# Mario Zechner and Armin Ronacher on agent code that doesn't suck

By Saurabh Kumar · TIL note, Nov 18, 2026 · Tags: harness, code-review, architecture

Source: https://saurabh-kumar.com/til/1795004231/

[Matt Pocock talks with Mario Zechner and Armin Ronacher](https://www.youtube.com/watch?v=ZBTegd8DUZM), the people behind Pi, about writing agent code that doesn't suck. Their line: trust an agent where something can check its work, and keep design and understanding for yourself.

- **Trust follows the oracle.** Pi gets 40 to 50 issues a day. A triage bot reproduces each one, writes a failing test and a fix, and sets a priority. A reproduced P0 with a failing test and a passing fix usually just gets merged. Feature work that touches the user: "results are hilarious".
- **Verification is oversold.** Agents still game the lint rules and tests they write. Armin wrote a Lean proof for parts of Pi and found it was one more file for the agent to read, not a constraint. A counterweight to [Ron Minsky's talk](https://saurabh-kumar.com/til/1793070864/), which treats agent-written proofs as a bet worth making.
- **System design hasn't moved.** Mario saw no real jump from Opus 4.8 to 5.5 in architecture or API design; models "still suck" at it. His method: have the agent write ten versions and pick by feel. Matt asked both for design terms to put in prompts. Neither had any to give.
- **Agent code only grows.** Agents never say no, add features nobody asked for, and guard every input. Armin: software's default is "towards entropy, towards having everything."
- **Don't run away from understanding.** They've seen incident calls where nobody knows what's going on and everyone is prompting Claude. Armin's rule: build so doing nothing during an incident doesn't make it worse, with switches that buy breathing room. No company's disaster plan should be a backup coding agent running on generators.

The detail I'll remember: Armin's agent kept notes saying a table had 2,000 records. It wrote them when the database was empty; the table now has millions. Row counts and rates in agent notes go stale without any diff, so I'd store the command that measures them, not the number.
