Independent guide to useful Bots · Across platforms
Bot Cabinet
← Crew Kits
New crew · manual setup

Idea Trial

Find the assumption most likely to sink an idea and design a fair test before building.

Set up the crew and pass the results between Bots yourself. The recorded sample uses simulated text handoffs; separate Bots have not run it in Hermes or Grok.

Download the plan

When to use this crew

Use this crew when you need someone to challenge an idea, check its supporting facts and review the pitch. For an initial list of assumptions, Nova may be enough.

The jobs

  1. Nova

    State the idea, assumptions, and a small test with decision rules.

  2. Researcher

    Check existing alternatives and the evidence behind claimed demand.

  3. Pitch Coach

    Challenge the explanation and remove unsupported claims.

What you will need

Idea, intended user, existing evidence, time and spending limits, alternatives, and the decision this test should inform.

Set up and run

  1. Select only the roles this job needs. Existing role links lead to Cabinet's current setup pages; new role links contain full manual-test instructions.
  2. Put each selected role in its own conversation or Bot. Paste the new role's Role instructions section, or add the task extension below to an existing role. These files are not native import archives or add-to-app links.
  3. Start with the fictional first task below. Supply the same approved source records to each role that needs them. A copied handoff alone is not evidence for a factual claim.
  4. Pass reviewed results in the order below. If your app lacks Bot-to-Bot handoff, copy the small handoff yourself. Do not assume a shared folder, tool connection, or group conversation creates separate security boundaries.
  5. Record each actual answer and failed attempt. Review before connecting real accounts or adding a schedule. Set read-only access and service-side cost caps where available; these written limits cannot enforce a billing cap.

Pass the work in this order

  1. Nova writes assumptions and proposed success, revise, and stop rules before seeing new results.
  2. Researcher checks alternatives and evidence, preserving contrary examples.
  3. Pitch Coach reviews the resulting explanation and labels unsupported claims.
  4. Nova updates the proposed test; the person chooses whether to run it.

Use this handoff

  • Task and current version:
  • Approved source records:
  • Result and its status: draft, checked, or approved:
  • Unresolved questions:
  • Next owner and action:
  • External action awaiting specific approval:

If a role cannot finish, it returns the missing input or failed attempt. The next role must not manufacture a success record.

First task

Fictional idea: a $10 monthly appointment reminder for independent tutors. Three tutors tried a mock-up; one asked about price; none paid. Alternative note: calendar tools already send reminders. Budget for this first exercise is $0. Produce a test brief and corrected pitch.

Check the result

  • Keeps interest separate from payment and acknowledges the existing alternative.
  • Chooses a question the test can answer and defines decision rules in advance.
  • Adds no spending, interviews, or build without approval.
  • Removes any claim that demand is already proven.
Read the sample answer and checks

Sample written in Codex on October 6, 2026. The same assistant wrote and checked the answer. This is not an independent review or a Hermes or Grok app test.

Original answer

Text simulation only: the following named-role handoffs occur in this one exercise, not separate Bot conversations. No interviews, searches, payment collection, or builds occurred.

Test brief, draft v1: The idea is a $10-per-month appointment-reminder service for independent tutors. The supplied record says three tried a mock-up, one asked about price, and none paid. These are different observations: trial, interest, and no demonstrated payment. The strongest risk is that tutors will not pay $10 monthly for a reminder function their existing calendars already provide. Whether existing reminders meet their needs, whether a distinctive unmet problem exists, and whether tutors will switch are assumptions. The calendar alternative is a supplied note, not a live product comparison.

Proposed $0 test: after the person approves outreach, conduct five short interviews with independent tutors, using the existing mock-up and a consistent $10 monthly description. Start by asking about their current reminder method and a recent concrete problem; do not lead with the new product. Show the mock-up, ask what it would change, and ask whether they would opt into a later $10 monthly pilot. Record yes, no, and unclear responses, along with contrary examples where calendar reminders are sufficient. Do not collect money, buy tools, build software, or promise a pilot start date. Five interviews of about 15 minutes each plus preparation and review is a proposed time requirement; no time limit was supplied.

Decision rules fixed before new results: success for this discovery stage means at least two of five independently describe a specific current shortcoming and explicitly opt into considering the pilot at the stated price; that permits proposing a stronger payment test, not declaring paying demand or approving a build. Revise if a common problem appears but fewer than two opt in, or interviewees need a materially different service: change one hypothesis and write fresh criteria before another test. Stop this version if four or five report that existing reminders meet their needs and none opts in. Mixed or incomplete results outside those rules are inconclusive; keep the raw responses and decide whether another bounded test is justified. These thresholds are proposed decision rules, not supplied results.

Research check: the original supplied record contains no payment evidence. The calendar note is a contrary explanation that must stay in the brief. No named calendar products, feature details, market counts, or live sources were supplied. Researcher cannot independently verify alternatives or current demand under this no-search exercise; that work stops at the supplied evidence.

Corrected pitch: 'We are testing a $10 monthly appointment reminder for independent tutors. Three tutors tried a mock-up, one asked about price, and none paid. Calendar tools already send reminders, so our next proposed test is whether tutors have an unmet need worth paying for.' This is a draft for review, not a published claim.

Nova's updated brief retains the calendar alternative and limits the success result to interview-stage interest. It does not equate an opt-in with payment. The person owns the decision to run the test. Missing inputs: available time, approved contact list and outreach method, the mock-up, original participant notes, and detailed alternative records. Sources used: only the fictional first-task record. Specific approvals needed before external action: contact tutors; later publish a pitch, collect payments, spend, or build. None is approved by a handoff or performed here.

Checklist results

  • pass: Keeps interest separate from payment and acknowledges the existing alternative. — Three trials, one price question and no payment are separate; calendar reminders remain a contrary alternative.
  • pass: Chooses a question the test can answer and defines decision rules in advance. — Five proposed interviews test a concrete unmet need and opt-in at a stated price, with success/revise/stop criteria fixed before new results; payment demand remains unproven.
  • pass: Adds no spending, interviews, or build without approval. — Budget remains $0, interviews require specific outreach approval, and no test or build occurred.
  • pass: Removes any claim that demand is already proven. — Corrected pitch says testing; brief labels demand hypothetical and opt-ins as discovery interest only.

Not tested

  • Single-agent labeled text simulation, not separate Bot conversations or security boundaries.
  • No outreach, live alternative research, actual demand test, payment, or build occurred.
  • The same agent generated the handoffs; evidence check is a distinct textual pass, not independent runtime execution.
Task instructions for existing Bots and run limits

Nova

Keep the existing Bot's role and boundaries. For this crew: State the idea, assumptions, and a small test with decision rules. Treat the idea as a hypothesis. Separate facts from assumptions. Define success, revise, and stop rules before a test; ask before outreach, spending, or building. Use only the input assigned to you for this task. Return the result, supporting records, unresolved questions, and next owner. A handoff does not approve an external action.

Researcher

Keep the existing Bot's role and boundaries. For this crew: Check existing alternatives and the evidence behind claimed demand. Check a defined question against the original approved records. Return evidence, source references, and gaps. Label supplied snapshots separately from current live research. Use only the input assigned to you for this task. Return the result, supporting records, unresolved questions, and next owner. A handoff does not approve an external action.

Run limits

One idea, three supplied evidence records, one no-spend test proposal. No automatic research or outreach.

Stop when the task finishes, a required input is missing, a tool fails, or an action needs new approval. No automatic retries. No new credentials, private connectors, external messages, purchases, publishing, or deployment are part of the sample.

Finished output

A short decision brief, an assumption list, and one test request.

Workflow written by Bot Cabinet. Inspired by The Idea Killer, from the supplied @unicodef1wn chart. Read the source notes. See Grok’s official guides for setup and sharing instructions.