What Thorsten Ball thinks about AI agents
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.
Filter AI agents · Newest first
27 more topics
Only Thorsten Ball on AI agents. See everyone on AI agents
15 dated positions, 2026, in their own words. Our reading of what Thorsten Ball has said — not written or endorsed by them.
-
Our readingBecoming agent-pilled is a one-way door.
Their wordsBecoming agent-pilled is a one-way door. You only realize this once you've gone through.
- 11 days earlier
-
Their wordsAnd everything else that was painful about setting up remote envs is truly no longer painful with agents.
- 13 days earlier
-
Their wordsWhat stopped hallucinations? Tool calls. They let agents touch our reality. If the agent can't see something, it makes it up.
-
Their wordsKnowledge 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.
-
Their wordsEach agent should be able to install and run whatever it needs to get job done. Easy in remote machines, yucky in local dev.
-
Their wordsDon'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."
-
Their wordsAsk for irrefutable proof. Biggest game changer. Agents are really good at producing proof: end-to-end walkthroughs, demo videos, before/after numbers.
-
Our readingDon't wait for your agents; let them wait on you, with bigger, batched, asynchronous tasks.
Their wordsDon'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.
-
Their wordsAutomation/schedules/wake-up/heartbeat are killer feature. Didn't realize it, but missed it dearly once it was off.
-
Our readingStop managing an agent's context by hand: compaction works very well, so keep one thread per task.
Their wordsEvery 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.
-
Their wordsDon'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.
- 9 days earlier
-
Their wordsWith agents you can now move 10x faster, you can finally do real continuous integration, and get more confidence in the changes the agent made.
- 3 weeks earlier
-
Their wordsIf TTFT is important to you, you're doing something wrong. Don't wait for the agents, make them wait for you.
-
Their wordsWhat will matter in future is runtime behavior: Performance characteristics, resource usage, failure modes, observability, debuggability, deployments, rollbacks. And legibility of all that to agents.
- 1 day earlier
-
Their wordsIncreasingly convinced: people who do best with agents are those that are good at shipping things in small pieces