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 🔥🔥🔥

austin (eeek!/ackkk! 👻)@thebadcode.com

the fact that ant/oai dont trivially expose a "download all my org's inference logs" button makes me think that they realize those logs are worth almost as much as the output of the agent sessions themselves

atticus goldfinch

@atticusgf.bsky.social

26 July

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

austin (eeek!/ackkk! 👻)

@thebadcode.com

26 July

RAG on claude sessions:

austin (eeek!/ackkk! 👻)

@thebadcode.com

26 July

RAG on slack:

austin (eeek!/ackkk! 👻)

@thebadcode.com

26 July

RAG on slack from inside a claude session:

atticus goldfinch

@atticusgf.bsky.social

26 July

So does this functionally let you "collaborate" with other agents and devs?

atticus goldfinch

@atticusgf.bsky.social

26 July

"Xyz is working on feature y, what is she guiding her agent to do" etc?

austin (eeek!/ackkk! 👻)

@thebadcode.com

yeah. for centuries, man has yearned to query their coworker's keystroke logs to dig up all their hard-earned context instead of re-deriving it, and its suddenly become completely tractable

26/7/26, 9:48 pm0 reposts4 likes

atticus goldfinch

@atticusgf.bsky.social

26 July

I've had very similar thoughts around rag and tracking feature/ticket/project level decisions as they happen. I'll poke at this first though. Finally getting to a place where I'll have more time for these internal projects.