Real AI agent use cases, with sources and setup prompts

Turn the NPCs in a GTA III remake into AI agents

Claude Opus 5.5 built a System 1 / System 2 AI layer into re3, the reverse-engineered GTA III. Type a cheat and nearby NPCs become agents: a fast model picks actions like walk, run, fight, talk or drive while GPT-4.1 mini writes what they say and think.

$4 in / $20 out per 1M tokensDaysAdvancedSource linked

Source

@vladrezdev on X · 2026-10-20

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

What they did

Claude Opus 5.5 built a System 1 / System 2 AI layer into re3, the reverse-engineered GTA III. Type a cheat and nearby NPCs become agents: a fast model picks actions like walk, run, fight, talk or drive while GPT-4.1 mini writes what they say and think.

Result (as claimed)

Demo video in the post.

Tools they used

Cost: Claude Opus 5.5: from $4 in / $20 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 Opus 5.5 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: Turn the NPCs in a GTA III remake into AI agents
What the original author did: Claude Opus 5.5 built a System 1 / System 2 AI layer into re3, the reverse-engineered GTA III. Type a cheat and nearby NPCs become agents: a fast model picks actions like walk, run, fight, talk or drive while GPT-4.1 mini writes what they say and think.
Reported result (as claimed by the author): Demo video in the post.
Source: https://x.com/vladrezdev/status/2112437552183701557
Tools they used: Claude Opus 5.5, GPT-4.1 mini
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 reverse-engineer and revive old devices with AI · How to run multiple coding agents together · How to automate work with n8n and AI

Related use cases