Post

How do y'all avoid having seven+ terminal windows open with agent conversations that are probably over? but maybe you might want to pick back up a few days from now? seems a shame to throw away all that exploration & context, right?

we chunk and summarize everyone’s agent transcripts, compute text embeddings, and do RAG over the result. it works insanely well

This, but just use agentsview.io to do it for you instead of building it yourself. Shout out to @wesmckinney.com

we deliberately wanted something that worked without needing to scrape the local session logs but this is also cool 👍

How do you do it without?

we forked agentgateway.dev to robustly persist all inference request/response bodies to s3 as gzipped jsonl batches

session reconstruction from the raw inference call logs happens out of band

Nice!

a common coworker reaction has been “it’s really freaky that this agent knows what my teammate was doing 10 minutes ago but i can’t imagine going back to not having it”

Probably cuts down on people sexting their agents, too. Oh, well. You can't have it all.

(i secretly built this tooling in part to set the norm that your agent sessions are work product just like your slack messages, and you should not type anything into the chat gippetty that you wouldn’t want your manager to see)

"chat like it will someday be read back to you in a deposition" is a general rule of thumb in my business