Fix the environment, not the prompt
Workflow
Run separate agent threads that watch the working agents, spot blockers and repeated failures, and change their setup. The aim is to let many agents run in parallel without colliding.
Theo's current stance
Theo says his prompts were trivial; the results came from removing bottlenecks, such as giving agents SSH (remote login) access to other machines when they ran out of compute.
Try it
- Keep a second agent thread auditing what is slow or failing over and over.
- Ask for multiple sub-agents working independently, and note in agents.md how they avoid stepping on each other.
- If agents keep running out of compute, give them access to more machines.
First seen
43:40
Real talk though, the things I did here were not around the prompts. It was around the environment and setup to allow it to do this stuff. So I like I had other threads going where I was auditing constantly figuring out where the blockers were, what's taking a
Every mention
43:40
Real talk though, the things I did here were not around the prompts. It was around the environment and setup to allow it to do this stuff. So I like I had other threads going where I was auditing constantly figuring out where the blockers were, what's taking a
43:00
out of compute all the time. So I took other machines I had in my fleet, configured them for SSH access, and told it, "You have SSH access to other machines now, like cup two and Alvin two of my uh VPS's." I noticed it kept
Theo Daily is unofficial and not affiliated with Theo or t3.gg. Written by Claude Opus 5.5 from each video's transcript.