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 🔥🔥🔥

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

one nice thing about RAG is that it forces you away from thinking in terms of "i will grep my local logs" and into "im building an online system that many useful things will dump events to" thinking

haven’t tried that 🤷‍♂️ and to be 1000% clear i am not an ml engineer. but i’ve been very happy and pleasantly surprised with the easy peasy-ness of searching vector space for embeddings vs the difficult difficult lemon difficult of getting elastic to consistently return good results

0 reposts2 likes

No replies yet.