1. Library
  2. Edition 2.0
  3. AI Media Buying

Edition 2.0

AI media buying with the controls left in.

How to use Claude for research, diagnosis, reporting and creative operations on Meta, and how to let it propose changes without ever handing it the budget.

For media buyers, performance marketers and agency teams. About 180 minutes across 14 chapters. Facts checked .

Replaces the AI Media Buying Framework (V1), which is kept online for people arriving from older videos.

Get the full guide

Free. 14 chapters, about 180 minutes. One sign-up opens all three Edition 2.0 guides on this device.

Start with your country code, for example +971, +966 or +20.

Chapters

14 chapters. Take them in order; each one ends with a task and a checklist.

  1. 01

    What changed since V1

    Meta automated the campaign structure, removed two attribution windows and shipped its own AI connectors. Find the V1 habits that now break, and see which chapter teaches each job you want Claude to do.

    10 minDone
  2. 02

    Read, propose, approve, execute

    The operating model behind every workflow in this guide. Five separate authorities, what each boundary must enforce, three working modes, labelled evidence, and the decision-rights card that fixes who may approve what.

    13 minDone
  3. 03

    Set up a safe Claude workspace

    Pick a Claude surface, install and verify Claude Code, learn the five terminal commands you need, then build a media-buying project folder with secrets blocked, project memory in CLAUDE.md and a first task on synthetic data.

    12 minDone
  4. 04

    Data, attribution and evidence

    Get data to Claude in a form it can trust. Four ways in, a safe export procedure, the attribution facts that changed in 2025 and 2026, a data contract, tracking health, what never goes to a model, and how to keep hypotheses separate from causes.

    14 minDone
  5. 05

    Daily diagnosis, monitoring and reports

    A morning routine in a fixed order. Signal health, the morning diagnosis, four monitor watches, alerts that run inside Meta, anomaly triage, and daily, weekly and monthly report templates, all without giving Claude write access.

    15 minDone
  6. 06

    Budgets, tests and scaling proposals

    Replace fixed ROAS rules with break-even and target numbers from your own margins, then run the weekly budget review, draft a monthly allocation, plan tests, choose a scaling move and read market signals, all as proposals with a rollback rule.

    15 minDone
  7. 07

    Creative operations

    Creative is the input you still control. Turn customer language into themes and store fixes, keep a claims library, write copy by angle, stage and placement, brief winner variations, take assets from a folder to a named and mapped plan, and stay inside Meta's AI disclosure rules.

    14 minDone
  8. 08

    Launches, destinations and stock

    Take a brief to a paused draft that passes QA, launch a new product with alerts set in advance, check every destination that receives paid traffic, and keep ads away from products that cannot sell.

    14 minDone
  9. 09

    Skills and SOPs that hold

    Turn your SOPs into Claude skills that make good work repeatable. Where skill files live and how they load, a full template, V1's budget optimiser rebuilt as a skill, an evaluation set to test it, chaining without chaining trust, and the controls a skill cannot replace.

    15 minDone
  10. 10

    APIs, docs and version changes

    What an API is and is not, how to tell a read from a write, how to read a Meta Marketing API reference page, V1's campaign example corrected, five error categories with the right response to each, and the protocol to follow when Meta changes the API.

    11 minDone
  11. 11

    Development versus production credentials

    Set up a Meta development app and test account that cannot spend real money, choose the right credential for development, staging and production, decide where each one may live, read store data safely, and check every token before you trust it.

    15 minDone
  12. 12

    The approval machine

    The controlled agentic pattern end to end. Claude returns a schema-checked proposal, a person approves its exact hash, and a small executor applies only that, within caps, paused by default, with a journal and a reconciliation pass.

    15 minDone
  13. 13

    Security, policy and incidents

    The threats that actually hit AI media-buying setups and the control that stops each one, prompt injection, connectors, browser agents, client separation, the Meta and Anthropic policies you operate under, and a step-by-step incident playbook.

    10 minDone
  14. 14

    Rollout, operations and readiness

    A staged path from synthetic data to production, the evidence each stage must produce, a first-month plan, the metrics that show whether the system itself is healthy, the re-verification calendar, and the final readiness check.

    9 minDone

What changed since V1

  • Meta now runs most delivery decisions itself. The AI’s job moved from tweaking bids to diagnosing, briefing creative and proposing changes.
  • Credentials are split by environment: short-lived tokens for testing, system users for production, and no token ever inside the model’s context.
  • Official connectors and Agent Skills replace copy-pasted scripts and prompt-only guardrails.
  • Every write goes through a proposal, a human approval and a deterministic executor that creates objects paused.

Review status

Beta Available for testing; behavior and interface may change. Next review due .

  • Owner review of every chapter before the status moves from beta to active
  • Re-verify Meta API version, token and access-tier facts at each quarterly Marketing API release
  • Replace synthetic examples with account-calibrated thresholds before any implementation

Primary sources used in this guide

Official documentation and changelogs only. When a source and this guide disagree, the source wins.

  1. Marketing API versions Meta
  2. Introducing Graph API v26 and Marketing API v26 Meta
  3. Marketing API v25.0 changelog Meta
  4. Advantage+ campaigns Meta
  5. Out-of-cycle changes 2025 Meta
  6. Marketing API v26.0 changelog Meta
  7. Meta ads AI connectors Meta
  8. Advertising Week New York 2026 Meta
  9. Install apps and generate system user tokens Meta
  10. Claude connectors directory Anthropic
  11. Claude Code security Anthropic
  12. Marketing API overview Meta
  13. Structured outputs Anthropic
  14. Claude Code advanced setup Anthropic
  15. Terminal guide (Claude reads images in your folder) Anthropic
  16. Claude Code overview (scheduled tasks) Anthropic
  17. How Claude remembers your project Anthropic
  18. Configure permissions Anthropic
  19. Claude Code sandboxing Anthropic
  20. Claude Code permission modes Anthropic
  21. Claude Developer Platform workspaces Anthropic
  22. Ad account insights reference Meta
  23. Insights limits and best practices Meta
  24. Out-of-cycle changes 2026 Meta
  25. Ad set reference (learning_stage_info) Meta
  26. Split testing Meta
  27. Conversions API Meta
  28. Deduplicate Pixel and server events Meta
  29. Meta Business Tools Terms Meta
  30. Custom conversion reference Meta
  31. Meta Platform Terms and Developer Policies Meta
  32. Ad Rules Engine Meta
  33. Ad rules execution spec Meta
  34. Marketing API rate limiting Meta
  35. Pricing (Batch API discount) Anthropic
  36. Budgets Meta
  37. Advantage campaign budget Meta
  38. About daily budgets Meta Business Help Center
  39. Currencies and offsets Meta
  40. Ads MCP server A/B tests and conversion lift studies Meta
  41. Ad Library API (ads_archive) Meta
  42. Automated Data Collection Terms Meta
  43. URL tags for tracking Meta
  44. Generative AI transparency in Meta's ads products Meta
  45. Meta prepares for the 2026 US midterms Meta
  46. Ads MCP server overview Meta
  47. Anthropic Usage Policy Anthropic
  48. Ad campaign reference Meta
  49. Ads MCP server ad creation and management tools Meta
  50. Product sets reference Meta
  51. Advantage+ catalog ads Meta
  52. Shopify access scopes Shopify
  53. Playwright MCP Microsoft
  54. Extend Claude with skills Anthropic
  55. Hooks reference Anthropic
  56. Claude Code MCP configuration and scopes Anthropic
  57. Define success criteria and build evaluations Anthropic
  58. Ads MCP server rules best practices Meta
  59. Marketing API error reference Meta
  60. Graph API error handling Meta
  61. Marketing API versioning Meta
  62. Meta Node.js Business SDK releases Meta
  63. Marketing API get started Meta
  64. Access tokens Meta
  65. Get long-lived tokens Meta
  66. System users Meta
  67. Securing requests (appsecret_proof) Meta
  68. debug_token reference Meta
  69. Marketing API authorization and access tiers Meta
  70. Marketing API changelog (access tier rename) Meta
  71. Ads MCP server, get started Meta
  72. Authorizing access for AI tools Shopify
  73. Shopify API versioning Shopify
  74. Shopify client credentials grant Shopify
  75. Models overview Anthropic
  76. Using Claude in Chrome safely Anthropic
  77. Custom connectors (unlisted) Anthropic
  78. MCP authorization specification 2025-11-25 Model Context Protocol
  79. Meta Terms of Service Meta

Education, not legal, security or financial advice. Never paste a live access token, API key or customer data into an AI chat, a prompt, a screenshot or a public repository.