What is MentionFlow
MentionFlow tracks, explains, and improves how AI assistants talk about your brand. Here is what it does and how these docs are organised.
MentionFlow measures your brand's visibility inside AI answer engines — ChatGPT, Perplexity, Gemini, Google AI Overviews, and more — the same way an SEO tool measures your visibility in classic search. It samples what those engines actually say to real prompts, extracts every brand mention and citation, and turns the results into metrics, receipts, and recommended actions.
Who these docs are for
This documentation serves two audiences from the same pages:
- People who use MentionFlow — marketers, founders, and agencies who want to understand a metric, set up a monitor, or read a report.
- People who build on MentionFlow — developers using the v1 API or the MCP server, and engineers extending the product itself.
Every feature page follows the same shape: what the surface does, how to use it, how it computes what it shows (the denominators, windows, and rounding), its limits, and the related API endpoints. The "how it computes" sections are checked against the code that produces the numbers, so they double as a reference for anyone changing that code.
The model in one minute
A few nouns carry the whole product. The Core concepts page defines them all; the short version:
- A brand (also called a project) is what you track. A workspace owns one or more brands and holds your plan.
- A monitor samples one brand across a market, a set of engines, and a set of prompts on a schedule.
- A prompt is a question you want to watch (for example, "best project management software for agencies").
- A run is the atomic unit of data: one prompt, asked to one engine, in one region, on one day. Each run stores the verbatim answer.
- A receipt is a completed run shown in full — the answer text, the ranked brand mentions, the citations, and any shopping or ad surfaces.
Everything you see — visibility, share of voice, sentiment, sources — is aggregated from runs over a rolling time window.
MentionFlow samples the consumer surfaces of these engines (logged-out, geo-targeted), not their developer APIs, because that is what your customers actually see. The Methodology page explains exactly how each engine is sampled and why.
How to read this section
- New here? Start with the Quickstart — it takes about five minutes to a first monitor.
- Want the vocabulary first? Read Core concepts.
- Deciding on a plan, or hitting a limit? See Plans and quotas.
- Building an integration? Jump to the API and MCP reference.
If you would rather learn inside the product, the in-app Learn academy has interactive walkthroughs of each surface. These docs are the reference layer above them.