that would have been impossible and/or worth billions of dollars a year ago is now a side-project

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

build the eval harness first 👍

Are you embedding json session logs from Claude’s file system? It took some work but a few hooks can log conversation turns into MLflow, then I backfill my embeds from there

historically have been using the magic aws bedrock “log all inference calls to s3” checkbox but finally deployed an agent gateway to sit between all inference providers and all consumers (which also logs everything to s3)

oh right I remember you said this. our enterprise hosts on bedrock too but no one has access to the infrastructure, so I end up looking for clientside solutions