What a coding agent needs
A coding agent quickly produces a plausible result, but it fills the gaps in its instructions with its own assumptions. This lesson teaches you to turn a spec into a complete brief for an agent, and to know what to ask of it to judge whether the work is really done before you sign off.
Lesson objective
By the end of this lesson, you will be able to turn a spec into a self-contained brief for a coding agent: context, files and interfaces involved, constraints, out of scope and a definition of done with a verification step it can run.
Topics covered
- coding agents
- prompting a coding agent
- definition of done
- AI-assisted development
- specs for AI agents
Where it fits
Specs for coding agents
What do you need to write so an AI coding agent builds the right thing, and how do you check before and after?
Lessons in this module
- What a coding agent needs (this lesson)
- The intent file and repository conventions
- Review an agent's plan against the spec
What you will learn in this module
This lesson is part of the course Write specs that developers and AI agents understand
- Write a spec and an intent file that a coding agent can use (context, constraints, files involved, out of scope, verifiable definition of done).
- Review a coding agent's plan against the spec, spot gaps before it writes code, then check the evidence of what was delivered.
- Keep a spec alive (versions, decisions, updates when the code reveals a case) and spot the anti-patterns that make it useless.
Related courses
- Product ManagementJuniorSome basics are useful: introductory knowledge of the topic.
Design and validate a product experience with AI
2 hr 30 min
- Product ManagementAdvancedRegular practice: you already use the tools or work on this topic.
Instrument a product and use data to make decisions
3 hr 30 min
- Product ManagementAdvancedRegular practice: you already use the tools or work on this topic.
Prioritize and build an outcome-based roadmap
2 hr 30 min