> ## Documentation Index > Fetch the complete documentation index at: https://productbrain.io/docs/llms.txt > Use this file to discover all available pages before exploring further. # FAQ > Frequently asked questions about Product Brain, the Chain, MCP, pricing, data storage, and getting started. **Early access** — Answers here summarize intent; your tenant’s limits and toggles win when they differ. [**Join the Product Brain Community**](https://community.productbrain.io) for the live FAQ. ## What is Product Brain? Product Brain is a governed knowledge graph for AI-assisted product work. It gives your agents a shared source of truth: decisions linked to the tensions that caused them, standards linked to the work they constrain, insights linked to the work packages they inform. ## What is the Chain? The Chain is the typed, versioned graph inside Product Brain. It holds decisions, tensions, standards, business rules, architecture entries, work packages, and insights. Each entry has an ID, relationships, and enough structure for agents to query it through MCP before they act. ## How does it work with Cursor, Claude, or Codex? Product Brain exposes the Chain through MCP. Add the MCP configuration to your tool, then **you** ask in plain language and **your agent** calls `orient`, `entries`, `capture`, and session tools—without you re-pasting project history every time. ## Who is it for? Product Brain is for builders and product-led teams doing serious work with AI agents. It is useful when the problem is not missing notes, but scattered context and uncertainty about which decisions are still true. ## What is the Loop? **The Loop** is the working rhythm around the Chain: orient before meaningful work, build with relevant context loaded, capture durable decisions and tensions as they appear, then close the session so the next person or agent starts grounded. See [The Loop](/docs/method/overview). ## Brain Chat vs MCP? **Brain Chat** is the in-app workspace chat ([Brain Chat](/docs/working-in-the-app/brain-chat)). **MCP** is for external agents (Cursor, Claude, ChatGPT, …). They read the same Chain but run in different hosts. ## Import vs paste? **UI import** walks batches through review before commit ([Import & review](/docs/working-in-the-app/import-review)). **`pb ingest`** is CLI-first bulk ingestion for repos—ask your agent when you have filesystem access. ## Is there a free tier? Yes—early builders can start free during beta with generous defaults. Exact caps evolve; see [Pricing](/docs/pricing) and Community announcements. ## Why usage-based pricing? Per-seat pricing punishes collaboration. Product Brain is priced around usage: MCP traffic, Chain writes, and guidance operations. Final meters appear in-app and on the marketing site when billing hardens. ## What data do you store? Product Brain stores your Chain entries and workspace configuration in the managed Product Brain service. Your workspace is isolated. We do not train models on your data or sell it. ## Security, residency, BYOK **Early access stance:** data stays in our managed stack for the hosted beta; region pinning and BYOK are roadmap items—ask in Community before assuming compliance boxes are checked. ## Governance modes (very short) **Open** vs **consensus** changes what happens when an agent “commits.” Sometimes commits create proposals that humans must ratify. Exact behavior is configured per workspace—see in-app settings. ## Can I self-host? Not today. Product Brain is currently a managed service. If self-hosting matters for your organization, raise it in the [community](https://community.productbrain.io). ## How do I get started? Start with [Install pb](/docs/install) if you want the CLI, then [Quickstart](/docs/quickstart), or connect through [MCP overview](/docs/mcp/overview). If setup gets rough, bring the exact error to the community after redacting secrets.