Hire an AI ad decline tracker and replacement briefs

Everything it can hand back

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

• A list of sliding ads, each with its last runs of numbers and the cause
• Weak ads that never worked, kept apart from tired winners
• 10 or more hook briefs for each proven winner, each tagged with what it changes
• New ad ideas with briefs, when the whole account looks the same
• A pace for each winner that fits your stock and cash
• A list of pauses, budget moves and launches to approve

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

• Calling a fresh ad tired. Give each ad time to leave the learning stage first.
• Writing new hooks for an ad that never worked.
• Pushing a winner hard when stock or cash is short.
• Pausing an ad on one bad day.
• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.

What a good result looks like

An example, not your task: You have one or two ads that carry most of your spend and you want warning before they fade.

• Sliding ads. Each ad with its last runs of return, frequency and click rate, and whether the ad is spent or the audience is small.
• Not fatigue. Weak ads that never met the target, each marked as a pause candidate or needing more spend.
• Replacement briefs. Hook briefs for each proven winner, each tagged with what it changes, plus new idea briefs if needed.
• Pace. Whether to squeeze the winner or run it lower for months, based on your stock and cash.
• Backups. Formats to add now if one ad holds more than half of your spend.
• Changes to approve. Pauses, budget moves and launches, each with a reason. Nothing happens without your yes.

How the work is checked

• Every slide is shown with its numbers from at least two runs.
• No hooks were written for an ad that never met the target.
• No hook repeats one in hooks-used.md.
• Every hook is true to the product. No invented customers, experts or results.
• 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 Eugene Schwartz and John Caples would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Read the history. Opens the saved rows for each ad and adds this run's numbers, so a trend comes from data.
• Spot the slide. Flags an ad when its return falls two runs in a row while frequency climbs, or when the daily check flags it.
• Sort each flagged ad. An ad that never met the target is a weak ad, not a tired one, and gets no hooks. A proven winner goes on to be revived.
• Revive the winners. Calls the cause, sets the pace from your stock and cash, and writes hook briefs that keep the winning body.
• Check for sameness. If many ads slide together, it groups the live ads by idea. A high score means the account needs new ideas, not new hooks.
• Find new ideas. When the account repeats itself, it finds ideas you have not tried and turns them into designer-ready briefs.
• Plan the backups. If one ad holds more than half of spend, it names the formats to make now.
• Log and hand back. Saves the hook list so nothing repeats, then stops for your yes.

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 ad-fatigue-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/ad-fatigue-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

• Ad results for the last 7 days, one row per ad, with spend, purchases, frequency and click rate
• The cost per sale or ROAS each ad needs to hit
• The history file from your last run, once it exists
• Stock and cash for your best seller, and the words of your winning ad (advised)
• Your brand brain, if the account needs new ideas

Helpful context (optional)

• The transcript of your best ad
• Your stock position for the products you advertise most

Tools and access

• Claude Code: It can keep the history files and run on a timer.
• Meta Ads Manager: Export ad-level results with frequency, hook rate and hold rate. The export needs no setup. A direct read-only link needs access through your own login or token.
• Any good chat AI: The paste route is reading and arithmetic only. Claude, ChatGPT and Gemini all handle it.
• Meta Ads command line tool: It lets an AI that can run commands read your account read-only, with your own token.
• Meta Ads Manager: It shows spend, frequency and hook and hold rate for the fading ad, and runs the opener tests.
• Instagram trial reels: A cheap way to read how far a hook travels and where viewers drop, if the feature is open to your account.
• Any good chat AI: Any current chat AI can write hook briefs from a transcript and a list of levers.
• Any good chat AI: Any current chat AI can group a pasted table of ads.
• Meta Ads Manager: Source of ad-level frequency over 30 to 60 days for cold campaigns.
• Meta Ads Manager: An export by ad gives the 'measured' grade, with spend and results for each ad over the dates you pick.
• Meta Ad Library: Shows the ads your page runs now, with start dates, when you have no export to work from.
• Google Sheets: Keeps one row per past ad, so each lens and the moments grid are filters you can check.
• Meta Ads Manager: An export by ad for the last 1 to 4 weeks shows spend, purchases and frequency, which pick explore, extend or refresh.
• Meta Ad Library: Shows what runs now, as 'observed' evidence when you have no export.
• Google Sheets: Tracks cost per sale and frequency week by week, so you can see when a winner starts wearing out.
• Any good chat AI: Any current chat AI can sort a pasted list of ads and set targets.
• Meta Ads Manager: Source of your live ads and spend by ad.

Functions and deliverables

• Ad decline tracker and replacement briefs: Compare each ad with its history. Separate declining past winners from weak ads and prepare replacement briefs only where the evidence supports them.
  • A list of sliding ads, each with its last runs of numbers and the cause
  • Weak ads that never worked, kept apart from tired winners
  • 10 or more hook briefs for each proven winner, each tagged with what it changes
  • New ad ideas with briefs, when the whole account looks the same
  • A pace for each winner that fits your stock and cash
  • A list of pauses, budget moves and launches to approve
• Meta ads daily checker: Check your Meta (Facebook and Instagram) ads in five minutes a day. Get spend pacing, winners, money wasters and tired ads from your own numbers.
  • Spend against your budget and target
  • A list of what is running
  • Seven-day results by campaign
  • Your top 3 winners and bottom 3 losers, with numbers
  • Signs of creative fatigue, with the numbers behind them
  • Lines to add to your own learnings file
  Source: Matt Berman.
• Fading ad refresh planner: Give it a fading winner's numbers. Get the cause, ranked revival moves and 10 hook briefs.
  • A cause call, with the numbers behind it
  • Ranked revival moves and a pacing plan that fits your stock
  • 10 or more hook briefs, each tagged with the lever it changes (3 for a small budget)
  • A shoot list, a test plan with names, and a log of what changed
• Ad sameness checker: Share your ads with buyer, message, offer and format. Get idea groups, a repeat score and specific changes for repeated ideas.
  • Clusters of ads that are really one concept
  • A sameness score out of 100, with the sum shown
  • Which ads to replace, and what to change in each (persona, angle or offer)
  • A list of cold ads with a frequency above 2
• Untried ad idea finder: Find untried ad ideas for your brand. Paste your past ads and brand file. You get a gap map and five ad ideas, each one a clear test.
  • A record of every past ad, with each result graded measured, reported or seen running
  • Five lenses and a list of your proof, showing what's covered, thin or open
  • The five biggest gaps, ranked, plus the proof worth collecting
  • Five ad ideas, each with its test question, a five-link check, headlines and an opening
  • Any check the map still missed, one line each
• Ad test brief writer: Share brand facts and any ad results. Get three ideas, nine distinct designer briefs and questions to fill key gaps.
  • A header with the evidence grade, the plan chosen and why
  • Three ad ideas, each aimed at a different buyer doubt, with a filled-in thinking block
  • Nine versions with layout, headline, picture and what each one changes
  • A footer listing guesses and the questions to ask the founder
  • Any check the brief still misses, one line each
• Ad creative mix planner: Plan your ad mix: give it your live ads and get a target split by source, stage and format, plus which formats to add or retire.
  • A target mix by source, stage and format
  • Which formats to add and which to retire
  • 10 to 15 distinct format and angle slots
  • An ad set layout across stages, and a pain-versus-desire balance
• 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
• Eugene Schwartz: Match a headline or sales page to what buyers already want and know. Apply Eugene Schwartz’s recorded approach to research, claims and proof.
  • Your problem worked on the way Eugene Schwartz would: their questions, their method, their push-back
  • The answer or the work, in Eugene Schwartz's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• John Caples: Write headlines and plan a fair ad test through John Caples’s recorded approach. Lead with the reader’s gain and count replies by version.
  • Your problem worked on the way John Caples would: their questions, their method, their push-back
  • The answer or the work, in John Caples'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 one or two ads that carry most of your spend and you want warning before they fade.
• A winner has started to slip and you need a replacement plan, not a guess.
• Your ads all look alike and results are flattening.

Limits to check before starting

• Your account has only a few sales a day. The numbers swing too much, so check once a week by hand or ask your AI for a plain ad review.
• You want to check an ad against Meta's rules before it goes live. Use the Meta ad policy checker instead.
• You have one ad that never worked. A new opening will not fix it, so pause it or give it more spend.

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 today's check.
• Put this week's ad results in one folder, or attach them in the chat. The export works with no connection. A read-only Meta connection needs your own login or access token, and some connector tools charge a fee.
• Give it your target and, for your best ad, the transcript.
• Read the list. Approve the pauses and launches you agree with.
• Run it again in three or four days. The first run only starts the history. From the second run it looks for a slide.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/ad-fatigue-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.