Decision Memo

Make a decision you can defend later. The AI drives Options and a recommendation checkpoint, then records the call.

Universal 4 steps 1 checkpoint Human approval Self-correcting
Use this workflow

Free to start · runs with your own AI

Workflow steps

Runs inside your AI conversation · the orchestrator drives

"Help me decide whether to build or buy this tool"

you — in any AI chat

  1. 1

    Frame

    Frame the decision before exploring options.

    Capture:

    • The decision — what exactly is being decided, in one sentence
    • The context — why this is on the table now
    • The stakes — what a good or bad call affects
    • The decision criteria — what a good outcome must satisfy, in
      priority order (cost, speed, risk, fit, reversibility)
    • The deadline and who owns the final call

    A decision with no stated criteria cannot be evaluated. If criteria are
    unclear, agree them with the operator before advancing.

    Save the framing as a task note with task_notes_add. The next step —
    Options — reads this note.

  2. 2

    Options

    Read the task notes with task_notes_list — the note from the Frame
    step contains the decision, stakes, and criteria. Work from it.

    Lay out the realistic options. What good looks like:

    • Each genuine option named, including "do nothing" where relevant
    • For each: how it scores against the stated criteria
    • The trade-offs — what you gain and give up with each
    • Risks and how reversible each path is
    • Any evidence or research backing the assessment

    Be even-handed — do not stack the deck toward a favorite. If a research
    report informs this, pull from its findings.

    Save the options and their trade-offs as a task note with
    task_notes_add. The Recommendation step reads this note.

  3. 3

    Recommendation

    Read the task notes with task_notes_list — the Options note holds the
    options and trade-offs, and the Frame note holds the criteria. Work
    from them.

    Write the recommendation:

    • The recommended option, stated clearly
    • The rationale tied directly to the decision criteria
    • What you are trading away by choosing it, acknowledged honestly
    • The conditions under which a different option would be better

    Present this as a recommendation, not a verdict. Save the recommendation
    as a task note with task_notes_add. Then ask the operator to make the
    call. This is a checkpoint — the decision is the operator's to make, so
    the AI cannot advance until you decide. If you reject the recommendation,
    the workflow returns to Options to reconsider.

    The AI pauses here and waits for a human to approve before the conversation continues.
    If rejected → returns to options
  4. 4

    Record

    Read the task notes with task_notes_list — the Recommendation note
    holds the recommended option and the operator's decision. Work from it.

    Record the final decision. Save a task note with task_notes_add capturing:

    • The decision made
    • The date and who made the call
    • The rationale — the criteria it satisfied and the trade-off accepted
    • The options not chosen, briefly, so the reasoning is on the record

    This note is the durable record of the decision. Close out the task.

  5. Workflow complete — outcome delivered, every step on record.

Why this workflow?

Without a workflow

  • The decision gets made in a hallway and three months later nobody remembers why
  • One option gets championed and the alternatives are never seriously weighed
  • The recommendation lands before the decision-maker has actually signed off on it

With ConvOps

  • The AI records the framing, the options, and the rationale as notes, so the reasoning is on the record when someone asks
  • The AI drives an Options step that lays out each path with its trade-offs before any recommendation
  • The AI pauses at a recommendation checkpoint so you make the call, rather than the AI deciding for you

Related workflows

Ready to automate?

Stop re-explaining your process. Pick a template, start a task, and let the AI drive the work through your workflow.