Gist

Fix how AI describes your product

See how ChatGPT and Claude describe your product. Find the gaps, then fix them.

Why gist.design

AI tools read your code but not the decisions behind it. They fill gaps with competitor patterns and wrong positioning. gist.design is a structured file that captures design decisions, positioning, and boundaries so AI tools get it right.

Without gist.designWhat prevents it
AI coding tool builds auto-execute when you designed for user approvalDesign Decisions: "chose X over Y because Z"
AI fills gaps with competitor patterns your product deliberately avoidsNot This: explicit boundaries on what this is not
LLM recommends your product to the wrong audiencePositioning: who it's for and who it's not for
LLM describes your product as a clone of a competitorPositioning: vs comparisons with honest differences

How it works

Three steps. One file that fixes how AI understands your product.

ChatGPT

62%

Claude

45%

Perplexity

58%

Gaps found

Positioninghigh
Design decisionshigh
Audience targetingmed
01

Discover the gaps

See how ChatGPT, Claude, and Perplexity describe your product from your website alone. Find where they guess wrong, miss features, or confuse you with a competitor.

Integrations

Cursor

@Docs → Add new doc → paste your gist.design URL

Claude Code

Install the gist-design skill to generate files natively, or drop one in your repo root.

GitHub Copilot

Place file in repo root

ChatGPT

Paste URL or upload file for accurate product recommendations

Works with Figma MCP

Figma MCP gives structure. gist.design gives intent. Together they produce accurate implementation.

Structure
+
Intent
=
Accurate

How does this relate to llms.txt?

They're complementary. Use both.

llms.txt

What it does

A README for LLMs. Features, links, how to use it.

“Acme is a project management tool with kanban boards.”

gist.design

How to talk about it

Positioning, boundaries, and design rationale. Stops LLMs from getting your product wrong.

“Not for enterprise. No Gantt charts by design. Chose manual scheduling because teams want control.”

Principles

What makes a gist.design file useful.

Chose X over Y
The button is blue
Because Z matters

Decisions over descriptions

“We chose X over Y because Z” is useful. “The button is blue” is not.

Specific
HighMedLow

3-tier badge next to each suggestion

vs
Generic

“uses confidence visualization”

Specific over generic

“Confidence scores appear as a 3-tier badge next to each suggestion,” not “uses confidence visualization.”

Auto-execute
Competitor pattern
Generic defaults

Negative space matters

What it's NOT prevents AI from filling gaps with competitor patterns.

/
features/
auth.gist.design
search.gist.design
checkout.gist.design
gist.design

One file per feature

One file per significant feature. Keeps each file focused and useful.

We chose approval over auto-execute...
.gist.design

Generated, not written

The tool handles the format. You handle the thinking.

Reference

TopicDetails
robots.txtCrawlers — What can you access?
sitemap.xmlSearch engines — What pages exist?
llms.txtLLMs — What does this product do?
gist.designLLMs — How should you talk about this product? Positioning, boundaries, audience, design rationale
File placement/gist.design in the project root, or /features/[name]/gist.design for multi-feature products
SpecOpen for community input. Pattern research at aiuxdesign.guide

Create your gist.design file

Fix the gaps AI gets wrong about your product.