Hire an AI product comparison page writer

Everything it can hand back

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

• A page table by rival and type with the search, what the shopper wants and whether the search is open
• A build order in batches, with fairness rules for every page and a legal check note
• A best-of page brief and draft with the same block for each item, a comparison table and a proof checklist
• A list of claims held back because they had no support
• The page rewritten answer first, with a short summary, a FAQ and a list of facts that still need a source

How it does the job well

• Write for one named audience and one action. Each asset has a single job.
• Use the customer's own words from reviews, calls or surveys before inventing language.
• Every claim needs proof the business can show. Leave unproven claims out or mark them.
• Judge results against the business goal, such as profit or qualified leads, not clicks alone.

Mistakes it avoids

• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
• Calling a test winner before there is enough data.

What a good result looks like

An example, not your task: Shoppers compare you with rivals before they buy, and you are not on the pages they read.

• Step 1: Page plan. A table of pages by rival, type and search, plus build order, fairness rules and a legal check note.
• Step 2: Best-of page. A page type check, brief and draft with a table, item blocks, proof checklist and held-back claims.
• Step 3: Answer-first rewrite. The draft rewritten so each section opens with the answer, plus a summary, table and FAQ.
• Facts that still need a source. A list of numbers and claims the page cannot yet back.
• 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.

Capabilities

• Plan the page set. Comparison page set planner lists the five page types for each rival (best-of, review, alternatives, rival versus rival and you versus rival). It checks which searches are open, sets fairness rules and a legal check, and orders the pages in batches.
• Write the best-of page. Best-of page writer checks the page type against what ranks, then writes a brief and a draft. Every item gets the same block with real pros and cons. It holds back any claim that you tested something without notes to show for it.
• Rewrite answer first. Answer-first page rewriter opens each section with the answer in a short capsule that makes sense alone. It adds a summary, FAQ and table, and lists the facts that still need a number or a source.

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 publish-comparison-and-best-of-pages-that-shoppers-and-ai-quote 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/publish-comparison-and-best-of-pages-that-shoppers-and-ai-quote/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 category and the five to ten rivals you want to cover
• Your product facts, including prices and specs
• The real prices and specs of each rival, which it asks you to collect halfway through
• Your brand file (optional)
• Search results or sales results by page (optional)

Tools and access

• Google Search Console: Shows which searches that name rivals already bring you impressions, and which versus searches are open.
• Any good chat AI: It builds the table once you give it your rivals and your proof.
• Any good chat AI: It drafts the brief and page from the facts you give it. Ask it to flag every number it can't source.
• Google Search Console: Shows which FAQ questions bring clicks after you publish, so you can split a strong one into its own page.
• 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

• Product comparison page writer: Share product and competitor facts. Get a comparison-page plan and one sourced draft that starts each section with its answer.
  • A page table by rival and type with the search, what the shopper wants and whether the search is open
  • A build order in batches, with fairness rules for every page and a legal check note
  • A best-of page brief and draft with the same block for each item, a comparison table and a proof checklist
  • A list of claims held back because they had no support
  • The page rewritten answer first, with a short summary, a FAQ and a list of facts that still need a source
• Comparison page set planner: Plan your comparison pages for each rival: best-of, review, alternatives and versus pages, with open searches marked and a build order for your team.
  • A table of page types by rival: the search, what the shopper wants and the page or channel
  • A build order and batch size
  • Fairness and legal reminders for every page
  • A way to add new rival searches as pages go live
• Best-of page writer: Write a fair best-of page that includes your product. Give it a buyer question and your rivals' facts. You get a brief, a draft and a proof list.
  • A brief: title, meta description, URL, entities to cover, questions for an FAQ, internal links
  • A best-of page draft with the same block for every item and a comparison table at the top
  • A checklist of first-hand proof you still need to add
  • A list of claims it held back because they had no support
• 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
• 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

• Shoppers compare you with rivals before they buy, and you are not on the pages they read.
• You want AI assistants to name your product when someone asks for the best option.
• You have written a best-of page that reads like an ad and want it to be fair and useful.

Limits to check before starting

• You only need one product page: write a plain product page instead, since this workflow plans pages that compare you with rivals.
• You have no rivals shoppers compare you with: use the Category search plan builder to find what shoppers search for.
• You only want the page plan and no draft: use the Comparison page set planner on its own.

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's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Name your category and your rivals. Add your brand file if you have one.
• When it pauses, pick the first page from the plan and collect the real price and specs for you and each rival. Note the date you checked them.
• Before you publish, fill in the proof checklist and cut any claim you cannot back. Have the page checked against the comparative advertising rules where you sell.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/publish-comparison-and-best-of-pages-that-shoppers-and-ai-quote 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.