Forge Mentor FAQ

Setup and AI assistants

What is MCP, and do I need to understand it?

MCP (Model Context Protocol) is a standard way for AI assistants to talk to outside tools. Think of it as a USB port for your AI: once it's plugged in, the assistant gains new abilities. You don't need to understand the protocol to use Forge Mentor. You only need to paste one URL into your assistant's settings, or run a single setup command. No coding, no JSON files.

Which AI assistants can I use?

Eight, out of the box: Claude Desktop, ChatGPT, Microsoft Copilot Studio, Gemini CLI, Codex, Claude Code, Cursor, and Windsurf. The desktop and web clients take a URL; the CLI clients use a one-line npx command. Free ChatGPT accounts can't add MCP servers yet; everything else works.

Do I need to install software, API keys, or config files?

No. For desktop clients you paste https://mcp.mentor4ai.app/mcp. For CLI clients there's a one-line npx @brain-mcps/setup ... that writes the right config for you. Authentication is a magic link sent to the email you signed up with.

What changes inside my chat once it's connected?

Your assistant gains a new set of tools and starts behaving like it has a senior business coach inside it. When you ask it to work on a business idea, it stops improvising and follows a methodology with concrete criteria: asking the right questions for the right stage, recording what you tell it, and refusing to advance until the evidence is there.

Can I use my existing AI subscription?

Yes. Forge Mentor isn't a separate chat product; it's something your current assistant gains access to. Bring your own Claude, ChatGPT, Gemini, etc. We never see, store, or proxy your assistant's traffic; our server only receives the methodology tool calls and the payload you choose to store.

How the methodology works

What is Forge Mentor, in one paragraph?

It's a business-development methodology that walks you from "I have a hunch" to "I'm selling and learning what to change." It refuses to let you hide behind frameworks: every stage has criteria that have to be met before you advance, and the mentor always points to the next concrete move. The core idea: a business is always an experiment, and selling is the only real validation.

What does the experience look like?

You bring the mentor a business idea you want to develop, whether it's a hunch, an early-stage venture, or something you're already running. From there the methodology walks you through guided phases, each one with criteria that have to be met before you advance. The mentor asks indirectly when it needs to surface what you've been assuming, and directly when it's time to commit to a move. The bulk of the work eventually becomes a loop: try something concrete with real people, learn from the result, adjust.

What do I get along the way?

Concrete artifacts at every iteration: a structured opportunity statement, a refined offer, short and long pitches you can drop into a DM or a landing page, an MVP designed for what you actually have, a price range derived from how customers perceive value, a financial model with a clear runway number, and a quick health check of where the business stands. Everything lives in a single business document you can return to.

What if I pause halfway through?

You don't lose progress. Every business is saved continuously. The next session, ask your mentor to resume; it reads where you stopped and picks up the conversation. You can keep multiple businesses in the registry at once and switch between them.

AI behavior and safety

What stops the assistant from hallucinating bad advice?

Two things. First, the methodology constrains how the assistant moves: stage gates have to be met before advancing, and it can't freelance an answer at you. Second, anything from external sources is recorded as unverified until you confirm it; unverified information can't drive your decisions, it can only flag a possible discrepancy for you to weigh in on. Your judgment stays the source of truth.

Does the assistant make decisions for me?

No. The methodology surfaces what's working, what isn't, and what might need to change. The decision (pivot, persist, kill, double down) stays with you.

Data, privacy, and cost

Where does my business data actually live?

Everything you record about a business (the opportunity, the offer, the experiments, the financial model) lives in a single business document stored on our servers, so you can resume across sessions and devices, and access it from your dashboard. We don't store your chat transcript with the assistant. We don't sell, share, or train on your content. During the alpha, the only humans who ever look at your data are us, and only when you explicitly send feedback or report a bug.

What does it cost?

There's a 15-day free trial when public access opens. During the current alpha, invited testers get free access with no trial timer running. We want feedback from real users before we lock pricing; alpha testers will get advance notice and a fair offer before anything ever moves to paid.

Alpha and support

What does "alpha" mean for me as a user?

The methodology works and the connection is stable, but rough edges are guaranteed. Some clients (especially newer ChatGPT MCP support) behave differently. Some surfaces (dashboards, billing, notifications) are still being polished. Feedback during this window has outsized influence on the final product.

How do I give feedback or report a bug?

The fastest path is inside the chat itself. Say "I have feedback about this experience" and the assistant submits it through the methodology's feedback tool: no separate form, no separate inbox. You can also reply directly to your alpha invite email; it goes to a real human.