Step-by-step Codex workflows from How I AI expert interviews. Each guide includes prompts, code snippets, and practical tips.
Use the advanced coding capabilities of GPT-6 Astra to reverse-engineer and control a closed-API hardware device like a Divoom Bluetooth speaker. Build a custom web app and CLI to programmatically interact with your hardware.
Use GPT-6 Astra's computer use capabilities to take over your browser and automate a complex lead routing and email drafting workflow in a node-based CRM. Turn hours of manual UI work into minutes of hands-off automation.
Use a hybrid AI workflow to bridge design and development. Generate high-level design concepts and tokens with Claude, then use Codex for robust implementation of the technical components in your codebase.
A guide for solo entrepreneurs to manage business operations using AI. Learn how to source manufacturers, build and maintain an e-commerce site, and replace dashboards with voice commands, all without a human team.
Turn a complex, artistic concept into a manufacturable 3D model. This workflow shows how to use AI to generate a design from a photo and then create CAD files for 3D printing, even for previously 'unmanufacturable' items.
Process a bounded set of LinkedIn requests with explicit acceptance rules and a reviewable action log.
Turn a source video into several short social clips by specifying the audience, moments, pacing, and export format.
Build a gamified homework tracker from a PRD that defines the child experience, parent controls, rewards, and completion states.
Create a specialized AI agent to automatically investigate and triage bug reports from Sentry. This harness uses the Claude Agent SDK to gather evidence, identify root causes, and generate actionable engineering reports.
Use an AI agent with browsing capabilities to automate the tedious process of finding valuable, underpriced collectible cards on eBay, turning hours of manual search into an automated background task.
Use a Codex Automation to create a 'meta-agent' that analyzes your codebase, identifies opportunities for new reusable agent skills, and then spawns sub-agents to automatically test and validate those new skills.
Leverage powerful AI coding agents to perform deep, exhaustive benchmarking on complex infrastructure problems. This workflow automates the process of testing numerous solutions, like different database engines or index types, to find the optimal configuration without manual effort.
Turn a spoken feature idea into a versioned Markdown spec, then let a coding agent implement and verify it. Future changes start in the spec, which records the behavior and its history.
With a background coding agent connected to Notion, turn a short task and screenshot into a GitHub pull request, live preview, test notes, and UI verification in about 20 minutes.
Use Claude Code or Codex to build a private, interlinked learning site for a subject you want to understand. Choose the audience and depth, generate a map of the field, and keep revising the structure as your questions become more specific.
Infer an undocumented device protocol from captured traffic and turn the confirmed message structure into a small control tool.
Delegate a long data migration with explicit invariants, checkpoints, validation queries, and a reversible cutover.
Turn a vulnerability report into scoped code fixes, tests, and a traceable remediation record.
Move a running page into Figma as editable design, let the team refine it together, then give the updated frame URL back to a coding agent so it can apply the design to the local codebase.
Pair Opus 4.6 as the eager builder with GPT-5.3 Codex as the rigorous reviewer: let one create the broad change, then let the other challenge its architecture, performance, and edge cases before shipping.
Use one model to build quickly and a second model to review the diff for plan mismatches, code smells, and better architecture before applying the fixes.
Use a reusable Plans.md rubric to make Codex produce a self-contained, milestone based implementation plan for a complex change. Alex plans a Python SDK from an existing TypeScript SDK before asking Codex to build it.
Give parallel Codex tasks separate Git worktrees so each agent has its own branch and directory. Alex creates French and German variants, runs both at once, and keeps their changes independently testable.
Open an unfamiliar repository in Codex, ask how to run it, launch the app with the returned command, and make a small behavior change in plain language while Codex traces the relevant code.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.