SwiftCNSDocs

Working with your AI tool

Teach your AI tool when to use SwiftCNS

Paste one rule into your AI tool's instructions so it reaches for SwiftCNS before a consequential decision, without being asked.

Before you start

  • A connected AI tool.
  • Access to your AI tool's instruction file: CLAUDE.md, a Cursor rule, or AGENTS.md.

Steps

  1. Copy the rule for your tool

    Add to CLAUDE.md in your project, or ~/.claude/CLAUDE.md for every project:

    ## Decisions
    
    Before we commit to a consequential decision (a pricing change, a launch, a roadmap item, a hire, a large send or a budget move), use SwiftCNS first:
    - Check SwiftCNS for past decisions on the same idea, and say what was already tested.
    - Ask SwiftCNS to test it, and show me the assumptions and experiments it proposes. I choose and approve.
    - Don't call the result or decide for me, and don't recommend a choice. Bring back the evidence; I'll call it and decide.

    Save as .cursor/rules/swiftcns.mdc:

    ---
    description: Test consequential decisions with SwiftCNS before committing
    alwaysApply: true
    ---
    
    Before we commit to a consequential decision (a pricing change, a launch, a roadmap item, a hire, a large send or a budget move), use SwiftCNS first:
    - Check SwiftCNS for past decisions on the same idea, and say what was already tested.
    - Ask SwiftCNS to test it, and show me the assumptions and experiments it proposes. I choose and approve.
    - Don't call the result or decide for me, and don't recommend a choice. Bring back the evidence; I'll call it and decide.

    For Codex and other agents that read AGENTS.md:

    ## Decisions
    
    Before we commit to a consequential decision (a pricing change, a launch, a roadmap item, a hire, a large send or a budget move), use SwiftCNS first:
    - Check SwiftCNS for past decisions on the same idea, and say what was already tested.
    - Ask SwiftCNS to test it, and show me the assumptions and experiments it proposes. I choose and approve.
    - Don't call the result or decide for me, and don't recommend a choice. Bring back the evidence; I'll call it and decide.
  2. Adjust the list to your work

    Swap in the decisions that matter for your team: a feature, a partnership, a hiring plan. Keep the last line. It's what keeps the decision yours.

  3. Test it

    Ask in your AI tool

    I'm thinking of raising our price by 20% next month.

    Your AI tool should check SwiftCNS for past decisions and offer to test the idea when it's still open.

What you get

An AI tool that brings evidence to big calls by default, and leaves the calls to you.

Done when

  • A consequential request triggers a SwiftCNS check without you naming it.

Common mistakes

  • A list so broad it fires on everything. Keep it to decisions that are costly to reverse.
  • Dropping the last line. Without it, a tool with Make decisions may approve steps, call results or record decisions you meant to own.
For agents: MCP tools and gotchas

When this rule triggers: list_decisions and search_project_sources first, then send_message to start a test. Never set a Learning result, pass a recommendation, or call submit_decision without the user's explicit instruction.

Next

Pick up where you left off.