Use research to add a historical scenario to a game remake

Nate Combs had ChatGPT collect background on Alesia, then used Claude Code to turn that material into a playable add-on for a 1990s game remake.

Done with Claude Code· Intermediate

What they did
Combs started by having ChatGPT gather historical context on the battle of Alesia and draft instructions for the coding agent. Claude Code used that package of information to create a new scenario for a remake of an old 1990s video game, with the battlefield layout rebuilt from written references ChatGPT surfaced. Those references included a Caesar translation, The Latin Library, Britannica, and a French archaeology museum. Combs then played through it, pointed out issues, and Claude Code adjusted the content.
How it went
He described the result as strange but engaging and shared screenshots of it. At the time he posted, testing was still underway, so there was no final outcome or performance metric.
Tips
A two-step handoff can help when one agent is better at gathering source material and another is better at implementation. If the work depends on history, keep the sources visible so you can check the structure as the agent builds.

Try it yourself with Claude Code

First, gather trustworthy background on [historical event, place, or battle] from a few text-based sources and turn it into a short brief for a coding agent. Then use that brief to build [feature, level, scenario, expansion] for [game/project], including any map, timeline, or layout details that matter. Before you make or change anything that would be hard to undo—such as deleting files, submitting content, sending a build, or making a payment—pause and ask me to approve the plan. After I review it, continue, then wait for my playtest notes and revise the work based on my feedback.

Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.

Get 3 agent uses like this every morning

With the day's top AI news. Free, and one click to unsubscribe.