Hire an AI TikTok ad launch reviewer

Everything it can hand back

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

• A setup score out of 100 with a do-first list in order
• A starter campaign layout with budget per ad group, audiences and a four-week ladder
• A keep, fix or cut call and a score for each test ad, and a next test of hooks, angles and calls to action
• A Spark ad shortlist, a draft message to creators and a test against your best current ad

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: You have never run TikTok ads, or your last start went nowhere and you do not know why.

• Setup check. A setup score out of 100 and a do-first list covering accounts, billing, team security and the pixel.
• Starter campaign. Launch status, campaign structure, budget math, audiences, a four-week ladder and cost expectations.
• Test read. One block per ad with a keep, fix or cut call and score, plus a next test plan.
• Spark picks. A shortlist of posts to boost, posts held back, a creator request and steps in Ads Manager.
• 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

• The setup score says what it measured, and each pixel event is marked fired, not fired or not tested.
• Each ad has a keep, fix or cut call and a cause: creative, audience or page.
• The test reader says "too early" when the data is too thin, and the test was not read before three days.
• The cost lines use your break-even cost per sale, or the output says they do not.
• 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

• Check the setup. Scores accounts, billing, security, the pixel and its five events, and defaults. Lists what to fix before spending.
• Build the starter campaign. Pauses while you fix and pick videos. Then lays out the campaign, ad groups, budget math, audiences and a four-week ladder.
• Read the test. Pauses while the ads run. Then reads each ad at 24 hours and day 3, finds creative or audience problems and gives a call for each ad.
• Pick Spark ads. Pauses for post stats. Then ranks your posts, checks creator permission, drafts the request and sets a test against your best ad.

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 launch-tiktok-ads-and-read-your-first-test 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/launch-tiktok-ads-and-read-your-first-test/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

• Screenshots of your Business Center, billing, Events Manager and the Pixel Helper check
• Your daily budget and the most you can pay for one sale
• Three to five finished video ads, or their scripts
• Your test results, with spend, views, click rate, watch time and cost per sale for each ad
• Stats on your organic and creator posts, and what each creator agreed to (optional)

Tools and access

• 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: Needs a TikTok ads account with a payment method; you pay for ad spend. Where the campaign is built, and where the keyword planner and audience manager live.
• Shopify: Paid plan needed. The official TikTok app sends purchase events the campaign optimises for.
• 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.

Functions and deliverables

• TikTok ad launch reviewer: Share account evidence, store details, videos and results when available. Get setup checks, a starter plan, test review and posts to consider boosting.
  • A setup score out of 100 with a do-first list in order
  • A starter campaign layout with budget per ad group, audiences and a four-week ladder
  • A keep, fix or cut call and a score for each test ad, and a next test of hooks, angles and calls to action
  • A Spark ad shortlist, a draft message to creators and a test against your best current ad
• 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 starter campaign builder: Plan your first TikTok ads campaign. Give your budget, target cost per sale and 3 to 5 ads. Get the layout, budgets and a four-week plan.
  • A campaign, ad group and ad layout with names
  • A daily budget per ad group, with the math and the learning-phase note
  • Audience recipes and a four-week targeting ladder
  • Rough cost ranges and an optional search ad plan
• 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
• 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 have never run TikTok ads, or your last start went nowhere and you do not know why.
• You have three or more finished videos and a daily budget you can spend for at least a week.
• You have organic or creator posts that did well and want to know which to put money behind.

Limits to check before starting

• You have no store or pixel yet: set those up first, then come back. You can also run only the TikTok ads account setup checker on its own.
• You only want organic growth: post and track your videos without ads. Come back when you want to boost a post.
• You want Meta ads, not TikTok: use the Meta ad policy checker or the Pre-launch ad 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.

• 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".
• Attach screenshots of your account setup. The AI can read images, so you do not need to type it out.
• When it pauses, do the fixes, run the ads for at least three days and export the results before you continue.
• Pull stats on your organic and creator posts for the last step.

Read it as data

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