Hire an AI product setup instruction and tour planner

Everything it can hand back

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

• A corrected first-use path, one step per line, ending at the first useful result
• A table of instructions with the control each one points to, and which ones do not match
• New labels and prompts in your users' words, beside the old ones
• A plan for optional in-app help, with skip, resume and finish rules
• A walkthrough checklist a person can run on the live product

How it does the job well

• Start from the user's task and the content, then the layout. Decoration comes last.
• Design every state: empty, loading, error, long text and mobile.
• Keep one visual system. Reuse spacing, type and colour tokens instead of one-off values.
• Check text contrast (at least 4.5:1 for body text) and keyboard focus as you go.

Mistakes it avoids

• Accepting an instruction that names a control you could not find on a screen.
• Renaming a real control just to match a label you prefer.
• Claiming facts about users with no evidence.
• Planning a tour that cannot be skipped.
• Designing only the happy path at desktop width.
• Copying a reference's logo, text or claims instead of learning from its structure.

What a good result looks like

An example, not your task: You renamed or moved a menu and the welcome tour, emails and help pages still use the old names.

• First-use path. The shortest steps to the first result, each tied to a control found on a screen.
• Instruction match table. Every instruction beside the control it names, with mismatches marked.
• Label table. Old and new labels and prompts for each screen, written in your users' words.
• Tour plan. Optional in-app help at each point where users stall, with skip, resume and finish rules.
• Walkthrough checklist. A screen-by-screen list for a person to run on the live product with a fresh account.

How the work is checked

• Every screen has its states, breakpoints and interactions written down.
• Colour pairs and type sizes pass the stated contrast checks.
• The handoff names components, tokens and open questions.
• 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 Grace Hopper would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• First-use onboarding designer. Uses your user tasks and the first useful result to choose the smallest path. Checks each step against the supplied screens and marks any control it cannot find. Marks missing audience evidence before it suggests a change. Hands step 2 the path and the screens it touches. Check before moving on, every step names a control found on a screen.
• Plain words interface rewriter. Rewrites the labels and prompts on the selected screens in the words your users already use. Keeps the product's own names for real controls. Hands step 3 the new labels. Check before moving on, each new label still points to the same control.
• In-app tour designer. Plans optional guidance for the revised path, with skip, resume and finish behavior, and words each tip with step 2's labels. Keeps it to the moments where users get stuck. Hands back the tour plan and the walkthrough checklist. Check before moving on, the tour never blocks the product and can be skipped at every step.

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 make-onboarding-instructions-match-the-product 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/make-onboarding-instructions-match-the-product/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 current onboarding screens, as screenshots, a recording transcript or a list of screens in order
• Your help text, tooltips and welcome emails that give setup instructions
• The first result a new user should reach, such as sent a first invoice
• Questions new users ask most, from support or reviews (optional)
• Who your new users are and what they call things (optional)

Helpful context (optional)

• Approved examples of a good result.
• A named reviewer and their acceptance rules.

Tools and access

• A capable chat AI with file support: Read the full pack and supplied sources; connected actions need the corresponding authorized tools.
• Any good chat AI: Rewriting text in a given set of words is work any strong chat AI does well.
• A person who has never used it: A new hire shows which words still confuse. No tool replaces that test.
• Claude or ChatGPT: Either can weigh the trade-offs and write the plan. No tool or files are needed.
• Your product analytics: Feature-use numbers make the success measure real. Without them you can only track tip clicks.

Functions and deliverables

• Product setup instruction and tour planner: Share current setup screens, help and user tasks. Get a first-use flow, plain labels and an optional guided-tour plan.
  • A corrected first-use path, one step per line, ending at the first useful result
  • A table of instructions with the control each one points to, and which ones do not match
  • New labels and prompts in your users' words, beside the old ones
  • A plan for optional in-app help, with skip, resume and finish rules
  • A walkthrough checklist a person can run on the live product
• First-use onboarding designer: Design a first-use onboarding flow around one early win. Give it your product and users. You get fewer setup steps and a habit cue.
  • Onboarding flow with a reason for each step
  • First-win definition
  • Habit cue and return trigger
  • Different paths by user readiness
  • List of setup steps to cut
  Source: sickn33.
• Forms and instructions rewriter: Share forms, screen text or steps and your users’ words. Get a plain rewrite, a swap table and open questions.
  • A rewrite in the words your users say
  • A list of old terms and their replacements
  • Instructions that start with a verb
  • A read-aloud check and the questions a new hire would still ask
• In-app tour designer: Plan an in-app product tour that shows each tip only when a user needs it. Get a build or skip verdict, a tip plan and a way to track feature use.
  • A verdict: build a tour, build a small one, or do not build one
  • A tip plan with the trigger, placement, dismissal and re-show rule for each tip
  • A draft line of tip text for each row
  • A tracking plan that shows if a tip led to real feature use
  • A simple upkeep plan so tips do not go stale
  Source: RampStack.
• 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
• Grace Hopper: Make a tool or task easier to use through Grace Hopper’s recorded approach. Use people’s words, automate dull work and document clear steps.
  • Your problem worked on the way Grace Hopper would: their questions, their method, their push-back
  • The answer or the work, in Grace Hopper'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 renamed or moved a menu and the welcome tour, emails and help pages still use the old names.
• New users ask support the same first-week question, and the answer is already in your help text.
• A new designer or product manager joins and finds three versions of the setup path.
• You are about to ship a redesign and want the first-use text checked against the new screens.

Limits to check before starting

• Your product has no screens yet to compare with. Use the First-use onboarding designer on its own to plan the path.
• You only want a tour built for a path you already trust. Use the In-app tour designer.
• You want emails for new customers, not in-product text. Use the New customer onboarding sequence writer.
• You want to rewrite help articles, not first-use screens. Use the Forms and instructions rewriter.

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 workflow pack and add it to your AI, such as Claude, ChatGPT or Gemini.
• Attach the onboarding screens and help text in the order a new user meets them. Say the first result they should reach.
• After step 1, check the path against your product. The AI marks any step it cannot match to a screen as MISSING. Do not accept a step it could not find.
• After step 2, read the old and new labels side by side and keep the ones your users would say aloud.
• Run the walkthrough checklist on the live product with a fresh account before you ship the new text.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/make-onboarding-instructions-match-the-product 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.