I Let Codex Run for 6 Hours. Here’s What Happened.

Why It Matters

Goal-based loops enable sustained, autonomous AI workflows that can complete complex, multi-step engineering and product tasks—reducing manual oversight and accelerating iteration. Clear goal design and verification are crucial for safe, reliable automation and wider adoption of long-running AI agents.

Summary

Claravo demos OpenAI Codex’s /goal feature, showing how goal-based loops let the model run autonomously for hours by iterating, testing and self-verifying until a measurable outcome is reached. She explains when to use goals versus single-turn prompts, how to manage goal lifecycle (start, pause, resume, remove), and shares that her first run lasted nearly six hours. The video outlines how to write effective goals—defining outcome, verification, constraints, boundaries, iteration policy and stop conditions—and gives a technical example (reducing P95 checkout latency) and nontechnical use cases. Practical tips emphasize measurable success criteria and guardrails so the agent can self-manage without constant human prompting.

Original Description

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:

1. What Goals are and how they differ from standard prompts

2. How I used /goal to eliminate hundreds of error logs in my codebase over a five-hour autonomous run

3. The 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 Linear

4. How to write effective /goal prompts with measurable outcomes, verification methods, and constraints

5. When not to use Goals and what makes a strong versus weak Goal

6. Why 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: https://mercury.com/

In this episode, we cover:

(00:00) Introduction

(01:50) What is /goal and when should you use it?

(02:45) The difference between prompts and Goal-based loops

(04:06) Claire’s first five-hour 45-minute autonomous coding task

(05:05) How to manage a Goal lifecycle: view, pause, resume, and clear

(06:06) How to write strong goals: outcomes vs. outputs

(07:34) The six components of effective Goals

(08:57) Example: Reducing P95 checkout latency with /goal

(09:36) Demo: Using /goal to eliminate Sentry errors in ChatPRD

(13:18) Demo: Burning down Vercel API errors

(17:28) Non-technical use case: Cleaning 3,900 emails with /goal

(21:24) Demo: Using /goal to clean up Linear project tasks

(24:41) When not to use /goal

(26:10) Why /goal changes everything

Tools referenced:

• Codex: https://openai.com/codex/

• Sentry: https://sentry.io/

• Vercel: https://vercel.com/

• Linear: https://linear.app/

Other reference:

• OpenAI blog post “Using Goals in Codex”: https://developers.openai.com/cookbook/examples/codex/using_goals_in_codex

Where to find Claire Vo:

ChatPRD: https://www.chatprd.ai/

Website: https://clairevo.com/

LinkedIn: https://www.linkedin.com/in/clairevo/

X: https://x.com/clairevo

_Production and marketing by https://penname.co/._

_For inquiries about sponsoring the podcast, email [e-mail]._