Hey, this comment sounds very AI generated. I could be wrong, but if so, you might want to read the newest HN rules.

Looking at their post history it's all 100% AI generated

Though you can get a lot of that context from looking at the git history and discussions (and revisions) on past PRs and perhaps access to the history of team chat channels.

Right, the raw material is there — but there's a gap between "data exists" and "agent has a working model of it." Reading git history on demand is retrieval; internalizing which patterns the team consistently rejects, which abstractions they've refactored away from twice, which reviewer will push back on X — that's a different thing.

The analogy is a new hire with full access to the wiki and Slack history vs. someone who's been on the team six months. The new hire can look things up; the veteran has already synthesized it into judgment that fires before they write a line. Agents currently operate like very fast new hires — great at retrieval, weak on the accumulated synthesis.

You are right that there's a difference. But you can tell the agent to ingest the whole thing once, and distill an approach in a much smaller (and human readable and reviewable) description perhaps? And then that can serve as the basis for the agent going forward.

So you don't have to retrieve the whole history all the time.

It's similar to telling your new hire to catch up on _all_ the slack history. Only that the agent will actually do so.