korrents
Thorsten Ball

What Thorsten Ball thinks about AI agents

@thorsten-ball · 81 positions · 2 changes of mind · On ppll ↗

Co-founder of Amp and co-host of the Raising an Agent podcast. Wrote Writing an Interpreter in Go.

Thorsten Ball did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

15 dated positions, 2026, in their own words. Our reading of what Thorsten Ball has said — not written or endorsed by them.

  1. Becoming agent-pilled is a one-way door. You only realize this once you've gone through.

    ↗@thorstenball on Xx.com

  2. 11 days earlier
  3. And everything else that was painful about setting up remote envs is truly no longer painful with agents.

    ↗@thorstenball on Xx.com

  4. 13 days earlier
  5. What stopped hallucinations? Tool calls. They let agents touch our reality. If the agent can't see something, it makes it up.

    ↗How I work with Agentsx.com 4th of 14 in this piece

  6. Knowledge piles up in the codebase: AGENTS.md files, skills, scripts, docs. But do agents actually use it? Spawn five blind agents, control vs. treatment, and find out. Agents are really, really good at running experiments.

    ↗How I work with Agentsx.com 6th of 14 in this piece

  7. Each agent should be able to install and run whatever it needs to get job done. Easy in remote machines, yucky in local dev.

    ↗How I work with Agentsx.com 7th of 14 in this piece

  8. Don't iterate with the agent. Let it build tools to iterate. Not "let's try this. ... ah no, let's try that." Instead: "Generate 20 variations and a little page that lets me combine and test them."

    ↗How I work with Agentsx.com 8th of 14 in this piece

  9. Ask for irrefutable proof. Biggest game changer. Agents are really good at producing proof: end-to-end walkthroughs, demo videos, before/after numbers.

    ↗How I work with Agentsx.com 9th of 14 in this piece

  10. Don't wait for your agents. Let them wait on you. If you worry about TTFT, you're probably doing something wrong. Lean into async. Give them bigger tasks, be more ambitous. Batch instead of back and forth.

    ↗How I work with Agentsx.com 10th of 14 in this piece

  11. Automation/schedules/wake-up/heartbeat are killer feature. Didn't realize it, but missed it dearly once it was off.

    ↗How I work with Agentsx.com 11th of 14 in this piece

  12. Every thought you spend wondering about "is it using 300k or 380k tokens?" is wasted time. Compaction works incredibly well. Don't manage context by hand. One thread = one task.

    ↗How I work with Agentsx.com 12th of 14 in this piece

  13. Don't let agents write for humans. Except: debugging steps, inicident reports, some docs. Mechanical stuff where human on other end doesn't matter that much.

    ↗How I work with Agentsx.com 13th of 14 in this piece

  14. 9 days earlier
  15. With agents you can now move 10x faster, you can finally do real continuous integration, and get more confidence in the changes the agent made.

    ↗@thorstenball on Xx.com

  16. 3 weeks earlier
  17. If TTFT is important to you, you're doing something wrong. Don't wait for the agents, make them wait for you.

    ↗@thorstenball on Xx.com

  18. What will matter in future is runtime behavior: Performance characteristics, resource usage, failure modes, observability, debuggability, deployments, rollbacks. And legibility of all that to agents.

    ↗@thorstenball on Xx.com

  19. 1 day earlier
  20. Increasingly convinced: people who do best with agents are those that are good at shipping things in small pieces

    ↗@thorstenball on Xx.com