Hire an AI TikTok Ads budget reviewer

Everything it can hand back

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

• Each ad called keep, fix hook, fix audience, kill or too early, with the sums
• Posts worth boosting as Spark ads
• A raise, hold or cut call on budget, with the gate that decided it
• One ranked list of changes to approve
• The numbers to watch next week

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

• Changing the account on your own.
• Calling an ad good from TikTok's return alone, without break-even.
• Killing an ad on a day or two of data.
• Changing many things in one week, so next week cannot show what worked.
• Using this on an account spending very little. With about three ads or fewer, or a few dollars a day, the numbers are too thin to call; wait and gather more.
• Generic copy that could fit any brand.

What a good result looks like

An example, not your task: You run TikTok ads and want each ad judged the same way every week.

• This week. One line with spend, purchases, cost per purchase and return, set against your break-even.
• Ads called. Counts of keep, fix, kill and too early, with each ad named and its one fix or reason.
• Spark picks. Posts worth boosting as Spark ads, or a note that there are none this week.
• Changes to approve. A ranked list of changes with where, size, which step proposed each and why.
• Scale call. Raise, hold or cut on budget, with the gate that passed or failed.
• Watch next week. One to three numbers that decide next week's path.

How the work is checked

• Every call is measured against break-even, and the sums are shown.
• No ad under three days old was killed.
• No budget raise is proposed unless the gates passed this week.
• An ad fixed last week and still failing is called KILL, not fixed again.
• 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

• Get the base number. Works out your break-even cost per sale once, then measures every ad against it.
• Check the setup. On the first run, checks your pixel and events. If tracking is broken, it stops the ad calls, because the numbers can't be trusted.
• Read each ad. Calls each ad keep, fix or kill. Ads under three days old are left alone. An ad fixed last week that still fails is killed.
• Pick posts to boost. If you gave it organic or creator posts at least five days old, it picks the ones worth boosting as Spark ads.
• Check the real return. Once a month, or after a sudden jump, it compares TikTok's return with your store totals and saves the factor.
• Check before scaling. Only when half the ads keep and the true return beats break-even does it split a budget raise. Otherwise it holds.
• Hand back one list. Merges every change, removes repeats, keeps the more careful call when steps disagree, and 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 tiktok-ads-weekly-account-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/tiktok-ads-weekly-account-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

• A TikTok Ads export with one row per ad for the last 7 days
• Your price, landed cost, shipping and fees, the first time
• Organic or creator posts with their results (optional)
• Your store orders and revenue for the same days (optional, for the monthly return check)

Helpful context (optional)

• A note of every change you made in the account last week
• Your organic and creator post results

Tools and access

• Claude Code: It can keep the keeper folder and ad log, read last week's files and run every step on a schedule.
• TikTok Ads Manager: Export the ad-level report here, with spend, CTR, watch time, add to cart and purchases.
• Any good chat AI: Any current chat AI can do the sums if it shows its working. Check one product by hand first.
• Shopify admin: The Cost per item field on each product feeds live margin reports, so your numbers stay current.
• TikTok Pixel Helper: A Chrome add-on that shows which events fire as you walk through your store.
• TikTok Events Manager: Shows pixel status and each event's count, and has a test events tool.
• Shopify: Paid plan needed. The official TikTok app installs the pixel and sends purchase events.
• TikTok Ads Manager: Export the ad-level report with CTR, CPM, CPC and cost per result for the days you want.
• Google Sheets: Keep one row per ad and per day to see how the lines move.
• TikTok Ads Manager: Needs a TikTok ads account with a payment method, and boosting costs ad spend. Where you add a post under TikTok post and paste the creator's code.
• TikTok Creator Marketplace: A place to find creators and agree on terms before you ask for a code. It needs a TikTok account, and access and any fees can change, so check TikTok's current terms before you plan around it.
• Any good chat AI: Any chat AI can run the ladder and the score. Check the store base by hand.
• Meta Ads Manager: Lets you compare attribution settings and break results down by new, engaged and existing audiences.
• Shopify: Gives new-customer revenue and orders, and a cohort report for your own repeat data.
• A post-purchase survey app: Collects where buyers say they first heard of you, so you can compare it with platform data.
• Claude, ChatGPT or Gemini with file upload: It can read your full exports instead of a pasted sample.
• Any good chat AI: The ranking is arithmetic and reasoning on numbers you paste, so any current chat AI can do it.
• Meta Ads Manager: Its audience breakdown shows your CPM and frequency on existing customers, and it runs lift studies.
• GA4: Gives a second view of new-customer revenue to set beside the platform reports.

Functions and deliverables

• TikTok Ads budget reviewer: Review eligible TikTok ads against costs and tracking. Get keep, fix or stop proposals and budget gates to check.
  • Each ad called keep, fix hook, fix audience, kill or too early, with the sums
  • Posts worth boosting as Spark ads
  • A raise, hold or cut call on budget, with the gate that decided it
  • One ranked list of changes to approve
  • The numbers to watch next week
• Product margin checker: Check your product margin before you set ad targets. Give it a price and every cost. Get gross margin, break-even ROAS and CAC, and a score.
  • Product margin against true gross margin, with the gap in dollars and points
  • Break-even ROAS and break-even CAC
  • The three margins, labelled product, gross (CM2) and contribution (CM3)
  • A go or no-go flag and a score out of 100, with the sum shown
• TikTok ads account setup checker: Check your TikTok ads account setup before you spend. Get missing steps, a pixel event check and a readiness score out of 100.
  • Each checklist item marked done, missing or not sure
  • One fix for each gap, with the first things to do listed in order
  • A pixel event table showing which events fire
  • A setup readiness score out of 100 and a launch call
• TikTok ad test reader: Paste your TikTok ad test numbers. Get a keep, fix or kill call for each ad, the likely cause, and a score out of 100 for each ad and the test.
  • A call for each ad: keep, fix hook, fix audience, kill or too early
  • The likely cause of each problem
  • A score out of 100 for each ad and for the test
  • A plan for the next test
• TikTok Spark ad picker: Find which TikTok posts to boost as Spark ads. Give your posts and results. You get a shortlist, a creator request and a test plan.
  • A shortlist of the posts to boost, with the reason for each
  • A list of posts held back and why
  • The steps a creator follows to give you the code, and a draft message to send
  • A test plan against your current best ad
• Ad return evidence checker: Share ad reports and store totals. Get matched comparisons, evidence gaps and a custom review score, without a causal sales claim.
  • A comparison of reported measures, definitions, periods and missing coverage
  • A supported top-ad breakdown with audience and attribution limits
  • The evidence basis and next check for each proposed budget decision
  • A bounded custom checklist score with missing checks shown
• TikTok Ads account auditor: Find where your TikTok ad money leaks. Give it your TikTok Ads exports and get an audit of tracking, creative, bids and budgets, with proof.
  • A short health summary of the account
  • Findings with the source number behind each one
  • Ranked fixes with a small first step for each
  • A list of features it left unscored
  • A list of what it could not check
  Source: Daniel Agrici.
• Marketing budget allocation planner: Share channel spend, new-customer sales and test results. Rank small budget changes by evidence, then set stop points and a fallback.
  • A ranking of where the next $10,000 goes, and what a $10,000 move between channels would do
  • A stop point for each channel
  • A test plan to measure the return on the next dollar
  • A rule for how much to put into brand content and how to judge it, if you want that shift
  • A fallback rule and a loss limit
• 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

• You run TikTok ads and want each ad judged the same way every week.
• You have organic or creator posts and want to know which are worth boosting.
• You want to raise your budget, but only when the numbers say it is safe.

Limits to check before starting

• You spend a few dollars a day or run about three ads or fewer: wait and gather more data, because the numbers are too thin to call.
• You want a read on one ad only: use the TikTok ad test reader, one of the steps this agent runs.
• You have not set up your pixel or events yet: fix tracking first, or use the TikTok Ads account setup checker.

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 week's check.
• Put this week's export in one folder, or attach it in the chat.
• The first time, give it your price and costs. It saves the break-even number and reuses it.
• Read the change list. Make the changes you agree with in TikTok Ads, or say yes to each one and let it make only those if it is connected.
• Run it again next Monday. It reads last week's ad log.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/tiktok-ads-weekly-account-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.