Concept

Plans and Task Lists

The artifacts that come before code — and how to steer them with comments.

Before touching files, an Antigravity agent externalizes its intent: a task list (the checklist it will execute) and an implementation plan (files, approach, risks, test strategy). These aren't decoration — they're your cheapest steering surface. A plan that reads wrong costs you a comment; a diff that's wrong costs a rework cycle.

Read plans the way you'd read a junior engineer's design note. Did it actually look at the code first — real file paths, real function names, not generic ones? Does a test strategy exist? Is anything in scope you didn't ask for? A plan built from the task title alone is fiction, and fiction is easiest to catch before it compiles.

Steering is conversational: leave a comment directly on the plan — Google-Docs style — and the agent revises before executing. You never have to interrupt or restart to redirect.

Check your understanding
Q1. How do you tell an implementation plan was grounded in the repo rather than hallucinated?
Q2. What's the cheapest way to fix a plan that has the wrong scope?
· Score 100% on the quiz.