Hire an AI support help article writer

Everything it can hand back

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

• The top topics ranked by ticket count, each with whether an article exists and was found
• Proof of whether last month's articles reduced tickets
• Mismatches between an article and what support said, for the product owner
• New articles drafted from real solved tickets, personal details stripped
• Failed articles rewritten answer first, with titles customers would type
• Voice fixes on every draft

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

• Writing an article from how the product should work instead of how support said it works.
• Leaving a customer's detail in a draft.
• Publishing ten articles and measuring none.
• Rewriting an article that was never the problem.
• Promising refunds, dates or fixes the policy does not allow.
• Copy-paste replies that ignore what the customer said.

What a good result looks like

An example, not your task: The same question fills your support inbox and the help page for it either does not exist or nobody finds it.

• This month. Ticket count, top topics, topics with no article, and articles that failed.
• Did last month's articles work. Each article with tickets before and after, marked worked, no change or worse.
• The topics. Top topics ranked by ticket count, with whether an article exists, was found, and the action.
• Mismatches. Articles that say one thing while support said another, for the product owner to settle.
• New articles. Drafts built from real solved tickets, with personal details removed.
• Rewrites. Failed articles rewritten answer first, with new titles and facts that still need a source.

How the work is checked

• Every topic count comes from the sorted tickets.
• No article contains a name, email, order number or anything that points at one customer.
• Every new article came from a real solved ticket or the product docs, not from a guess at how the product works.
• Every rewrite kept the answer support gave, unless flagged as a mismatch.
• 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.

Capabilities

• Read last month. Counts this month's tickets on each topic an article was published for, against last month.
• Count the topics. Groups the tickets by topic, ranks the top ten and keeps the best solved ticket for each.
• Check what the help centre already says. For each top topic, whether an article exists, where, and whether it matches what support actually told customers.
• Sort each topic. No article, not found, found but did not answer, or working. Only the first three get action.
• Draft the missing articles. A page from the best solved ticket, or a fuller article from several tickets and the product docs, with every personal detail stripped.
• Rewrite the pages that failed. Each section opens with its answer and the title says what the customer typed.
• Check the voice. Every new or rewritten article checked against your brand brain.
• Log and hand back. Updates the topic and article files, then stops. You publish.

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 monthly-help-centre-keeper 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/monthly-help-centre-keeper/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

• Last month's ticket export with the question, the reply that solved it and the page visited first, if recorded
• Every help article as text, with its address and last-updated date
• Your brand brain, for the voice check (advised)
• Internal product docs or release notes (optional)
• Last month's keeper file, once it exists

Helpful context (optional)

• Your help centre search logs, so "not found" can be confirmed
• Release notes for the month, so an article can be checked against the current product

Tools and access

• Claude Code: It can keep the topic and article files between months and read the help centre export directly.
• Your support tool: Export tickets with the solving reply and the first help page visited.
• 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: Rewrites and checks sections under the rules. Always edit the result in your own voice.
• Google Search: People Also Ask boxes give the FAQ questions to add at the bottom.

Functions and deliverables

• Support help article writer: Match support questions with help pages. Get missing article drafts, conflicting answers and proposed updates without customer details.
  • The top topics ranked by ticket count, each with whether an article exists and was found
  • Proof of whether last month's articles reduced tickets
  • Mismatches between an article and what support said, for the product owner
  • New articles drafted from real solved tickets, personal details stripped
  • Failed articles rewritten answer first, with titles customers would type
  • Voice fixes on every draft
• Support ticket sorter: Sort support tickets by type and severity, route each to a team, and get a first reply drafted. Paste a batch and see urgent cases first.
  • Each ticket classified
  • A severity ranking
  • A routing choice per ticket
  • A draft first reply
  • An escalation flag for urgent cases
  Source: Burhan Sebin.
• 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.
• Help article writer: Share support questions and verified product notes. Get help articles or FAQs with clear steps, common fixes and details to check before publishing.
  • Step by step help articles
  • Short FAQ entries
  • Troubleshooting sections for common errors
  • Search-friendly titles and related links
  Source: Burhan Sebin.
• Answer-first page rewriter: Share a blog, guide or FAQ page. Get sections rewritten answer first, with facts still needing a source.
  • Rewritten sections with an answer-first opening
  • A list of facts that still need a source or number
  • An FAQ block and a comparison table where they fit
• Draft brand voice checker: Share a draft and voice guide. Get ranked findings and before-and-after edits for top issues.
  • Issues ranked High, Medium or Low
  • The reason each line was flagged
  • A before and after fix for the top issues
  • A separate list of legal and compliance flags
  • A short overall verdict
  Source: Anthropic.
• 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

Tasks you can use it for

• The same question fills your support inbox and the help page for it either does not exist or nobody finds it.
• Your help articles have not been checked against what support says since launch.
• You want proof that an article you published last month reduced tickets.

Limits to check before starting

• You need to answer today's tickets: use the Customer inbox reply drafter, which writes replies to open tickets.
• You have no ticket export yet, or only one ticket: write the help page by hand from the reply that solved it.
• You want articles published or customers answered for you: this agent only drafts, and a person must publish.

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.

• Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to run last month.
• Export last month's tickets from your support tool with the solving replies. Put them in the support team's folder with your help articles, or attach them in the chat.
• Attach your brand brain if you have one.
• Read the mismatches first and settle them with the product owner. Then read the drafts.
• Publish what you approve in your help centre yourself. Run it again next month; it tells you whether the articles worked.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/monthly-help-centre-keeper 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.