Real AI agent use cases, with sources and setup prompts

Compare the cost of building the same game with three coding agents

The same Tetris prompt went to Claude Code (Opus 5.5), Codex (GPT-6.1 Sol) and a DeepSeek harness (V4 Pro), timing each run and its cost.

$17/mo5 minBeginnerSource linked

Source

@gogetit1214 on X · 2026-10-20

Written in our own words. Credit to the original author. Link checked 2026-10-20.

What they did

The same Tetris prompt went to Claude Code (Opus 5.5), Codex (GPT-6.1 Sol) and a DeepSeek harness (V4 Pro), timing each run and its cost.

Result (as claimed)

All three shipped a playable game with an AI that clears lines: Claude Code 3:58 for $0.60, Codex 3:25 for $0.16, DeepSeek 3:24 for $0.26.

Tools they used

Claude CodeOpenAI CodexDeepSeek V4 Pro

Cost: Claude Code: from $17/mo; OpenAI Codex: free plan, paid from $8/mo; DeepSeek V4 Pro: from $1.32 in / $3.96 out per 1M tokens.

Set it up

  1. Write a one-page brief

    Describe the app in plain words: who it is for, the 3 core screens or actions, and what "done" looks like.

  2. Start the project with your agent

    Open Claude Code and paste the brief. Ask it to propose a stack and a file plan before writing code.

  3. Build one slice at a time

    Ship the smallest working flow first, run it, then add features one by one. Commit after each working step.

  4. Test it like a user

    Click through on desktop and phone. Ask the agent to add basic tests and fix anything that breaks.

  5. Check security and ship

    Keep keys in environment variables, check auth and database rules, then deploy and share the link.

Copy the full setup prompt

Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.

You are helping me set up this AI use case end to end in Claude Code.

Goal: Compare the cost of building the same game with three coding agents
What the original author did: The same Tetris prompt went to Claude Code (Opus 5.5), Codex (GPT-6.1 Sol) and a DeepSeek harness (V4 Pro), timing each run and its cost.
Reported result (as claimed by the author): All three shipped a playable game with an AI that clears lines: Claude Code 3:58 for $0.60, Codex 3:25 for $0.16, DeepSeek 3:24 for $0.26.
Source: https://x.com/gogetit1214/status/2112349465508204963
Tools they used: Claude Code, OpenAI Codex, DeepSeek V4 Pro
Category: Vibe coding & apps

Please:
1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like).
2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure.
3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data.
4. Finish with a checklist to run it again next time.

The Daily 5

Get five new use cases tomorrow morning

Free. Real sources. Unsubscribe any time.

Guides for this use case

How to run multiple coding agents together · How to vibe code an app with Claude Code · How to use Claude Code and Codex together · How to make a Godot, Unity or 3D game with AI agents

Related use cases