Hire an AI media buyer

Everything it can hand back

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

• A checked baseline, trends and relevant segment analysis with source limitations.
• Ranked selectable recommendations with specific work, evidence, tradeoffs and measurement.
• A selected execution handoff, campaign/test briefs and verified implementation evidence for actions actually performed.

How it does the job well

• Diagnose with the funnel: cost to reach people, click rate, landing conversion and order value. Find which step changed.
• Give ad sets enough budget and time to leave the learning phase before judging them. Check current platform guidance.
• Change budgets in small steps so delivery is not reset.
• Refresh creative when frequency rises and click rate falls together.
• Judge spend on profit, using store or backend numbers, not platform-reported return alone.
• Never state an average cost, click rate, return rate or audience size as fact. If a figure is needed and the user gave none, say what to check in the ad platform.
• Platform features, formats and limits change. Mark any spec or setting "confirm on the platform's help page". If you have web search, cite the page and its date.

Mistakes it avoids

• Several changes at once, so the cause of a result is unknown.
• Trusting platform-attributed sales without checking them against the store.
• Changing live budgets, bids or audiences without approval.
• Copying the profile's sample targets or benchmarks as the user's facts.
• Recommending a platform because it is popular, not because it fits.
• Promising results, or calling a test a win before there is data.

What a good result looks like

An example, not your task: Investigate rising Meta purchase CPA or declining ROAS.

• Paid social plan. Your goal, budget and customer, with the platforms in and out and why.
• Platform picks. Each platform with why it fits, its share of budget and its main objective.
• Funnel and audiences. Each stage from first view to retargeting, with the audience, exclusions and ad format.
• Creative briefs. One brief per platform with format, hook idea, what to show and what to avoid.
• Measurement. What to track, where it is counted and where the numbers may not match.
• 30-day test plan. Tests with one change each, a budget and what a good result looks like for you.

How the work is checked

• Each finding compares like-for-like periods and names its data source.
• Each recommendation states the expected effect, risk and how it will be measured.
• Proposed live changes list the exact setting, old value and new value for approval.
• Every claim traces to the brand brain or supplied evidence.
• 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 Claude Hopkins would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Measurement and baseline. Verify event, scope, attribution, time, completeness and comparability; route unresolved collection faults to measurement work.
• Performance diagnosis. Analyze weighted totals, time trends, meaningful segments, mix and changes; retain competing explanations and low-count limitations.
• Selected execution. Turn evidence-backed choices into campaign and experiment work; hand accepted insights to creative, production or CRO and verify supported actions.
• Learning. Evaluate actual comparable outcomes against guardrails and retain scoped reviewed feedback in the user environment.

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 media-buyer 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/media-buyer/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

• The desired acquisition or revenue outcome and business guardrails.
• Scoped account data or an authorized read connection, metric definitions and relevant business context.

Helpful context (optional)

• A last-90-days export from each ad platform you use.
• Your best-performing videos, images or posts.
• A list of your customers, to build audiences from.

Tools and access

• Ad account exports and business facts
• An authorized ad-platform read connection or export; matching write authority only for approved business changes
• Claude, ChatGPT or Gemini with file upload: It can read an export from your ad platforms next to your goals, so budget and audience advice follows your real results.
• Your own ad platform dashboards: Use them to confirm formats, limits and audience sizes before you launch. The AI cannot see your account.
• Claude, ChatGPT or Gemini with file upload: The agent reads several exports and screenshots at once and does sums on them.
• Claude: Works the sums from a pasted export step by step and shows them, so you can check each one.
• Google Sheets: Lets you redo any number in the table yourself, from the same totals.
• Meta Ads Manager: Export both periods with reach, frequency and the attribution setting, and make any approved change there by hand.
• Claude, ChatGPT or Gemini with file upload: You can attach CSV exports so the AI reads real numbers instead of your summary.
• Google Ads, Microsoft Ads and Meta Ads Manager reports: Each platform lets you download the tables this audit needs.
• Claude Code: It can keep the sprint folder and remind you of the read date.
• Meta Ads Manager: Export ad-level results by ad set, and show the incremental column if your account has it.
• TikTok Ads Manager: Export ad-level results for the round if the sprint runs there.
• 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.
• Claude, ChatGPT or Gemini: A long chat can hold your tag list and your test results, so it can tighten the plan as you go.
• Google Tag Manager, GA4, Google Ads and Meta Events Manager: These show you the real setup and let you run each test in the plan.
• Any good chat AI: The sums are simple, and any current chat AI can run them and explain each step.
• Meta Ads Manager: Your spend, sales and cost per sale for each ad set come from here.
• Shopify: Your real order value and orders a week come from store reports.
• 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.
• Meta Ads Manager: Its export gives you spend, impressions, CTR and link CTR by ad. The Columns menu has the incremental attribution view.
• Any good chat AI: Any current chat AI can read an export and follow the metric order. Attach the file instead of retyping numbers.

Functions and deliverables

• Paid social advertising strategist: Plan paid ads on Meta, LinkedIn and TikTok. Get platform picks, a funnel, audiences, creative briefs, a budget split and a test plan.
  • A short list of platforms to use, with a reason and a share of budget for each
  • A funnel from first view to retargeting, with audiences and exclusions per stage
  • A creative brief per platform, with formats and what to show
  • A way to measure results, and where your tracking may be weak
  • A 30-day test plan with one change per test and what a good result looks like
  • Facts still missing and what to check in your own ad accounts
  Source: Michael Sitarzewski and Agency Agents contributors.
• Meta Ads results reviewer: Review your Meta Ads results against your targets. Get ranked findings, tracking gaps, proposed fixes and a checkpoint for the next review.
  • A setup check that says if your dates, currency, attribution and metrics line up
  • A ranked findings table with the evidence, the sum and how sure the AI is for each row
  • A tracking check that lists what is confirmed and what is not
  • A list of evidence gaps and the checks that did not run
  • A proposed actions list, with nothing changed in your account
  • A checkpoint file for your next review
• Ad sales drop analyst: Share two periods of ad totals and your target. Get the weakest link, ranked possible causes, next checks and a target-based score.
  • A table of every ad with its rates recalculated from the totals
  • The chain split, showing each link's share of the change in cost per sale
  • A ranked list of findings, tracking problems first, each with possible reasons, what to check and a proposed action
  • A list of the data that was missing and what it would have told you
  • A score out of 100 for each period, showing how close cost per sale is to your target (only when you give a target)
• Paid media auditor: Paste your Google, Microsoft or Meta ad exports. Get ranked account problems, each with proof from your data, a fix and the effort needed.
  • A plain-language summary for someone who does not run ads
  • A table of findings ranked critical, high, medium or low, each with proof, why it matters, a fix and effort
  • A rough size of the impact for the top findings, shown as an estimate from your numbers
  • A list of checks it could not run because the data was missing
  • A 30-day order for making the fixes
  Source: Michael Sitarzewski and Agency Agents contributors.
• Ad testing manager: Plan ad test rounds, read real results and use each lesson for the next plan, stopping after three rounds without a winner.
  • A test budget, a spend limit per ad and a read date for the round
  • Five untried ideas, each with designer-ready versions
  • A campaign layout with one idea per ad set
  • A keep, leave or replace call for each set after each round, and what it means
  • A running list of lessons, with dates
  • A call on whether the problem is the ads or the page after three rounds
• 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
• Conversion tracking planner: Plan or fix your ad conversion tracking across GA4, Google Ads and Meta. Get an event list, a double-count check and a step-by-step test plan.
  • A list of conversion events, each with its trigger, details to send and platforms that receive it
  • A plan for which conversion counts toward bidding and which are only for reporting
  • A plan to stop the same sale being counted twice
  • A consent and privacy section for your regions
  • A test plan for each event, with the tool to use and the result to expect
  • A ranked list of likely causes when your counts disagree
  Source: Michael Sitarzewski and Agency Agents contributors.
• Ad test budget calculator: Share your target cost per sale and test days. Get a daily budget, spend limits and a results-review window.
  • A total test budget and a daily budget, with the sum shown
  • A keep, wait or cut rule at each spend checkpoint
  • A read window and notes on day-of-week swings
  • What to do with a winner and with a loser
  • For high order values, a plan using cheaper signals and a rule for which ads move to paid
• 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 test analyst: Paste your ad test results by ad set. Get keep, leave or replace calls for each ad, false winners flagged and a score for how safe the read is.
  • A verdict for each ad set against your target
  • A table of every ad with keep, leave, replace or retest and the reason
  • False winners flagged, with the path from view to purchase for each ad
  • The next creative brief, and a read score out of 100 with its sum shown
• 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
• Claude Hopkins: Write specific ads or plan a small buyer test using Claude Hopkins’s recorded approach. Replace vague praise with facts and track cost per customer.
  • Your problem worked on the way Claude Hopkins would: their questions, their method, their push-back
  • The answer or the work, in Claude Hopkins'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

• Investigate rising Meta purchase CPA or declining ROAS.
• Review an existing paid-social account and plan supported remedies.
• Coordinate an accepted campaign or experiment through the available methods and real tools.

Limits to check before starting

• Platform reporting alone does not verify net profit, new-customer CAC or incremental lift.
• Creative production, website implementation and finance decisions need their relevant specialist methods and inputs.
• No assumed account connection, spending authority, promised CPA improvement or completed action without real evidence.

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 pack and add it to your AI as a skill. If you cannot, paste SKILL.md into a new chat, then paste references/source-agent.md.
• State your goal, monthly budget, customer and product. Paste recent results from each ad platform if you have them. No code is needed.
• Say which platforms you already use and what creative you have. Add your customer list size if you could use it for audiences.
• Read the platform picks and the "Facts still missing" list first. Add what you know and ask it to re-run the plan.
• Before you spend, check each setting and format in the ad platform itself. Ad tools change often, so confirm any limit or spec on its help page.
• Launch one test at a time. Record the result against your own numbers, not the plan's targets.

Read it as data

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