Gauntlet Loop

A 3D shooter autonomously developed by Grok 4.6 using the Gauntlet Loop method.

Playable

Gauntlet Loop media is blocked

Allow external media to connect to the provider and play this content.

Description

A 3D first-person shooter featuring movement and combat mechanics, with an on-screen HUD displaying ammunition counts for an 'M4A1 AUTO' weapon. The game was built autonomously by Grok 4.6 during a continuous 48-hour development session using a 'Gauntlet Loop' iterative process.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.

Details

Why this is interesting: Demonstrates the capability of frontier models to build functional, multi-day game projects from a single prompt.
Built with: Opus 5 Opus 4.8 Opus 4.7 LTX 2.3 Pro 3.1 Pro Opus 4.6 Seedream 5.0 Pro Vidu Q3 Pro Seedance 1.5 Pro Flux 2 Pro Opus 4.5 Nano Banana Pro Gemini 3 Pro Grok 4.6
Links: somethingbig.ai
View tweet
Tags: #fps #grok #gamedev #gauntlet-loop

Discovered: X
First posted: X · Aug 16, 2026
Listed: Added 9d ago
Build: Strong
Models: Strong

Prompt

I want to run a Gauntlet Loop for this goal: [GOAL]

Possible references or quality bars: [OPTIONAL REFERENCES]

Choose the strongest concrete bar that an agent can actually inspect and compare its work against. If I have not supplied one, propose a useful comp or measurement that plays the same role for this task that real Call of Duty screenshots played for Matt Shumer's Claude of Duty game (read the prompt: https://github.com/mshumer/Claude-of-Duty/blob/main/prompt.md). Explain the bar in one sentence. Then write a short prompt for Claude Code or Codex in the style of Matt's prompt (minimal is better here, we want the agent to decide the specifics!).

Give the lead agent the goal and the bar, but let it choose the approach. Tell it to divide the goal into the smallest pieces that can be improved and judged independently. For each important piece, it should fan out a builder and a separate critic with fresh context. Each critic must inspect the real output, compare it directly with the bar—using a blind A/B comparison when possible—identify the biggest remaining gap, and send it back for another round. Keep looping until our output wins or I stop the run. Have the lead agent maintain a simple live progress page that shows the work evolving over time. Have it use subagents and ultracode. Do not prescribe the architecture, exact decomposition, or a fixed number of rounds. Keep the final prompt short, just like Matt's.

Source

All projects

Games

Gauntlet Loop

A 3D shooter autonomously developed by Grok 4.6 using the Gauntlet Loop method.

Playable

Gauntlet Loop media is blocked

Allow external media to connect to the provider and play this content.

Description

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.

Details

Why this is interesting: Demonstrates the capability of frontier models to build functional, multi-day game projects from a single prompt.
Built with: Opus 5 Opus 4.8 Opus 4.7 LTX 2.3 Pro 3.1 Pro Opus 4.6 Seedream 5.0 Pro Vidu Q3 Pro Seedance 1.5 Pro Flux 2 Pro Opus 4.5 Nano Banana Pro Gemini 3 Pro Grok 4.6
Links: somethingbig.ai
View tweet
Tags: #fps #grok #gamedev #gauntlet-loop

Discovered: X
First posted: X · Aug 16, 2026
Listed: Added 9d ago
Build: Strong
Models: Strong

Prompt

I want to run a Gauntlet Loop for this goal: [GOAL]

Possible references or quality bars: [OPTIONAL REFERENCES]

Choose the strongest concrete bar that an agent can actually inspect and compare its work against. If I have not supplied one, propose a useful comp or measurement that plays the same role for this task that real Call of Duty screenshots played for Matt Shumer's Claude of Duty game (read the prompt: https://github.com/mshumer/Claude-of-Duty/blob/main/prompt.md). Explain the bar in one sentence. Then write a short prompt for Claude Code or Codex in the style of Matt's prompt (minimal is better here, we want the agent to decide the specifics!).

Give the lead agent the goal and the bar, but let it choose the approach. Tell it to divide the goal into the smallest pieces that can be improved and judged independently. For each important piece, it should fan out a builder and a separate critic with fresh context. Each critic must inspect the real output, compare it directly with the bar—using a blind A/B comparison when possible—identify the biggest remaining gap, and send it back for another round. Keep looping until our output wins or I stop the run. Have the lead agent maintain a simple live progress page that shows the work evolving over time. Have it use subagents and ultracode. Do not prescribe the architecture, exact decomposition, or a fixed number of rounds. Keep the final prompt short, just like Matt's.

Source

Gauntlet Loop

Description

Timeline

Gauntlet Loop

Description

Timeline