Treat an AI agent like a junior operator: tell it how you would approve the work, and…
This is a dev post classified by Jev as AI dev tools (a tutorial), kept by the Dev Radar because it carries real work, not commentary.
Treat an AI agent like a junior operator: tell it how you would approve the work, and make verification part of the task-not an afterthought. Start with the acceptance check: whatever a human would do to approve the work can be given to Claude Code as the verification instruction. When verification finds bugs, Claude Code fixes them, tests again, and repeats that loop until the task passes. Then run the cost check using the stated rates: Haiku is $1/$5, Sonnet 5 is $3/$15, and Opus 4.8 is $5/$25 per million input/output tokens. Practical pattern: define approval first, let the agent verify
Posted by catman (1.7k followers) 2 days ago · 5 likes · 147 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- I think we’re looking for this — @vaibcode
- When a hard coding decision needs a second opinion, don’t settle for one model. — @DanKornas
- Banger paper from MIT and Sakana AI. — @dair_ai
- Nautilo agents use memory like memory competition champs. They never forget and they… — @Dan_Jeffries1
- AI agents need guardrails before they reach your tools. — @DanKornas
- 20-30 agents are only useful when you stop babysitting every one of them. — @catmanyau
- Okay, everyone wants us to give the unbiased facts. — @Teknium
- A single RTX 3090 hit 381 tok/s on Qwen3.8-27B. — @0x0SojalSec
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 14.4k posts from 4.7k X accounts over the last 21 days, 1.6k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 21:10 UTC. Full method.