Permissions

Before you start

• A connected AI tool. The permissions it asked for are listed under Settings → MCP client access.

Steps

1. Know what SwiftCNS drafts

   SwiftCNS drafts the assumptions, hypotheses, experiment designs and their success criteria, the tracker's row unit, and the Learning's observations and insights. Your tool needs Read CNS and Update CNS to ask for these.

2. Know what commits you

   Every step that commits you is a choice on a card: selecting assumptions, a hypothesis and an experiment; assigning and approving it; setting up and completing the tracker; publishing the Learning; recording the decision. Submitting these needs Make decisions.

3. Choose how much to delegate

   With Make decisions, your tool can submit those choices when you tell it to. Without it, your tool asks and you act in the app. Either way, SwiftCNS records who did what. The result and the decision should always be your own call.

4. Disconnect a tool

   In Settings → MCP client access, find it under Authorized applications and remove it. Access tokens may stay usable for up to 5 minutes.

What you get

Your tool never sees more than you can. Access is checked per workspace, project and conversation. See Security and data.

Done when

• You know which steps you'll take yourself and which you'll delegate.
• Your tool's permissions match that choice.

Common mistakes

• Delegating the success criteria. Approve those yourself. They're what your result will be judged against.
• Assuming a recorded decision is carried out. Recording doesn't execute anything. Your team still does the work.

For agents: MCP tools and gotchas

• Scopes: cns:read, cns:write, cns:decide, cns:sources:read. Each step lists its scope in actionOperations[].requiredScopes.
• Submit with the active actionRequestId and contractVersion. On an uncertain response, replay with identical input; changed input conflicts.
• If browserRequired is true, send the user to browserUrl.

Next

Teach your AI tool when to use SwiftCNS.