Module
Module 4 of 5Lesson 1 of 3~16 min

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.

Take this lesson: your first course is freeSee the full syllabus

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

  1. What a coding agent needs (this lesson)
  2. The intent file and repository conventions
  3. Review an agent's plan against the spec

What you will learn in the course

This lesson is part of the course Write specs that developers and AI agents understand

  • Choose the level of spec suited to the decision at hand (PRD, feature spec, ticket) and know what each must contain.
  • State the intent of a feature (problem, target outcome, constraints, non-goals) separately from the solution, to leave the right room to the team and the agent.
  • Write verifiable, declarative and unambiguous Given/When/Then acceptance criteria, including as tables of examples.
  • Identify edge cases and non-functional requirements (performance, security, accessibility, personal data) and make them testable.
  • 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