Docs navigation
KnitKnot index
Documentation
Run a competitive benchmark, inspect the claims and sources behind each result, and choose the response workflow your team needs.
Getting started
-
Getting started with KnitKnot
Set up the benchmark, read the answers behind your results, and choose a supported next step.
-
Read your Overview
Use the latest benchmark, competitive trends, cited pages, playbooks, and observed reach without mixing their different measurements.
-
Run your first benchmark
Confirm the setup inputs, choose the engines available to you, and follow the first run.
-
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
-
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.
-
Subjects: brands and products
How KnitKnot models your brand and its products separately, and why a multi-product company needs both.
-
Benchmark questions
Where benchmark questions come from, how the budget is split across topics by real buyer demand, and what a given library size can honestly claim.
-
Runs and scoring
What happens during a benchmark run: real AI responses, claim-level scoring, and evidence you can audit.
-
Issues and playbooks
Turn benchmark losses and damaging claims into issues and customer-managed response plans.
Guides
-
Manage benchmark questions
How to add, star, and archive the prompts your benchmarks run, and why a stable set helps comparison.
-
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.
-
Benchmark products separately
How to add a product so it gets its own questions, competitors, and report section, and how per-product results roll up under your brand.
-
Read search demand by topic and keyword
Find the searches behind a buyer topic, read its opportunity score, and open the benchmark questions grounded in a keyword.
-
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.
-
Share your report
Create an evidence-backed issue report, review its draft, and publish or unpublish its public link.
-
Connect to your AI tools (MCP)
Connect an OAuth-capable assistant to your KnitKnot workspace and query benchmark evidence from it.
-
Read your company profile
Check the researched positioning, market story, differentiators, and dated company updates behind your workspace.
-
Review and approve company facts
Add a fact to the ledger, check its source and observations, and decide whether KnitKnot may use it in published content.
-
Review discovered candidates
Check new competitors, capabilities, themes, buyer roles, dimensions, and facts before adding them to your company record.
-
Investigate a claim in an AI answer
Start with a claim gap, open the captured answer, check the source signal, and compare the wording with your company facts.
-
Find a content coverage gap
Read the topic and content-type map, open the pages behind a gap, and decide whether the missing page matters.
-
Work an issue and ship a playbook
Check a tracked issue, use its linked plan, record the page you shipped, and read the next benchmark.
-
Read agent activity and AI referrals
Separate agent fetches, customer-domain tool calls, and visits from AI answers in the Traffic view.
-
Review a proposed Agent version update
Compare a proposed page change with its current text, approve or reject it, and read the cycle record after publication.
-
Inspect ChatGPT retrieval queries
See the search queries ChatGPT exposed during a benchmark, trace each one to a tracked question, and avoid reading query counts as search demand.
-
Check whether AI agents can read your site
Read the Content Access checks, open a failing domain or page finding, and tell a site problem from a scanner failure.
-
Invite teammates and manage access
Invite someone to your workspace, change their account role, or remove their workspace access.
-
Connect workspace integrations
Set up analytics, agent activity, playbook destinations, article drafts, and the weekly Slack digest from Settings.
-
Update workspace details and your profile
Change the names your team sees, manage the workspace URL, and update your own name or photo.
-
Read themes across cited pages
Find patterns that recur across cited pages, buyer questions, and topics, then inspect the underlying evidence before acting.
-
Manage customer-domain agent interfaces
Read the desired and effective state of Agent feed, customer-domain MCP, and content indexes, and understand when an endpoint is live.
-
Trace a cited source
Find the pages AI cited, see who owns them, and follow a citation back to a measured answer.
-
Review the pages you own
Find an owned page, check whether it is readable and cited, and inspect the evidence behind its health and answer signals.
-
Read the Agent Ledger
Check which owned pages have an Agent version, its current state, version number, fact references, and publication date.
-
Read vocabulary gaps
Find terms used by cited pages but absent from your pages, then inspect the pages and answers before changing your copy.
-
Check Agent version delivery
Confirm whether Agent versions are live, inspect verification, and read which responses used an Agent version or the original page.
-
Manage authority sources
Add company websites and documents that KnitKnot can use to check claims and support playbooks.
-
Read Agent tool calls
See which customer-domain MCP tools agents called, separate tool use from setup handshakes, and check delivery when data is missing.
Reference
-
Metrics reference
Exact definitions of every number in your report: AI Presence Score, coverage, visibility rate, win rate, sentiment, and how each is computed.
-
Engines
The AI engines KnitKnot supports, how to choose those available on your plan, and what a captured response records.
-
Glossary
Quick definitions of the core KnitKnot terms: subject, question, run, answer, issue, playbook, and the rest, each linked to a fuller explanation.
-
MCP tools reference
Every customer-facing tool in the KnitKnot MCP server: what each does, its parameters, and what it returns, so you or your AI assistant know exactly which tool to call.