Hire an AI competitor ad change reviewer

Everything it can hand back

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

• Counts by format, age and ad type for each rival, against its own last month
• A list of rivals that moved and rivals that did not
• Message and position changes for the rivals that moved
• Ad gaps your proof can fill
• Up to two moves worth answering, or a clear "none this month"

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

• Guessing a rival's spend or results from how many ads it runs.
• Copying a rival's ad or wording. Take the structure, not the words.
• Reacting to every change. Most months need no move.
• Comparing months when the ads were collected on different days or with different filters.
• Adding a rival to the list without a yes.
• Generic copy that could fit any brand.

What a good result looks like

An example, not your task: You have three to six rivals you want to keep an eye on without a big monthly project.

• This month. Which rivals moved and which did not.
• What changed, per rival. Live ad counts, format mix, new offers or prices and new landing pages, set against last month.
• Gaps you can fill. Ad gaps your rivals leave open, each with the proof you have for it.
• Newcomers. Any cheaper or simpler new rival, with a call of nuisance or real threat and why.
• Moves worth answering. Up to two moves, each tied to a rival's change, or a clear none this month.
• What would change the call. One to three signals that would turn a watch into an action next month.

How the work is checked

• Every change is set against that rival's own last month.
• No claim about rival spend, sales or results is made.
• No move is proposed that your proof cannot support.
• Ads collected in different ways in different months were flagged.
• 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 Jack Trout and Al Ries would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Count the ads. Counts each rival's ads by format, age, landing page and ad type.
• Compare with last month. Sets those counts and each rival's price and offer claims against its own last month. Counts show structure, not spend.
• Choose where to look deeper. A rival counts as moved on a big change in live ads, a shift in format mix, or a new offer or landing page. If none moved, it stops here.
• Compare messages and find gaps. For rivals that moved, it compares their message with yours and finds ad gaps your proof can fill.
• Check newcomers and words. Checks a cheaper or simpler newcomer for real threat, and every third month maps the words rivals own.
• Pick the moves. Proposes at most two moves, each tied to a rival's change, or says to watch and what would change that.

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-competitor-watcher 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-competitor-watcher/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 three to six rivals, with their sites, the first time
• This month's ads from each rival, collected by hand from the public ad library, with the date
• Your brand file, for your claims and proof (optional)
• Your customer reviews (optional)

Helpful context (optional)

• A screenshot or export of each rival's pricing page
• Your own month of ad changes, for context

Tools and access

• Claude Code: It can keep the watch folder, read each rival's history and run every step on a schedule.
• Meta Ad Library: Collect each rival's live ads by hand here, on the same day each month.
• Meta Ad Library: Free and public. Shows a rival's ads, start dates and links, including inactive ones if you ask for all ads.
• Any good chat AI: Any current chat AI can count and label a pasted list, and transcribe a video if you attach it.
• Meta Ad Library: The public source for competitor ads, with library IDs and start dates, browsed by hand.
• Claude: Holds dozens of ad cards and your claims rules in one long chat.
• Google Sheets: Counts types per advertiser, so crowded and open cells are easy to check.
• Any good chat AI: Reading lines and reviews to find a recurring word is text work any strong chat AI does with this skill.
• Any good chat AI: Testing a rival against stated facts and writing the verdict is text work any strong chat AI does well with this skill.
• Your own sales and margin data: The overshoot and numbers tests rely on real figures.

Functions and deliverables

• Competitor ad change reviewer: Compare collected rival ads with last month. Find meaningful changes and up to two responses your evidence can support.
  • Counts by format, age and ad type for each rival, against its own last month
  • A list of rivals that moved and rivals that did not
  • Message and position changes for the rivals that moved
  • Ad gaps your proof can fill
  • Up to two moves worth answering, or a clear "none this month"
• Competitor ad format analyst: Count a rival's Meta Ad Library ads by format, age, landing page and awareness stage. Get content gaps and the longest-running ads to rebuild.
  • Counts of assets, copy lines and formats, and the share that are catalog ads
  • Median and oldest ad age, destination share and the awareness-stage mix
  • The share of ads that mention price, a discount or a guarantee, and which of the eight script beats are missing
  • Content gaps and a shortlist of the longest-running concepts
• Competitor messaging analyst: Name your rivals. Get a messaging and positioning comparison with content gaps. Reads public web pages.
  • A positioning comparison
  • A messaging and content review
  • Recent news and launches
  • A list of gaps to use
  Source: Anthropic.
• Competitor ad opportunity finder: Share competitor ads. Find messages and formats they overlook, with briefs for ads you could test.
  • A short summary and the top three gaps
  • A map of the category by ad type, crowded, thin or open
  • A card for every ad studied, and the claims everyone repeats
  • Briefs for each gap, with the proof each rests on and what to avoid
  • A score out of 100 for how many of its own checks the study passes, with each miss named
• Competitor brand association mapper: Share rival messages and buyer feedback. Get proposed word links, evidence gaps and possible space for your brand.
  • The one word buyers link to each rival, with how sure it is
  • A word-association result for the category
  • Each word marked taken, contested or open
  • Empty claims everyone makes
  • The opposite attribute to the leader's, and 3 open words to test
• Competitive disruption risk reviewer: Compare a cheaper rival with a disruption pattern. Get evidence-backed scores, missing facts and a response to consider.
  • A pattern-fit score out of 100, with what it measures
  • A verdict: nuisance, watch or real threat
  • A fact that argues against the verdict
  • A response with an owner and a date
• 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
• 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
• Al Ries: Clarify what a brand should stand for using Al Ries’s recorded approach. Examine its category, focus, name and launch story.
  • Your problem worked on the way Al Ries would: their questions, their method, their push-back
  • The answer or the work, in Al Ries'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 have three to six rivals you want to keep an eye on without a big monthly project.
• You want to know when a rival changes its offer, message or ad mix.
• You need a reason to act, or a reason to leave things alone.

Limits to check before starting

• You want a one-off study of rival ads: use the Competitor ad swipe file builder instead.
• You cannot collect rival ads on the same day each month: months will not compare well, so start with a one-time look by hand.
• You want to know what a rival spends or sells: no ad tool shows that, and this agent never guesses it.

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 this month's watch.
• Collect each rival's current ads from the public ad library on the same day each month, and put them in one folder.
• The first run builds the base for each rival and compares nothing. The second run is the first real comparison.
• Read the hand-back. Act on a move you agree with yourself, or ask for a brief for it.
• Run it again next month. It reads each rival's history file.

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-competitor-watcher 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.