# Selfwin Docs

> Documentation for tracking AI visibility, interpreting Selfwin analytics, and turning lost prompts into approved actions.

Selfwin is an AI visibility analytics product and approval-gated action agent. These pages document behavior implemented in the current product. They do not describe planned features.

## Get started

- [Welcome to Selfwin](https://docs.selfwin.co/introduction.md): Understand what Selfwin tracks, what it calculates, and how its approval-gated AI employee turns evidence into work.
- [Quickstart](https://docs.selfwin.co/quickstart.md): Create a project, choose prompts and model channels, run tracking, and review your first visibility result.
- [How tracking works](https://docs.selfwin.co/tracking.md): Learn how Selfwin runs prompts, separates model channels from model versions, stores evidence, and handles retries and duplicate runs.

## Understand results

- [Metrics overview](https://docs.selfwin.co/metrics.md): Exact definitions for visibility, share of voice, sentiment, position, retrieval, and citation metrics in Selfwin.
- [Overview dashboard](https://docs.selfwin.co/overview.md): Read visibility trends, brand rankings, source distribution, collection coverage, and recent answers from one page.
- [Chats and answer evidence](https://docs.selfwin.co/chats.md): Inspect the collected AI answers that form the denominator and evidence for every Selfwin analytics result.
- [Fanout queries](https://docs.selfwin.co/fanouts.md): See the searches and retrieval targets an AI system used while composing a tracked answer.
- [Sources, domains, and URLs](https://docs.selfwin.co/sources.md): Analyze what AI models retrieve and cite, classify sources, inspect trends, and find gaps between source and brand visibility.

## Configure tracking

- [Prompts, topics, and tags](https://docs.selfwin.co/prompts.md): Build the questions Selfwin tracks, organize them, import them in bulk, and understand prompt-level performance.
- [Competitors](https://docs.selfwin.co/competitors.md): Define tracked brands precisely, review suggestions, and recalculate historical answers when identity rules change.

## Advanced analysis

- [Brand insights](https://docs.selfwin.co/insights.md): Compare a brand across models, topics, tags, countries, competitors, and source retrieval using trends and performance matrices.
- [Brand perception](https://docs.selfwin.co/perception.md): Run an independent market study that measures how strongly AI answers associate each tracked brand with editable attributes.

## Take action

- [Visibility Agent](https://docs.selfwin.co/visibility-agent.md): Understand how Selfwin turns stored tracking evidence into classified gaps, proposed actions, and reviewed drafts.
- [Action queue](https://docs.selfwin.co/actions.md): Review, approve, dismiss, and measure the work proposed by Selfwin without allowing automatic external publishing.

## Operate Selfwin

- [Slack, Claude, and MCP](https://docs.selfwin.co/integrations.md): Connect Selfwin to Slack or an MCP client while preserving project scope, revocable access, and approval boundaries.
- [Project settings](https://docs.selfwin.co/settings.md): Configure project identity, model channels, collection method, schedule, time zone, brand rules, and integrations.

## Complete corpus

- [All Selfwin documentation](https://docs.selfwin.co/llms-full.txt): every documentation page in one Markdown document
- [Selfwin website](https://selfwin.co/landing): product overview and sign in