AddyOsmani.com - How to write a good spec for AI agents
addyosmani.com · 7,139 words · saved by 1 readers
Learn how to write effective specifications for AI coding agents to improve clarity, focus, and productivity in your AI-driven development workflows.
TL;DR: Aim for a clear spec covering just enough nuance (this may include structure, style, testing, boundaries) to guide the AI without overwhelming it. Break large tasks into smaller ones vs. keeping everything in one large prompt. Plan first in read-only mode, then execute and iterate continuously. “I’ve heard a lot about writing good specs for AI agents, but haven’t found a solid framework yet. I could write a spec that rivals an RFC, but at some point the context is too large and the model breaks down.” Many developers share this frustration. Simply throwing a massive spec at an AI agent
saved by
related reading
- Building Effective AI Agents \ Anthropicanthropic.com
- Building Effective AI Agents \ Anthropicanthropic.com
- Demystifying evals for AI agents \ Anthropicanthropic.com
- How I Use Claude Code | Philipp Spiessspiess.dev
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- Best practices for Claude Code - Claude Code Docsanthropic.com
- A Practical Guide to Becoming an AI-Native Engineerblog.bytebytego.com
- Effective context engineering for AI agents \ Anthropicanthropic.com
- How to Use Coding Agents Effectively from Planning to Execution and Monitoringcharonhub.deeplearning.ai
- Best practices for using AI coding Agents | Augment Codeaugmentcode.com
- How I use Claude Code on large projectslocalcan.com
- Harness design for long-running application developmentanthropic.com