Early access · beta # Set up your agent. Keep your workflow. One workspace. Your usual agent. Start with a task you already need to do. [Start your workspace ↗](https://work.productbrain.io/sign-up)[Get a free setup call →](#setup-call) Keep working in your connected agent. **Start with the free beta tier.** Included usage during beta. Team pricing is still being defined. [Start yourself ↓](#setup)[Setup help ↓](#setup-call)[Foundation day ↓](#guided)[Beta, data & pricing ↓](#questions) A small trial · a real piece of work ## Connect. Teach. Try a real task. Learn the practice on a task you already need to do. Then let your agent handle the routine. - 01 ### Open a workspace. Create or join your team’s workspace. Find connection details and your API key in Settings. [Create a workspace ↗](https://work.productbrain.io/sign-up) - 02 ### Connect and teach your agent. Claude web or desktop: follow the MCP guide. Terminal agents: install the CLI, then use `pb login` with your workspace key. [Claude connection guide ↗](https://productbrain.io/docs/integrations/claude)[CLI installation guide ↗](https://productbrain.io/docs/install)[Give it the working instructions →](#agent-instructions) - 03 ### Try your first task. Give your agent a real task. It looks up the recorded decisions and reasons—or helps you record your first choice. Reading needs no writing session. [Lookup and draft guide ↗](https://productbrain.io/docs/quickstart) ### Set the foundation. Delegate the routine. - **You set the roles** Fill the workspace’s lead role. Choose the role your agent acts in for this work. - **Teach the practice** Look up context before work; capture as you go. [Choose your capture preference →](/product/#capture-preference) - **Your agent handles the record** It can supply fields and links, then accept within its role when the entry’s requirements are met. [Bring your existing direction and roles →](#team-foundation) Quickstart role and acceptance steps are still incomplete. [Use the free setup call →](#setup-call) The first useful loop · through your agent ### One task. Then a fresh start. - **Work** A real task + relevant context - **Agree** Use an accepted choice, or record a new one - **Reuse** A fresh conversation starts from the record For a new choice: draft first, then accept in the deciding role when requirements are met. Your agent handles the writing session; you remain accountable. The useful check Open a fresh conversation. Can it use the decision and explain why—without you retelling the story? Teach your agent the working practice Add this practice to your agent’s project or workspace instructions, using its connection guide. Set your capture preference together. Use Product Brain as the shared reference for our work. Confirm the workspace and the role this work belongs to; ask if the role is unclear. Read the role in full, orient around the task and open relevant records and history. Explain names and meaning before record codes. Apply existing accepted choices before making new ones; treat drafts as proposals. As we work, capture choices and learning with their reasons, owning role and required links, following my preference to record early or show me first and our team’s rules. Tell me what you recorded and what is still unresolved. Reading needs no writing session. For writes, start a session in the deciding role. Accept only within that role’s authority when the entry’s requirements are met; make unresolved choices and missing requirements visible to me. Consult the record again as new work begins, so another person or agent can build on what we know. A connection alone doesn’t teach the practice. Adapt this instruction to your team. You still need a connected agent, an accountable role and the required context; this instruction does not install or configure them. Free · 20 minutes ## Make the first connection together. Bring a real task. Make the first connection, find relevant context and choose how your agent captures. **Randy Hereman** Founder, Product Brain - Connect your agent - Find one useful record - Choose your capture preference Connection and first steps. Full team setup and strategy work need more time. [Ask Randy for a setup call ↗](mailto:randy@productbrain.io?subject=Free%2020-minute%20Product%20Brain%20setup%20call) 20 minutes · no charge Practical answers ## Before you start. Do I need to use the Product Brain app every day? No. With a supported CLI/MCP connection and working instructions in place, daily lookups, capture and authorised acceptance can happen through your agent, in the environment where you already work. Your agent handles the record; you supply the judgment and remain accountable. Keep its instructions, your roles and the recorded knowledge current as your team learns. Setup and connection support vary by agent. [See supported agents and connection guides →](/product/#practice) Which agents can we use? Claude on web and desktop through the MCP connector. ChatGPT on plans with custom MCP connectors. Claude Code, Cursor and Codex through CLI or MCP; Copilot has instruction-file support. These connections are beta. Only Claude Code has opening briefing hooks; other surfaces look up context as needed. [See the connection differences and guides.](/product/#practice) Check your plan’s connector support; setup varies by surface. What does a team need beyond a connection? Make your purpose, vision, strategy and objectives visible. Define roles, holders and decision scopes. Configure agent instructions and agree how you’ll capture, accept and maintain the record together. Bring what already exists. You can start small and refine the foundation as you learn. Some entries have direction prerequisites. If your direction and roles already exist, use them. The optional foundation day is for teams that want help making them clear—not a prerequisite for trying the beta. Can my agent accept knowledge for me? Yes. Your agent can accept any kind of entry within the authority of the role its session acts in, once the entry’s requirements are met. Holding several roles does not give one session all of their authority. It’s recorded as acting for you; you remain accountable and can confirm it yourself. A draft isn’t accepted knowledge. Acceptance establishes the agreement; completing the work is a separate state. What if we don’t know who decides? The owning role decides. An unfilled owning role falls back to the nearest filled Team Lead role up that team’s hierarchy. An entry without an owner uses the applicable Team Lead fallback. - Your team’s lead - Then a parent team’s lead - Then the organisation’s lead The organisation’s root Team Lead must always have a holder. This fallback covers an empty role; it doesn’t override a filled owner. Broken or ambiguous ownership needs correction before the change can proceed. Not your role? The change is refused and you’re told who decides. Raise a tension or ask the owner. Who keeps it current? Does everyone get updates? Your configured agent can look up context, capture learning and accept knowledge within its acting role as you work. Your team decides what belongs in the record and keeps direction and roles current. Possible contradiction flags invite review; they don’t decide or guarantee alignment. Changes aren’t pushed into every active session. Teach your agent to consult the record when it acts. Who can see our data? Use the workspace for records intended for its members. Role ownership governs acceptance and changes; connected agents need authenticated access and writes need the appropriate role/session. Private-draft access is changing, so current beta drafts should not be treated as a confidentiality boundary. Product Brain does not train AI models on your workspace data. Service providers process data in the US as described in the [privacy policy](https://work.productbrain.io/privacy-policy). Can we export the whole workspace? **Complete workspace export is not currently supported.** CLI and MCP let you read individual records, but that is not a complete export of entries, relations and history. If a full export is a requirement for your team, discuss it with Randy before putting important knowledge into the beta. What does the software cost? You can start with the free beta tier and included usage. Final team software pricing is still being defined, separately from the founder-led service. Ask Randy about your team’s requirements and software costs before committing to a paid engagement. The foundation day is optional; it isn’t the price of trying Product Brain. Optional · founder-led ## Team foundation day. €5,000 Optional service · software separate One day + 2h, 1h and 1h follow-ups Make existing direction and authority visible. Sharpen the gaps. Practise together. ### Direction Purpose, vision, company and product strategy, initial objectives and key results. ### Starting governance Roles, holders and decision scopes, grounded in how your team works. ### First practice Connect your agents, choose capture preferences and practise on a real task. **1 day** Foundation + training **2h** Follow-up **1h** Follow-up **1h** Follow-up Bring the founder or accountable lead and the people shaping strategy and roles. You own the choices. A working foundation is the goal, not a proven one-day outcome. Follow-ups focus on what’s needed. Agree dates, scope and tax before booking. Software is separate. [Discuss the foundation day ↗](mailto:randy@productbrain.io?subject=Team%20foundation%20day) ## Try it with the work you already have. Connect your agent yourself, or make the first connection with us. [Start your workspace ↗](https://work.productbrain.io/sign-up)[Get a free setup call →](#setup-call)