Idea Office Hours
Pressure-test a product idea with forcing questions before jumping to solutions, then capture the decision in a short design doc — a structured 'office hours' diagnostic.
Steps
Entry step: frame. Each step names the specialist role it wants; the full working prompt is expandable.
- Frame the opportunityproduct strategistentry
Turn the rough idea into a specific problem, audience, outcome, and assumption set.
Show working prompt
Inspect the project brief and relevant workspace material before asking anything already answered there. Establish who has the problem, what they do today, why that is inadequate, the desired outcome, constraints, and evidence already available. Ask one high-leverage question at a time. Separate verified facts from assumptions and record what evidence would falsify the idea. Observable handoff: write the completed result to `notes/idea-brief.md` in the project's artifacts drawer with `write_artifact`. Do not merely describe what the file would contain. Re-read it with `read_artifact` before finishing this phase and repair any incomplete sections.
- Pressure-test the optionsproduct researcher
Challenge the premise and compare meaningful alternatives before choosing a solution.
Show working prompt
Read `notes/idea-brief.md`. Test the strongest assumptions against workspace evidence and, when available and appropriate, research tools. Develop at least three materially different options, including a no-build or manual option. For each, compare user value, evidence, effort, reversibility, key risk, and the cheapest falsification test. Recommend one narrow wedge and explain what evidence would change that recommendation. Before working, open `notes/idea-brief.md` with `read_artifact`. Observable handoff: write the completed result to `notes/idea-options.md` in the project's artifacts drawer with `write_artifact`. Do not merely describe what the file would contain. Re-read it with `read_artifact` before finishing this phase and repair any incomplete sections.
- Write the decision recordproduct writer
Capture a defensible decision and the smallest useful real-world action.
Show working prompt
Synthesize the brief and options into a concise decision record. Preserve uncertainty instead of manufacturing confidence. State the chosen wedge, why it beats the alternatives now, boundaries that prevent scope creep, leading and lagging success measures, the next experiment or delivery action, its owner, and a decision date or trigger for revisiting the choice. Observable handoff: write the completed result to `decisions/idea-office-hours.md` in the workspace with `write_file`. Do not merely describe what the file would contain. Re-read it with `read_file` before finishing this phase and repair any incomplete sections.
- Evaluate the deliverableproduct reviewer
Independently grade the observable deliverable and route it to finish, repair, or user escalation.
Show working prompt
Review `decisions/idea-office-hours.md`, `notes/idea-brief.md`, `notes/idea-options.md` against every criterion below. Inspect the underlying evidence files named by the workflow; do not grade from the author's summary alone. 1. The problem, audience, and success measures are specific enough to falsify. 2. Verified evidence and assumptions are clearly distinguished. 3. At least three meaningfully different alternatives, including no-build or manual work, were compared fairly. 4. The chosen wedge follows from the evidence and has explicit scope boundaries. 5. The next action has an owner, a measurable outcome, and a revisit trigger. Open `notes/idea-brief.md`, `notes/idea-options.md` with `read_artifact`. Open `decisions/idea-office-hours.md` with `read_file`. Write the evidence-backed review to `reviews/idea-office-hours-review.md` in the artifacts drawer with `write_artifact`. Give each criterion a PASS or FAIL with a concrete path, excerpt, measurement, or observed behavior. End with exactly `Verdict: PASS` or `Verdict: REVISE`. Then use `advance_task_step` for the active task: PASS routes to `finish`; REVISE routes to `repair` for review rounds 1 through 2, and the 3th REVISE routes to `needs-user`. Never route to finish while a criterion is unmet.
- Repair the deliverableproduct strategist
Fix only the concrete gaps from the latest independent review.
Show working prompt
Read `reviews/idea-office-hours-review.md` with `read_artifact` and repair every failed criterion in `decisions/idea-office-hours.md`, `notes/idea-brief.md`, `notes/idea-options.md`. Make changes on each file's declared surface (`write_artifact` for artifact inputs, `write_file` for workspace inputs), not in task notes or a reply. Preserve evidence that already passed. Re-run or re-check anything the reviewer found unproven. Ensure `decisions/idea-office-hours.md` is genuinely updated this turn so the repair is observable, then hand it back for independent evaluation.
- Finishproject lead
All deterministic and reviewer criteria passed.
Show working prompt
The independent review passed. Read `reviews/idea-office-hours-review.md` with `read_artifact`, then use `write_task_note` to record a concise DONE summary with the final deliverable paths (`decisions/idea-office-hours.md`, `notes/idea-brief.md`, `notes/idea-options.md`) and the evidence that each acceptance criterion passed. Report DONE without starting new work.
- Escalate unresolved concernsproject lead
The bounded repair loop ended without a defensible pass.
Show working prompt
The deliverable did not pass after 3 review rounds. Do not claim success. Read `reviews/idea-office-hours-review.md` with `read_artifact`, then use `write_task_note` to record DONE_WITH_CONCERNS: the unmet criteria, what was attempted, the affected paths, and the smallest user decision or missing input needed to continue.
Triggers
Phrases that suggest this craftbook to a crew.
- brainstorm this
- is this worth building
- help me think through
- office hours
Source
View this craftbook on GitHub · MIT license