Hire an AI business assumption and customer test planner

Everything it can hand back

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

• A one-page version of the plan with every box turned into a guess, ordered by risk, each with a cheap test and a pass line
• A conversation plan with which guess each talk tests, who to talk to, and questions about what people do now
• The riskiest guess, the smallest test to try next and a rule for changing direction or keeping going

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 business plan on paper and haven't yet tested any of it on real customers.

• Step 1: Guesses on one page. Each box of your plan turned into a guess, ordered by risk, with a cheap test and a pass line.
• Step 2: Customer talk plan. Who to talk to for each guess, questions about what people do now, and a way to record answers.
• Step 3: Smallest test. The riskiest guess left, the smallest test, pass numbers set before you run it, and a rule to change direction or carry on.
• 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

• Every box in the plan is a guess that could be shown wrong, and the riskiest one is first.
• The questions are about what people do now, not what they think of your idea.
• Each test has a pass line set before it runs.
• Step 3 used your notes from the talks. Nothing a customer said is invented.
• 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 Steve Blank and Eric Ries would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Turn the plan into guesses. Lays the plan out on one page: customers, value, channels, revenue and costs. Turns each box into a guess, orders by risk and adds a test and a pass line.
• Plan the customer talks. Takes the guesses from step 1 and lists who to talk to for each. Writes questions about what people do now, and a way to record what they say.
• Test the riskiest guess. After your talks, picks the riskiest guess that is left. Designs the smallest test, sets the pass numbers and a rule to change direction or carry on.

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 plan-assumption-tests 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/plan-assumption-tests/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 business plan or a short brief on the idea
• Who you think the customers are and how you plan to reach them
• Notes from your customer talks, for the last step

Helpful context (optional)

• A list of people who might talk to you
• Any numbers you already have on price or demand
• Your pricing idea and why

Tools and access

• Any good chat AI: Holds the plan, the guesses and your notes across the pause.
• A notes app or voice memo: Lets you capture what people said straight after each talk.
• Any good chat AI: Laying out and ranking a plan is text work.
• A one-page canvas or spreadsheet: Holds the five boxes where the whole team can see them.
• Any good chat AI: Ranking guesses and writing questions is text work.
• A shared spreadsheet or notes app: Holds the record sheet so all founders see the same data.
• Any good chat AI: Ranking guesses and writing a plan is text work.
• A landing page tool such as Carrd or Webflow: Builds a one-page offer for the test in an afternoon.

Functions and deliverables

• Business assumption and customer test planner: Share your business plan. Get testable assumptions, a customer interview plan and a small experiment for the riskiest assumption.
  • A one-page version of the plan with every box turned into a guess, ordered by risk, each with a cheap test and a pass line
  • A conversation plan with which guess each talk tests, who to talk to, and questions about what people do now
  • The riskiest guess, the smallest test to try next and a rule for changing direction or keeping going
• Business model assumption tester: Paste your plan and any proof. Get a one-page model, ranked assumptions and proposed tests with success rules set in advance.
  • A one-page model in five boxes
  • Each box as a guess, marked fact or guess
  • Tests and pass lines, ranked by risk
  • A change log to keep
• Customer discovery interview planner: Plan customer discovery interviews for your business idea. Get ranked guesses, who to talk to, and questions about what people do now.
  • Your guesses ranked by risk
  • Who to talk to for each, with where to find them
  • Behaviour questions for each guess
  • A record sheet and a rule for changing the model
• MVP experiment planner: Plan an MVP experiment for your product idea. Find the riskiest guess, run the smallest test, and set a pivot or persevere rule first.
  • A ranked list of guesses
  • The riskiest guess and the smallest test for it
  • Pass, fail and middle numbers set in advance
  • A pivot or persevere rule
• 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.
• Steve Blank: Test your startup assumptions with Steve Blank's customer development method. Get a guess list, a one-page model and your next customer interviews.
  • Your problem worked on the way Steve Blank would: their questions, their method, their push-back
  • The answer or the work, in Steve Blank'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 business plan on paper and haven't yet tested any of it on real customers.
• You are about to hire sales or marketing staff before you know who buys and why.
• You have talked to a few people but never wrote down what you were trying to learn.

Limits to check before starting

• Your plan has already been proven with paying customers: use the Minimum experiment planner to choose your next test.
• You only want to plan the customer talks and already have your guesses: use the Customer discovery interview planner.
• You want a market size or competitor study from public data: use the Community evidence researcher or a paid research report.

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 every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Give it your plan or brief. It runs steps 1 and 2 and stops.
• Talk to customers about each guess, and write notes straight after each talk.
• Bring the notes back and say "carry on from step 3".

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/plan-assumption-tests 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.