Hire an AI customer help article writer and reviewer

Everything it can hand back

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

• What your records already say about each question, with gaps marked
• A help page per question, with steps, what the reader should see and what to do if it fails
• A reading-level check and a plain rewrite of any page that reads hard
• An accuracy check on every page, with the fixes applied

How it does the job well

• 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.
• Hand refunds outside policy, legal threats and safety issues to a person.

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: Ten questions make up most of your support inbox.

• Step 1: What is known. For each question, the answer your records give today, the source, and any gap or contradiction.
• Step 2: Help pages. One help page per question, with ordered steps, what you should see after each, and what to do if it fails.
• Step 3: Reading level. Each page's grade, the hard sentences and words, and which pages need a rewrite.
• Step 4: Plain rewrites. Each flagged page rewritten in plain English, with a note on what changed and why.
• Step 5: Accuracy check. Missing steps, wrong screen or button names and unbacked promises, with fixes applied to the final pages.
• Hand-back summary. Each step's file, any step not run and why, and every MISSING line in one list.

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, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a 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 George Orwell and Kurt Vonnegut would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Gather what is known. Finds the answer your docs and tickets already give for each question, names the sources and marks gaps.
• Write a page per question. Writes one help page per question with steps, what the reader should see and what to do if it fails.
• Check the reading level. Measures each page's reading level and lists the sentences and words that make it hard.
• Rewrite the hard pages. Rewrites the flagged pages in plain English with the same meaning, following Orwell's rules.
• Check every page is right. Checks each page against the docs and screen names you gave for missing steps, wrong button names and promises your docs do not back, and applies the fixes. It does not open your app.

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-repeat-customer-questions-into-help-pages-people-understand 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-repeat-customer-questions-into-help-pages-people-understand/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 questions you answer every week, and how you answer them today
• Your current docs, FAQ or help pages (optional)
• Who the readers are and what they already know

Helpful context (optional)

• Your real replies to each question
• Screenshots or exact names of your screens and buttons
• Your current FAQ or help pages

Tools and access

• Any good chat AI: Writing, checking and rewriting are all text.
• Your help centre or website editor: Where the finished pages are published and linked.
• Help center, support desk, CRM, chat or email connected to your AI: It can only search what is connected. More sources means better cross-checking.
• Pasted docs and past replies: Works without any connection. It then says it used only what you pasted.
• Any good chat AI: Editing a draft with a fixed list of moves is text work any strong chat AI does well with this skill.
• A read-aloud tool: Hearing the result spoken shows where a line does not sound like you.

Functions and deliverables

• Customer help article writer and reviewer: Share repeat questions, solved tickets and current product docs. Get help-page drafts, plain-language edits and checks against the real steps.
  • What your records already say about each question, with gaps marked
  • A help page per question, with steps, what the reader should see and what to do if it fails
  • A reading-level check and a plain rewrite of any page that reads hard
  • An accuracy check on every page, with the fixes applied
• Customer question researcher: Get a sourced answer to a customer question, with how sure it is. It searches your docs, past tickets and chats and names each source.
  • One direct answer that leads with the bottom line
  • A confidence level, with the reason for it
  • Findings grouped by source, and a numbered list of sources
  • Conflicts between sources, and what could not be confirmed
  • Next steps, including who should check the answer
  Source: Anthropic.
• Support ticket help article writer: Turn a solved support ticket into a help article customers can follow. Get steps, what they should see, and a fix for common problems.
  • A ready-to-publish help article
  • Numbered steps with what you should see
  • A fix for common follow-up problems
  • Search-friendly title and keywords
  Source: Anthropic.
• Text difficulty checker: Paste a passage and name the readers and task. Get difficulty notes and support ideas.
  • A difficulty rating on length, meaning and task
  • A list of likely trouble spots
  • Support ideas for each trouble spot
  • A suggested reading plan
  Source: Gareth Manning.
• Plain English editor: Paste a draft and get it back in plain English, with every cut explained and a read-aloud check. Edit stiff emails, reports and pages.
  • The edited text in plain words
  • A list of every cut or swap, with its reason
  • The point of the piece in one sentence
  • Questions where a fact was missing
• Documentation accuracy reviewer: Check documentation claims against the actual code. Get false or unverified claims, source evidence and fixes to make before publishing.
  • A list of false or missing claims
  • Code samples marked as working or broken
  • Places where docs and code disagree
  • Fixes for each issue
  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
• George Orwell: Rewrite a memo, report or announcement in plain words using George Orwell’s recorded approach. Cut padding and reveal what vague labels hide.
  • Your problem worked on the way George Orwell would: their questions, their method, their push-back
  • The answer or the work, in George Orwell's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Kurt Vonnegut: Review plain writing or a story’s shape using Kurt Vonnegut’s recorded ideas. Cut clutter, trace changes in fortune and question the perfect plan.
  • Your problem worked on the way Kurt Vonnegut would: their questions, their method, their push-back
  • The answer or the work, in Kurt Vonnegut'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

• Ten questions make up most of your support inbox.
• Your help pages exist but customers write in anyway, because they could not follow them.
• You are training someone new and want the answers written down once, correctly.

Limits to check before starting

• You have one odd question from a single customer: reply to them directly, or ask a teammate who knows the answer.
• The problem is a product bug: send it to your developer or open a support ticket with the tool's maker.
• You want to clear your whole support inbox first: use the Customer inbox reply drafter.

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.

• Gather first: your list of weekly questions, your real reply to each one, and the exact names of your screens and buttons.
• Download the handoff pack. It is a zip with HANDOFF.md and the skill files this workflow uses.
• Upload the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md". It works from files, so use a tool that can read them.
• Paste your questions, replies and any docs. It saves one file per step.
• Read the reading-level report and the plain rewrites. Check every button name and step against your app.
• Publish the checked pages and link them in your replies.

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-repeat-customer-questions-into-help-pages-people-understand 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.