Hire an AI product risk and roadmap planner

Everything it can hand back

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

• Each of the four risks with the evidence behind it, or marked unknown
• An evidence score out of 100, with the working shown
• An owner for each risk, the cheapest test for the riskiest one and the result that would change your plan
• Your list sorted into features, problems and results
• Three to five problems for named customers, each with one result to measure and a review point in place of a date

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: You have a product idea and want to know which risk to test first, before you spend on building.

• Product idea risk check. The problem and customer, the four risks with evidence or unknown, an owner for each, and an evidence score out of 100.
• The riskiest risk and first test. The riskiest of the four, the cheapest test for it, and the result that would change your plan.
• Your list, sorted. Each item on your roadmap marked as a feature, a problem or a result, with who asked for it.
• Problems to solve. Three to five problems for named customers, each with one result to measure.
• Review point. A review point and the evidence needed, in place of fixed dates, plus any items dropped or parked and why.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, 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 Marty Cagan and Eric Ries would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• States the problem. Writes the problem and the customer in plain words, so everything after it has something to check against.
• Rates the four risks. Asks what the evidence says on value, usability, feasibility and viability, and marks anything unknown as unknown.
• Picks the first test. Names one owner for each risk, picks the cheapest test for the riskiest and writes the result that would change your plan.
• Sorts your roadmap. Takes your feature list and marks each item as a feature, a problem or a result, and who asked for it.
• Rewrites it as problems. Turns each feature into a problem for a named customer, using the risk findings, and gives each one a result you can measure.
• Replaces dates with review points. Groups the list into three to five problems and swaps fixed dates for a review point and the evidence needed.

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 idea-four-risks-check 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/idea-four-risks-check/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

• The idea, the problem it solves and who it is for
• What you already know, such as customer words, tests, costs and limits
• Customer reviews or messages (optional)
• Your brand file, for rules on claims and fit (optional)
• Your list of features, tasks or requests, with any dates
• Who asked for each item (optional)

Tools and access

• Any good chat AI: Rating evidence and writing a test is text work that any strong chat AI does with this skill.
• A prototype or mock page: Lets you run the cheap test it recommends with real people.
• Any good chat AI: Sorting and rewriting a list is text work that any strong chat AI does with this skill.
• A spreadsheet: Holds the result numbers you track at each review point.

Functions and deliverables

• Product risk and roadmap planner: Share a product idea, feature list and buyer evidence. Get a risk review, first-test proposal and roadmap framed as problems to solve.
  • Each of the four risks with the evidence behind it, or marked unknown
  • An evidence score out of 100, with the working shown
  • An owner for each risk, the cheapest test for the riskiest one and the result that would change your plan
  • Your list sorted into features, problems and results
  • Three to five problems for named customers, each with one result to measure and a review point in place of a date
• Product idea risk checker: Share your idea and evidence. Get four risk areas, evidence scores, and a cheap test for the riskiest gap.
  • Each of the four risks with the evidence, or marked unknown
  • A score out of 100 for how well the evidence covers the risks
  • A named owner for each risk
  • The cheapest test for the riskiest one, and the result that would change your plan
• Product outcome roadmap planner: Turn a feature roadmap into outcomes. Paste your features and dates. Get three to five customer problems, each with a result you can measure.
  • Each item marked as a feature, a problem or a result
  • Three to five problems, each for a named customer
  • One measurable result per problem
  • Review points in place of dates, with the evidence each needs
• Buyer problem and product idea finder: Name a market and your budget. Get 30 problem ideas, five picks and a plan to check products and competitors.
  • A list of 30 specific buyer problems, in your buyers' words
  • Your best five, with a reason for each and 2 or 3 products that could solve it
  • For each pick, the brands selling to it, with product, pain point, ad pattern and page type. They come from your tool or your own searches.
  • Search terms for the Meta Ad Library, when no tool is connected
  • A game plan with a test budget, a stop point and what to check if the test fails
• 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.
• Marty Cagan: Review a product idea using Marty Cagan’s recorded approach. Test its value, ease of use, build limits and fit with the business.
  • Your problem worked on the way Marty Cagan would: their questions, their method, their push-back
  • The answer or the work, in Marty Cagan's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Eric Ries: Turn a product plan into testable guesses using Eric Ries’s public approach. Start with the riskiest assumption and measure what customers actually do.
  • Your problem worked on the way Eric Ries would: their questions, their method, their push-back
  • The answer or the work, in Eric Ries'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

• You have a product idea and want to know which risk to test first, before you spend on building.
• Your roadmap is a list of features and nobody can say what each one should change.
• A leader keeps asking for features, and you want to turn the requests into problems you can measure.

Limits to check before starting

• Your product is finished and you already have customer data: use a usage analysis of what people really do, or ask your analyst.
• You want to screen one feature request, not a whole roadmap: use the Feature request screener.
• You only want a small test for one idea: use the Minimum experiment 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 plus one skill file for each step.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste your idea and your feature list. It works step by step and saves each result.
• Run the cheapest test on the riskiest risk, then bring back what you learn.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/idea-four-risks-check 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.