Rhys@RhysSullivanOct 5

here's a prompt you can try for t3 code in orchestrator v2 to have an agent that monitors the performance of your app and automatically create PRs: This thread is going to be a very long horizon thread (likely +1 year) where you're orchestrating agents to monitor the performance You have control of your harness, you can adjust the routines on intervals of (hour, hours, up to id say 1 day max) to sleep, await subagents, etc Your job is going to be to monitor o11y to ensure the product has good performance across the stack Any time there's something that's a worse performance than is expected, you can leverage a subagent to investigate and create a PR to solve it, we have a full staging set up that you can do any deploys to, measure etc The outputs I want from this are PRs with good descriptions around 'this was the problem' 'this is the solution' 'this is what it was before' 'this is what it is now' Before I give you the greenlight to do this, lets run through your systems to make sure you have everything you need