Hire an AI six-week product scope reviewer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A one-page brief with goal, audience, limits and what could go wrong
• A six-week bet with a small team and a list of what you will say no to
• A yes, later or no on each request, with the full cost of every yes
• A short reply to send for each request

How it does the job well

• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.
• Keep scope small enough to ship and learn. Name what is out of scope.
• Define how success will be measured before building.

Mistakes it avoids

• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.
• Roadmaps with dates but no owners or confidence levels.

What a good result looks like

An example, not your task: Your plan keeps growing and the date keeps slipping.

• Step 1: One-page brief. Goal, audience, limits, what could go wrong and the open questions you still need to answer.
• Step 2: Six-week bet. A score of the plan, a bet a small team can finish, what is cut, a no list and a default answer of no.
• Step 3: Request screen. Each request with how many people asked, the full cost of a yes, a fit check, a ruling and a reply.
• Replies. A short, kind note for each request, with the reason and no promised date.
• Hand-back summary. Each step's file and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Jason Fried would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Put the plan on one page. Pulls the facts you gave, asks a few questions about goal, audience and limits, and writes a one-page brief tested for weak spots.
• Cut it to a six-week bet. Scores the plan against the build-less rules of the 37signals books. They say build less, shape the work, fix the time and keep teams small. Cuts it to a bet a small team can finish in six weeks. Lists the features to say no to.
• Screen every request. Starts each request at not now and counts different people asking. Adds up what a yes would cost and checks it against the bet.
• Write the replies. Gives a yes, later or no with a short reply for each request.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id set-a-six-week-product-bet-and-screen-requests-against-it only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/set-a-six-week-product-bet-and-screen-requests-against-it/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your product plan, goal and who it is for
• Your team size and any fixed date
• The list of requests, with who asked and when
• What the product is for, and who it is not for, in one line
• Customer comments about the product (optional)

Tools and access

• Any good chat AI: Counting, costing and drafting short replies is text work.
• Your support inbox or feedback tool: Real request counts come from there.

Functions and deliverables

• Six-week product scope reviewer: Share your product plan and incoming requests. Get a bounded six-week brief, exclusions and a yes, later or no recommendation for each request.
  • A one-page brief with goal, audience, limits and what could go wrong
  • A six-week bet with a small team and a list of what you will say no to
  • A yes, later or no on each request, with the full cost of every yes
  • A short reply to send for each request
• Project kickoff brief writer: Turn a rough idea into a project kickoff brief with goal, audience, tone and limits that your team can sign off. Under two pages.
  • One-page brief
  • Clear goal, audience and tone
  • Scope and limits
  • A list of open questions to settle
  Source: RampStack.
• Lean product shaping coach: Cut your product plan down to a six-week bet. Get a score out of 10, a trimmed scope and a list of features to say no to.
  • A score out of 10 with reasons
  • A trimmed scope
  • A six-week pitch outline
  • A list of features to say no to
  Source: Wondel.ai.
• Feature request screener: Screen your feature requests and get a yes, later or no on each, with the full cost of every yes and a kind reply for the customer.
  • A repeat count per request, from different people, over time
  • The hidden costs of each request that repeats
  • A yes, later or no with one reason, and the vision conflict named
  • A short reply for each customer that promises no date
• Product context file writer: Share product facts, audience and positioning. Get a reviewed context file that other marketing skills can reference.
  • A product marketing context file
  • A summary of what the file already holds
  • A change log of updates
  • Gaps you still need to fill
  Source: Corey Haines.
• Jason Fried: Cut a project to a focused first version through Jason Fried’s recorded approach. Keep the core useful, reduce scope and protect a calmer workweek.
  • Your problem worked on the way Jason Fried would: their questions, their method, their push-back
  • The answer or the work, in Jason Fried's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• Your plan keeps growing and the date keeps slipping.
• Requests arrive faster than you can judge them.
• You want to say no kindly and have the reason ready.

Limits to check before starting

• You only have one big request to answer, with no plan to shape: use the Feature request screener.
• Your plan is already set and you want to shrink it to hit a launch date: use Small product launch planner.
• You want to cut a live product down to what matters: use Product design and scope reviewer.
• You need a task list for a sprint, not a bet: use the Sprint priority planner.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and the 3 skill files in the order they run: Project kickoff brief writer, Lean product shaping coach and Feature request screener.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste your plan, then your request list with who asked.
• Answer the few questions step 1 asks, then let it run.
• Send the replies yourself. Nothing goes out for you.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/set-a-six-week-product-bet-and-screen-requests-against-it for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.