KnitKnot
You are reading the agent-optimized layer of this page: the literal markdown we serve to AI crawlers and assistants, shipped in the page source of every visit. Making sure AI reads the right facts about a company is literally what KnitKnot does.

# KnitKnot Documentation

Product documentation for KnitKnot, the AI Presence Management platform.

## Getting started

## Core concepts

## Guides

## Reference

  • - Metrics reference: Exact definitions of every number in your report — AI Presence Score, coverage, visibility rate, win rate, and sentiment — and how each is computed.
    Markdown mirror: https://knitknot.ai/docs/metrics-reference.md
  • - Engines: The four AI engines every benchmark runs through, how responses are captured, and why the model version is recorded on each one.
    Markdown mirror: https://knitknot.ai/docs/engines.md
  • - Glossary: Quick definitions of the core KnitKnot terms — subject, prompt, run, evaluation, issue, playbook, and the rest — each linked to a fuller explanation.
    Markdown mirror: https://knitknot.ai/docs/glossary.md

## FAQ

  • - Frequently asked questions: Straight answers to the most common questions about how KnitKnot measures your AI presence, how accurate it is, and how to act on it.
    Markdown mirror: https://knitknot.ai/docs/faq.md

Full site content in one file: https://knitknot.ai/llms-full.txt

Raw mirror of this content: /llms.txt. Site-wide summary: /llms.txt · full content: /llms-full.txt

Docs navigation

Documentation

Everything you need to run AI benchmarks, read your report, and improve how AI represents your company.

Getting started

  1. Getting started with KnitKnot

    What KnitKnot does, how the benchmark → report → fix loop works, and what to expect in your first week.

  2. Run your first benchmark

    Check your company profile, competitors, and prompt library, then start a run and follow it live.

  3. Read your report

    What the AI Presence Score means, how to read wins and losses, and how to drill from a headline number to the exact AI response behind it.

Core concepts

  1. The AI Presence Score

    How the 0–100 score is composed, what visibility and win rate measure, and why the trend matters more than any single reading.

  2. Subjects — brands and products

    How KnitKnot models your brand and its products separately, and why a multi-product company needs both.

  3. The prompt library

    Where evaluation prompts come from, why they persist across runs, and how to curate them.

  4. Runs and scoring

    What happens during a benchmark run — real AI responses, claim-level scoring, and evidence you can audit.

  5. Issues and playbooks

    How benchmark gaps become persistent issues, how playbooks turn them into content actions, and how later full benchmarks measure change.

Guides

  1. Manage your prompt library

    How to add, generate, star, and archive the evaluation prompts every benchmark runs — and why a stable library keeps your score comparable over time.

  2. Manage competitors

    How to add and remove the competitors AI compares you against, why the set matters more than its size, and what happens when you add one.

  3. Benchmark products separately

    How to add a product so it gets its own prompts, competitors, and report section — and how per-product results roll up under your brand.

  4. Run and schedule benchmarks

    How to trigger a benchmark manually, put it on a recurring schedule, and read benchmarks as the periods that drive your score trend.

  5. Share your report

    How to publish a report to a public link anyone can open, and how the shared page relates to the report you see in the console.

  6. Connect to your AI tools (MCP)

    How to reach your KnitKnot workspace from Claude, ChatGPT, or any MCP-capable client — so you can query your benchmark and act on it without leaving your assistant.

Reference

  1. Metrics reference

    Exact definitions of every number in your report — AI Presence Score, coverage, visibility rate, win rate, and sentiment — and how each is computed.

  2. Engines

    The four AI engines every benchmark runs through, how responses are captured, and why the model version is recorded on each one.

  3. Glossary

    Quick definitions of the core KnitKnot terms — subject, prompt, run, evaluation, issue, playbook, and the rest — each linked to a fuller explanation.

FAQ

  1. Frequently asked questions

    Straight answers to the most common questions about how KnitKnot measures your AI presence, how accurate it is, and how to act on it.