Hire an AI customer interview case-study planner

Everything it can hand back

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

• A case outline: problem, decision, change and outcome, each point tied to a moment in the interview
• Evidence gaps: each outcome with no proof, as a MISSING line
• A customer approval checklist: every quote, number and detail they must OK before you publish
• A hand-back summary with one next step

How it does the job well

• One interview is one case. Never write that customers "often" or "usually" do something.
• Never invent a quote, number, date, job title or result. Quote only words that are in the interview. Mark paraphrase as paraphrase.
• A result must state its period and its source. If it has neither, mark it unsupported.
• Keep private details out of the files unless the customer approved them.
• Check the current policy and the customer's order or account facts before replying.
• Answer the actual question in the first two lines, then explain.
• Match the customer's tone. Acknowledge the problem once, without grovelling.

Mistakes it avoids

• Promising refunds, dates or fixes the policy does not allow.
• Copy-paste replies that ignore what the customer said.
• Closing a ticket without a clear next step.

What a good result looks like

An example, not your task: You interviewed a customer and now need an outline before you write the case study

• Case outline. The problem, the decision, the change and the outcome, each tied to a moment in the interview.
• Evidence gaps. Each outcome with no proof, as a MISSING line, and who could supply it.
• Customer approval checklist. Every quote, number and detail the customer must approve before you publish.
• Hand-back summary. Files saved, MISSING facts, checks not done and one next step.

How the work is checked

• Every point in the outline has a pointer to the interview.
• Every outcome is marked supported, needs customer OK or unsupported.
• No quote, number or title was added.
• The outline makes no claim about other customers.
• 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 Malcolm Gladwell and Ed Catmull would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Customer interview synthesizer. Separates the problem, the customer's actions and the outcomes they report. It keeps a pointer to each moment and treats the interview as one case. It hands on the tagged points.
• Case-first story builder. Builds the outline around the real decision and the change after it. It marks outcomes with no evidence as unsupported and hands on the outline.
• Draft proofreader. Tidies the outline wording without writing the finished case study. It keeps the source pointers and hands back the outline and the approval checklist.

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 turn-a-customer-interview-into-a-case-outline 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/turn-a-customer-interview-into-a-case-outline/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 interview, as a transcript or notes. The customer must have agreed to it
• Facts the customer has approved, such as name, role and company (optional)
• Evidence for any result, such as numbers with their dates and where they came from (optional)
• What the customer allowed you to publish, such as name, quotes and logo
• Who will read the case study (optional)

Helpful context (optional)

• A recording transcript with times, so each point can point to a moment.
• The customer's own numbers, exported from their tool, with dates.

Tools and access

• Claude, ChatGPT or Gemini with file support: They read the full transcript and keep each step's result as a file. None of them can ask the customer for approval. You send the checklist.
• Any good chat AI: Choosing and testing cases from notes is text work.
• Your own interview notes: A real case beats anything the AI can find on its own.

Functions and deliverables

• Customer interview case-study planner: Share a consented customer interview, facts and result records. Get a sourced case outline, evidence gaps and a customer approval checklist.
  • A case outline: problem, decision, change and outcome, each point tied to a moment in the interview
  • Evidence gaps: each outcome with no proof, as a MISSING line
  • A customer approval checklist: every quote, number and detail they must OK before you publish
  • A hand-back summary with one next step
• Customer interview synthesizer: Share interviews or support notes. Get evidence-backed patterns and product questions.
  • Tagged observations
  • Named patterns with evidence strength
  • Product implications for each pattern
  • Decisions and open questions
  Source: RampStack.
• Case study story planner: Share a topic and notes. Get one real case, the claim it tests and a story outline with the strongest case against it.
  • The one case, with why it holds the idea
  • The obvious explanation and the question that flips it
  • The strongest case against you
  • An outline that opens on a scene and ends on a person
• Draft proofreader: Proofread text while keeping its meaning and voice. Get a corrected version and an explanation of each edit, or an updated file when requested.
  • A corrected version in your voice
  • A log of every change with reasons
  • A saved copy named UPDATED_ plus your file name (for files)
  Source: sickn33.
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Malcolm Gladwell: Explain an idea using Malcolm Gladwell’s recorded approach. Start with a real case, question the obvious story and check whether the evidence holds.
  • Your problem worked on the way Malcolm Gladwell would: their questions, their method, their push-back
  • The answer or the work, in Malcolm Gladwell's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Ed Catmull: Plan feedback or protect rough creative work using Ed Catmull’s recorded approach. Name the problem, keep the creator’s choice and find hidden issues.
  • Your problem worked on the way Ed Catmull would: their questions, their method, their push-back
  • The answer or the work, in Ed Catmull'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 interviewed a customer and now need an outline before you write the case study
• A customer claims a result, such as time saved, and you need to see what backs it
• Sales or marketing asks for a customer story and legal needs to know what the customer approved
• You want a checklist to send the customer so approval is clear and in writing

Limits to check before starting

• You want to show a pattern across many customers. Use the Customer interview synthesizer on all the interviews, or Buyer research brief builder.
• You want your own project turned into a portfolio piece. Use the Portfolio case study writer.
• You want a talk or pitch built around one story. Use Case-based pitch and talk writer.
• The customer has not agreed to be interviewed or quoted. Get that first. This workflow only works with consented material.

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 is a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude, ChatGPT or Gemini and say "Follow HANDOFF.md".
• Paste the interview. Add the approved facts, any result evidence and what the customer allowed you to publish.
• Read the evidence gaps first. For each MISSING outcome, ask the customer for proof or cut the claim.
• Send the approval checklist to the customer. Write the case study only after they reply.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/turn-a-customer-interview-into-a-case-outline 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.