All ideasMore in Work
Work

The AI rebuilt our network proxy tool in 6 weeks. Doing it by hand had taken 16 months.

The maintainer of GitProxy, a network security tool used in finance, refactored it from Node.js to Java with AI working as a pair. Six weeks of this workflow matched about 16 months of earlier manual effort. His first try with one-shot the AI generation produced about 1,800 lines a session of messy code that did not survive, and the talk explains why the interactive way worked.

How it works

  1. Try one-shot generation with AI first; the code comes out messy and does not survive
  2. Switch to interactive pairing with AI against well documented, static typed APIs
  3. The agent explores docs, refactors boilerplate and binds to the APIs
  4. Six weeks of work matches about 16 months of manual effort

Why it’s worth knowing

The same agent idea failed as a code generator and worked as a pair. The difference was who kept the design decisions.

Where it’s from

Summarized from a public post on youtube.com. See the original ↗

Upgraded prompt

A ready-to-use prompt for this idea, built from research on what makes AI agents do the job right: who the AI should be, the exact steps, and a check to make sure it was done the way you wanted.

1Who the AI should be
2The prompt, with the steps
3The check when it’s done
Upgraded prompts are coming soon.

Try next

WorkThe AI audited my eBay store, found 28 listings going nowhere, and sold a bundle for meWorkA text and voice agent worked a realtor's 60,000 old leads and turned up 34 closed dealsWorkMatch 904 insurance documents overnight at my dental clinicWorkWhatsApp agent qualified leads, sales reached 461 thousand reais

Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.