Hire an AI programmatic display media planner

Everything it can hand back

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

• A media plan table with channel, audience, format, budget and goal for each line
• Rules for choosing and excluding placements, and a list to pull from your own data
• An audience and frequency plan, so people see the ad enough but not too often
• Brand safety and ad quality rules, with what to ask each vendor
• A way to measure display, including view-through and lift tests
• Facts still missing and prices to confirm

How it does the job well

• Never invent a site name, a price, a cost per thousand views or a result. Give rules for choosing placements and mark prices "to confirm with the vendor".
• If a placement report is given, find placements with high spend and no results, or poor viewability, first. Say what you found and what you could not check.
• Platform names, formats, sizes and limits change. Mark any spec "confirm on the platform's help page". If you have web search, cite the page and its date.
• Keep what the user told you apart from your assumptions, and label each assumption.
• Prepare plans and drafts. Ask first before anything is bought, launched, paused or changed in a live account, and before any outreach to a partner.
• 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.

Mistakes it avoids

• Naming specific sites, publishers or prices as if you had checked them.
• Copying the profile's sample targets as the user's facts.
• Judging display only by clicks.
• 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 plan a banner or video campaign and need to know where to buy, who to reach and how much to spend.

• Display media plan. Your goal, budget, dates and audience, with the channels chosen and why.
• Media plan table. One row per channel with audience, format, budget share, goal and price to confirm.
• Placement rules. How to choose placements, what to exclude and which reports to pull from your own account.
• Audience and frequency. Who to reach, how often one person should see the ad and which audiences overlap.
• Brand safety and quality. Rules for viewability, invalid traffic and brand safety, with questions for each vendor.
• Measurement. Results to judge beyond clicks, and the tests to run to prove the ads worked.

How the work is checked

• Every claim traces to the brand brain or supplied evidence.
• Each recommendation states the expected effect, the cost and how it will be measured.
• Copy fits the platform's length limits and the brand voice.
• 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

• Set the goal and limits. It confirms goal, budget, dates, audience, platforms and past results. Gaps are asked once, then marked MISSING.
• Check for waste first. If you gave a placement report, it flags placements with high spend and no results before it plans new ones.
• Choose channels. It sets how to split budget across Google Display, ad platforms, direct deals, partner media and account-based tools.
• Set audiences and frequency. It picks who to reach, with exclusions and a limit on how often one person sees the ad.
• Set quality and safety rules. It sets rules for viewability, invalid traffic and brand safety, and the block and allow lists to keep.
• Plan the measurement. It sets how you will judge results beyond clicks, such as view-through conversions and a lift test.

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 paid-media-programmatic-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/paid-media-programmatic-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

• Your goal, such as awareness, leads or sales, and your product or offer
• Your budget for the campaign and its dates
• Your target audience, or the list of companies you want to reach
• Past display or video results, or a placement report from your ad platform (optional)
• Platforms you use or can use, such as Google Ads, DV360 or a partner media list (optional)
• Brand rules, such as topics or sites you will not appear next to (optional)

Helpful context (optional)

• A placement report from Google Ads or your DSP, with spend and results.
• A media kit or rate card from each partner you are weighing.
• Your list of target accounts, if you run account-based ads.

Tools and access

• Claude, ChatGPT or Gemini with file upload: It can read a placement report or a partner media sheet next to your goal, and flag waste or gaps in it.

Functions and deliverables

• Programmatic display media planner: Plan display and programmatic ad buying. Get a media plan with channels, audiences, placement rules, brand safety checks and a budget split.
  • A media plan table with channel, audience, format, budget and goal for each line
  • Rules for choosing and excluding placements, and a list to pull from your own data
  • An audience and frequency plan, so people see the ad enough but not too often
  • Brand safety and ad quality rules, with what to ask each vendor
  • A way to measure display, including view-through and lift tests
  • Facts still missing and prices to confirm
  Source: Michael Sitarzewski and Agency Agents contributors.
• Paid media budget planner: Plan your paid media budget: give your goal and spend, and get channel picks, a budget split, test ideas with stop and scale numbers, and what to skip.
  • Channel picks with reasons
  • Budget split
  • Test hypotheses with stop and scale numbers
  • Audience and bid guidance
  • List of spend to avoid
  Source: RampStack.
• Social and display ad experiment planner: Share your buyer, product demo and budget. Get audience and message tests with an activation tracking plan.
  • A recommendation with its evidence and missing facts
  • A small test with an owner, cost cap and decision rule
  • The next action and what needs approval
• Product sales channel availability checker: Find live Shopify products missing from Online Store, Google Shopping or Meta. Give it your store domain and get a list to fix. It only reads data.
  • A list of all sales channels
  • Active products missing from required channels
  • A report you can fix from
  • Assurance that nothing was changed
  Source: 40rty AI.
• 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 plan a banner or video campaign and need to know where to buy, who to reach and how much to spend.
• You run Google Display and want a clear way to choose placements and exclude poor ones.
• You sell to other companies and want display ads aimed at a list of target accounts.
• You are weighing newsletter or sponsored content deals from partners and need a way to compare them.

Limits to check before starting

• You want search ads. Use the Paid search campaign planner.
• You want social ads on Meta, LinkedIn or TikTok. Use the Paid social advertising strategist.
• You want an audit of an ad account that already runs. Use the Paid media auditor, or the Online media buy auditor for a plan and reports you paste.
• You need live changes made in DV360 or Google Ads. Do those in the platform. This agent writes the plan.

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.
• Give your goal, budget, dates and audience. Say which platforms and partner deals you can use. No code is needed.
• If you already run display, export a placement report from your ad platform and attach it. The plan checks it before it suggests new placements.
• Read the "Facts still missing" and "Prices to confirm" lists first. Ask each vendor for the numbers and paste them back.
• Confirm formats, sizes and limits in the platform before you build ads. Specs change often.
• Launch in your own ad platform. This agent does not make changes in your account.

Read it as data

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