In this 30-minute episode, I walk through my favorite feature in Codex: the /goal command. I show how Goals transform AI from a turn-based assistant that needs constant ‘what’s next?’ prompting into an autonomous agent that can work for hours on complex, multi-step tasks. I share three real examples: eliminating thousands of Sentry errors, cleaning 3,900 emails down to 68, and organizing hundreds of Linear tasks.What you’ll learn:What Goals are and how they differ from standard promptsHow I used /goal to eliminate hundreds of error logs in my codebase over a five-hour autonomous runThe non-technical use cases that make Goals incredibly powerful: cleaning up 3,900 emails in under four hours and organizing hundreds of project management tasks in LinearHow to write effective /goal prompts with measurable outcomes, verification methods, and constraintsWhen not to use Goals and what makes a strong versus weak GoalWhy Goals represent a fundamental shift in how we work with AI, from babysitting the model to managing it—Brought to you by:Mercury—Radically different banking loved by over 300K entrepreneurs—In this episode, we cover:

Introduction

What is /goal and when should you use it?

The difference between prompts and Goal-based loops

Claire’s first five-hour 45-minute autonomous coding task

How to manage a Goal lifecycle: view, pause, resume, and clear

How to write strong goals: outcomes vs. outputs

The six components of effective Goals

Example: Reducing P95 checkout latency with /goal

Demo: Using /goal to eliminate Sentry errors in ChatPRD

Demo: Burning down Vercel API errors

Non-technical use case: Cleaning 3,900 emails with /goal

Demo: Using /goal to clean up Linear project tasks

When not to use /goal