Hire an AI business idea tests and evidence tracker

Everything it can hand back

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

• The riskiest guess and why it is first
• The next test, who to try it on, the pass line, the cost and the time
• Your last result judged against the line you set before it ran
• A keep going, change one thing or stop call, with the evidence
• A log of every guess, its test and its result

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

• Telling the owner the idea is good or bad. Report what the test showed.
• Counting friends, family and compliments as evidence.
• Changing the pass line after seeing the result.
• Running more rounds to avoid a stop call.
• Using this for an idea that has already been selling for months. Use a numbers review instead.
• Treating opinions or one loud request as proven demand.

What a good result looks like

An example, not your task: You have an idea and want to know if it is worth building before you spend on it.

• ROUND. The guess tested, the number it needed and the number it got.
• RESULT. Passed, failed or open, with the evidence it counted.
• CALL. Keep going, change one thing, stop or not enough yet, with the reason.
• NEXT TEST. The riskiest untested guess, the smallest test, who to try it on, the pass line, cost and time.
• LOG. How many guesses have passed, failed or are still untested.
• FILES AND MISSING. Each step's saved file and every line marked MISSING.

How the work is checked

• The pass line for this test was written before the test ran.
• The result is judged against that line, not a new one.
• Praise and "I would buy" without action are not counted as evidence.
• The next test is for the riskiest untested guess, not the easiest.
• 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 Rob Fitzpatrick and Steve Blank would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Read the log. Finds which round this is from the log of guesses and results.
• Look for a killer. In round 1, looks for the one fact that would end the idea, before any test is planned.
• Read the result. Counts facts and commitments from customer talks, or compares numbers with the pass line saved earlier. Praise does not count.
• Choose the path. A pass moves to the next guess. A fail with a clear fix gets one changed test. Two fails on one guess get a keep, change or stop call.
• Plan the next test. Picks the riskiest untested guess, the smallest test for it and a pass line, and saves them before anything runs.
• Hand back. Gives the result, the call, the next test and the log, then waits for the next result.

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-validation-analyst 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-validation-analyst/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 idea, who it is for, and any price or offer
• Results of the last test, such as notes from customer talks, sign-ups, pre-orders or replies
• What you can spend and how many weeks you will give each test (optional)

Helpful context (optional)

• Notes from customer talks with who said what
• The numbers from any sign-up page, ad or pre-order test

Tools and access

• Claude Code: It can keep the validation folder and log between rounds.
• A spreadsheet: Sign-ups, pre-orders and replies are easier to count in one place.
• Any good chat AI: Weighing notes against beliefs is text work any strong chat AI does well with this skill.
• A shared document: Keeping beliefs, notes and calls in one place lets a partner check your reasoning.
• Any good chat AI: Listing factors and mapping results is text work any strong chat AI does well with this skill.
• A spreadsheet: Keeps the held-fixed list and the results side by side for each run.

Functions and deliverables

• Business idea tests and evidence tracker: Test the riskiest guess behind an idea. Track real results against pass lines set before each test.
  • The riskiest guess and why it is first
  • The next test, who to try it on, the pass line, the cost and the time
  • Your last result judged against the line you set before it ran
  • A keep going, change one thing or stop call, with the evidence
  • A log of every guess, its test and its result
• Business idea killer: Test a business idea before you build it. Get a clear verdict: dead, with the reason, or survived, with the cheapest test left to run.
  • A verdict: dead or survived
  • The kill pattern named, if dead
  • The cheapest remaining test, if survived
  • A row for your kill list
  Source: sickn33.
• Risky business assumption test planner: Share your plan and key uncertainties. Get measurable assumptions, a small test for the riskiest one and decision rules set before testing.
  • The guesses your plan rests on, each with a number, ranked, with the riskiest named
  • The cheapest kind of test for the top guess, who to try it on and what to leave out
  • Pass, fail and in-between numbers set before the run
  • A run plan and a rule for what to do on a pass, a fail or a middle result
• Idea evidence reviewer: Check your customer talk notes against what you believed. Get a keep going, change or stop call on your idea, plus your next three talks.
  • Each belief marked supported, weakened, untested or wrong, with the evidence
  • The traps that may be skewing what you heard
  • A keep going, change or stop call, with the reason and a stop rule
  • Your next three questions and the next three conversations to have
• One-change experiment planner: Plan a one-change experiment. Tell it what you want to learn and get a test plan that changes one thing and says what each result means.
  • The question rewritten in plain terms, with each term defined
  • The one change to test and the list of things held fixed
  • A second check, the no-effect result and what each outcome means
• Customer progress strategy reviewer: Share the plan, goals and dated results by customer group. Get progress checks, gaps and a reasoned choice to change or continue.
  • Your growth engine, the one rate that drives it and a sum showing where you stand
  • A chain of hoped-for rates, starting rates to measure and dated milestones with predictions
  • Per-group rates in place of totals, and which changes were proven or unproven
  • A keep going or change course call with facts for and against, the kind of change and a dated review
• 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.
• Rob Fitzpatrick: Improve customer questions or review interview notes using Rob Fitzpatrick’s Mom Test approach. Ask about past behavior and separate facts from praise.
  • Your problem worked on the way Rob Fitzpatrick would: their questions, their method, their push-back
  • The answer or the work, in Rob Fitzpatrick's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• 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

Tasks you can use it for

• You have an idea and want to know if it is worth building before you spend on it.
• A test just finished and you are not sure what the result means.
• You have run a few tests and cannot tell whether to keep going.

Limits to check before starting

• Your idea has already been selling for months: review your sales numbers in a spreadsheet or with an accountant instead.
• You want a quick opinion on whether the idea is good: ask a few real buyers, because this agent only reads test results.
• You want it to run the test, send messages or spend money for you: do that step yourself, as it only plans and recommends.

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.

• Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then give it your idea.
• Run the test it plans. Do not move the pass line while it runs.
• When the test finishes, run the agent again and give it the result. It reads the log and picks the next step.
• Read the call. If it says stop or change, check the evidence it lists before you decide.
• It stops planning after four tests with no pass. After that, you decide what is next.

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-validation-analyst 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.