Hire an AI customer-goal product design planner

Everything it can hand back

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

• A map of the moments, the worry at each and a rating of today's experience
• A designed fix for each weak moment, with one owner
• A keep, cut and merge list for your features
• Three to five measures of customer progress, with a guard against gaming each
• Ten names tested three ways, with three ranked picks and a not-for line for each

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

• Mixing two jobs in one run.
• Rating a moment good or bad with no evidence.
• Keeping a feature because someone worked hard on it.
• A name that needs the company name to make sense.
• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.

What a good result looks like

An example, not your task: You know the job, but your product, features or reports still follow your org chart.

• Moments and experience. The job line, six to ten moments with worry, today's rating and evidence, the fix and one owner each.
• Feature cuts. Each feature marked keep, cut or merge, with a reason tied to the job, and any that cannot be cut.
• Measures. Your tracked numbers tagged, and three to five progress measures with source, owner and a guard against gaming.
• Name. The job in eight words or fewer, ten names with test scores, and the top three with hire-it-when and not-for lines.
• Hand-back summary. Each step's file, every MISSING line in one list and the checks that could not run.

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. Step 2 used the moments file from step 1, step 3 used the numbers the person tracks and the keep list, and step 4 used the measures.
• The map covers use after buying, not only the purchase.
• Every rating of today has evidence, and every moment has one owner.
• 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 Clayton Christensen and Jack Trout would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Map the moments. From first look to later use, including when things go wrong. For each: the worry, today's rating with evidence, the designed fix and one owner.
• Cut features by the job. Tests each feature against the job. Keeps what serves it, cuts or merges the rest and uses the moments map to weigh what fixes a weak moment.
• Pick the measures. Tags what you track, checks it against three data traps and writes a few measures of progress with a source, an owner and a guard against gaming.
• Name the product after the job. Drafts names in four routes and tests each on a stranger, on stretch, on lookalikes and without the company name. Drops any name that promises progress the measures do not track.

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 job-based-product-design 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/job-based-product-design/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

• A job spec for one customer circumstance
• Your feature wish list, with every request, and your question, such as what to build next
• The numbers and reports you track now
• Customer reviews, complaints and returns, pasted as written (optional)
• Product facts (optional)

Helpful context (optional)

• A job spec from the Job spec writer
• A switch story map from the Switch story mapper, if you have one
• Your dashboard or weekly report

Tools and access

• Claude: Holds the spec, the feature list and four steps of work in one run.
• A whiteboard or slide: The moments table is easier to review with your team when drawn out.
• Any good chat AI: Mapping moments and designing changes is text work any strong chat AI does with this skill.
• Any good chat AI: Weighing a list of features against one job is text work any strong chat AI does well.
• A spreadsheet: A part-by-part table with usage counts makes decisions easy to see.
• Any good chat AI: Tagging numbers and drafting measures is text work any strong chat AI does with this skill.
• A short survey tool: Optional. Some measures of progress, such as would do it again, can only come from asking. Free survey tools exist, such as Google Forms. Paid ones add features you do not need to start.
• Any good chat AI: Drafting names and scoring them against fixed tests is text work any strong chat AI does with this skill.
• A trademark search tool: This skill cannot check if a name is free to use, so you need to do it before you commit.

Functions and deliverables

• Customer-goal product design planner: Share the customer's goal, research and current features. Get key experience moments, feature choices, naming ideas and progress measures.
  • A map of the moments, the worry at each and a rating of today's experience
  • A designed fix for each weak moment, with one owner
  • A keep, cut and merge list for your features
  • Three to five measures of customer progress, with a guard against gaming each
  • Ten names tested three ways, with three ranked picks and a not-for line for each
• Customer experience journey mapper: Build a customer experience map from your job spec. See each worry from first look to later use and get the top three fixes.
  • A map of six to ten moments from first look to later use
  • The worry at each moment, and a rating of today's experience with the evidence
  • A designed experience for each weak moment, with the change inside and one owner
  • A plan for the proof moment, a premium price test and a hard-to-copy list
  • The top three changes for the next ninety days
• Feature cutting planner: Plan which features to cut. Give it your feature list and the main job users want done. You get keep, cut or merge calls with reasons.
  • A keep, cut or merge decision for every part, with a reason
  • The order the remaining parts should take
  • A consistency check on size, colour and wording
  • A dated plan, with the order to make the changes
• Customer success metric planner: Find which numbers you track miss the customer. Get three to five customer progress measures, each checked for gaming, with an owner.
  • Each number tagged and checked against three data traps
  • Three to five measures of customer progress, each with formula, source and owner
  • A repeat-use measure
  • A gaming check and a guard for each measure
  • A list of numbers to stop reviewing every week
• Job name picker: Paste your job spec and get a job name that tells strangers what to hire your product for. Ten names are tested and the top three ranked.
  • The job in eight words or fewer
  • Ten names across four routes
  • Scores from three tests and a maker test, with the sums
  • Three ranked picks, each with a hire-it-when line and a not-for line
  • A rule for keeping the name from blurring
• 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.
• Clayton Christensen: Explore why customers buy using Clayton Christensen’s recorded approach. Start with a real situation, the struggle and what the buyer used before.
  • Your problem worked on the way Clayton Christensen would: their questions, their method, their push-back
  • The answer or the work, in Clayton Christensen's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Jack Trout: Sharpen a brand’s place against rivals through Jack Trout’s recorded approach. Pick one clear idea, check the proof and avoid a blurred message.
  • Your problem worked on the way Jack Trout would: their questions, their method, their push-back
  • The answer or the work, in Jack Trout'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 know the job, but your product, features or reports still follow your org chart.
• Customers stall at set-up, return the product or do not use it twice.
• You have a long list of feature requests and no way to choose between them.
• You are about to name a product or range and want the name to say what it is for.

Limits to check before starting

• You do not yet know the job: write it first with the Customer task definition writer, then come back.
• You face one feature decision, not a whole product: use the Feature request screener.
• You want to see who else the customer could hire for the job: use the Customer alternatives researcher.

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, in an AI that can read files, and say Follow HANDOFF.md.
• Paste your job spec, your feature list and the numbers you track. Add complaints and reviews if you have them.
• Check each rating of today's experience against what you know. Correct any that are wrong before the later steps use them.
• Check trademarks and domains for the top names yourself. The AI cannot.
• Give each change to its named owner.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/job-based-product-design 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.