Skip to content

← Writing

engineering

Designing the Feedback Loop

· Jerwin Arnado · 1 min read ·

The single biggest lever isn’t the prompt — it’s how fast and how truthfully the agent can verify its own work. Garbage feedback, garbage agent.

Verifiable surroundings

  • Why ground-truth beats reasoning-in-a-vacuum (callback to part 1).
  • The loop: change → run → observe → adjust.

The feedback sources, ranked

  1. Type checks / compile — fastest, cheapest signal.
  2. Tests — behavioral truth; the agent reads failures and fixes.
  3. Build scripts — does it actually assemble? (e.g. this site’s bin/build.)
  4. Screenshots / browser — the agent’s “eyes” for UI work. Frontend correctness ≠ code correctness.

Making the loop fast

  • Watch mode, incremental builds, scoped test runs.
  • Why a 2-second loop changes agent behavior vs a 2-minute one.

What can’t be checked, say so

  • UI feel, content voice, judgment calls — the agent should flag, not fake.