Hire an AI customer interview evidence planner

Everything it can hand back

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

• The group to talk to first, with where to find them this week
• Messages that get you the conversations
• A question guide about their life, your big three unknowns and the scary question, planned
• Your notes sorted into what people did, gave up and committed to, with the weak signals flagged
• A keep going, change or stop call with the reason, and the next three talks to have

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

• Running the second half on made-up or imagined answers.
• Counting "I'd buy that" or "great idea" as proof.
• Skipping the scary question because it's uncomfortable.
• 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 an idea and want to know if it's worth building before you spend time or money on it.

• First customer group. The group to talk to first, and where you could reach them this week.
• Interview messages. A warm-intro message and a cold message that ask for help, not a sale.
• Question guide. Questions about their life, the big three unknowns and a plan for the scary question.
• Sorted notes. Each talk split into what they did, what it cost them and what they committed to, with weak signals flagged.
• Ask plan. The next step to ask each person for in time, reputation or money.
• Idea evidence review. A keep going, change or stop call, the reason, and the next three talks.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• No question or message pitches the idea before learning about the person's life.
• The call in step 6 rests on what people did or gave up (time, reputation, money), never on compliments alone.
• Nothing was sent, posted or charged without the person's 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 Rob Fitzpatrick and Steve Blank would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Picks who to talk to. Slices the market until there's a who and a where you could reach this week, and picks the group to start with.
• Writes the messages. Warm-intro and cold messages that ask for help, not a sale, and keep it casual.
• Writes the questions. Questions about their life and their past, never about your idea, plus the three unknowns that could change the plan and the question you're afraid to ask.
• Sorts what you heard. Splits your notes into what they did, what it cost them and what they committed to. Compliments, vague claims and feature ideas are flagged as weak.
• Plans the commitment. For each person, the next step to ask for in time, reputation or money, and who is all praise and no commitment.
• Makes the call. Sets what you believed against what people did, then says keep going, change or stop, and lists the next three talks.

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-worth-building 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-worth-building/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 in a sentence or two, and who you think it's for
• Any group of customers you already have in mind, and where they spend time (optional)
• Your notes from the talks, for the second half

Helpful context (optional)

• Notes from each conversation, written straight after, in the person's own words
• What you're most afraid to hear about your idea
• Where your customers already gather, such as groups, events or forums

Tools and access

• Claude: Holds the questions, the notes from ten talks and six steps of work in one run.
• A notes app or voice memo: Lets you write or record what was said straight after each talk, in their words.
• Any good chat AI: Slicing and scoring are text work that any strong chat AI does well with this skill.
• LinkedIn search: Shows quickly whether a slice has enough findable people in one place.
• Any good chat AI: Short message drafting works well in any strong chat AI with this skill.
• LinkedIn: A common place to find the person and a friend who knows them.
• Any good chat AI: Rewriting and ranking questions is text work any strong chat AI does well with this skill.
• A pocket notebook or index cards: Easier than a laptop for keeping your three questions in view during a casual chat.
• Any good chat AI: Sorting and tagging notes is text work that any strong chat AI does well with this skill.
• A shared spreadsheet or index cards: Sorted notes are easy to filter by mark when each item has its own row or card.
• Any good chat AI: Sorting replies and writing asks is text work any strong chat AI does well with this skill.
• A shared spreadsheet: One row per lead, with the last commitment and date, makes zombie leads obvious.
• 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.

Functions and deliverables

• Customer interview evidence planner: Share an idea and real customer notes when available. Get interview plans, outreach drafts, evidence sorting and a reasoned next-step review.
  • The group to talk to first, with where to find them this week
  • Messages that get you the conversations
  • A question guide about their life, your big three unknowns and the scary question, planned
  • Your notes sorted into what people did, gave up and committed to, with the weak signals flagged
  • A keep going, change or stop call with the reason, and the next three talks to have
• First customer group picker: Pick your first customer group from a broad market. Slice it into people you can find, then get the one group to talk to first.
  • A list of narrower groups, each with why they want it and what they already do about it
  • A who-and-where pair for every group you could actually reach
  • The one group to start with, a backup, and why, scored on pay, reach and fit for you
  • A plan for your first week of conversations
• Customer conversation request writer: Write a customer interview request that gets a yes. Give it who you want to meet. You get a warm intro note, a cold message and an opening line.
  • The easiest route to a first conversation, casual before formal
  • A message in the five-part shape for a warm intro, a cold approach or a friend to forward
  • An opening for the meeting that keeps you in charge
  • A list of wording to avoid
• Customer interview question writer: Write customer interview questions about their real life, not your idea. Get fixed drafts, your top three questions and a plan for the scary one.
  • Your questions rewritten, each with what was wrong and what the new one tests
  • Your top three questions for this type of person
  • A plan for the scariest question, including what answer would change your mind
  • Short lines for pulling a drifting conversation back
• Customer conversation notes sorter: Sort raw customer interview notes into facts, compliments and feature ideas. Get a follow-up question for every weak note.
  • Every note tagged with a symbol and marked as fact, compliment, fluff or idea
  • The follow-up question for each weak note
  • A summary of the real signals (pains, goals, obstacles, workarounds and money)
  • A judgement of each person as a customer, a complainer or not a customer
• Sales next-step planner: Plan the commitment to ask for after a meeting, and sort what people said into real leads, stalls and polite no's. Say your stage and what they said.
  • The commitment to ask for, in time, reputation or money, sized to your stage
  • The exact words to ask, and a fallback if they say no
  • Each reply sorted into compliment, stall, fuzzy promise or real commitment
  • A verdict on each lead, and the one question that settles it
• 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
• 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's worth building before you spend time or money on it.
• You've talked to people, everyone liked the idea, and you still don't know if anyone will pay.
• You're choosing between two ideas, or two groups of customers, and want evidence instead of a hunch.

Limits to check before starting

• Your idea is already proven and people pay for it: use the Seven-question startup scorer to test the next step.
• You have no customers to talk to yet: use the Customer community finder to find where they gather, then come back.
• You want to learn why past buyers chose you: use the Customer purchase interview script writer.

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".
• Describe your idea in a sentence or two. It runs the first half and stops.
• Send the messages and have five to ten conversations. Write notes straight after each one, as close to their words as you can.
• Bring the notes back and say "carry on from step 4". Read the call last, with the evidence it rests on.

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-worth-building 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.