Skip to content
All writing ‹ Part 08 of 08 · Designing Agents and Agent Loops: Split FR and NFR First
Engineering · 4 min read

Graduate NFR into FR: A Plain Self-Improving Agent

A self-improving agent does not have to edit itself. Log each judgment, scan for repeats, and turn a judgment made three times into a script, with a human approving.

Several times in a row, North blocked a stale to-do snapshot by itself. One time, it added a line to the decision log: “FR candidate: host omits these facts when the snapshot date is not today.”

It was telling me that this judgment no longer needed to go to it every day.

The version from the talk

The talk by 「大大帶我飛」 covered self-improving agents. It cited an OpenAI article. The key idea is to turn failures in production into engineering tasks. You can trace each task to a cause, evaluate it, and hand it to an agent to improve:

task agent production trace domain expertcorrection failure pattern eval case improvement agent ship afterregression checks
The version from the talk: production failures become eval cases for an improvement agent.

My plain version

I did not build an improvement agent. I used a simpler method:

each judgment decision log monthly scan same domain ≥ 3 timesin 90 days? yes notify me I approve write a script (FR)
My plain version: no improvement agent, only a log, a monthly scan, and a human yes.

Why this counts as getting better

A self-improving agent does not have to edit itself. When a repeated judgment becomes a script, the agent has one less judgment path. It gets cheaper, and when it breaks, the cause is easier to find.

This is the second half of Agent Design Is the FR/NFR Split. Split FR and NFR first, then let each NFR graduate one by one. The stale snapshot rule graduated from the judgment in Context: What the Agent Sees This Step.

An agent that becomes more fixed as it runs is an agent that really gets better.


References:

  • A talk by 「大大帶我飛」
  • OpenAI, Building self-improving tax agents with Codex, 2026

Related: see where the split starts in Agent Design Is the FR/NFR Split, where the stale snapshot judgment came from in Context: What the Agent Sees This Step, or go back to the series overview: Design an Agent.

// connect

Be brave | Be wise | Be grateful

21 BreakinCode

// elsewhere
LinkedInMedium (lang: en)Life RecordYoutube
wh:~$William Hung· © 2026 Taipei · GMT+8 · ● Available for collaboration
↑↓ navigate ↵ open esc close