A1: Why AdCP
Free module — No account required. ~15 minutes with Addie.
Learning objectives
By the end of this module, you should be able to:- Explain why agentic advertising is a paradigm shift from programmatic
- Describe what AI agents are and how they differ from traditional APIs
- Articulate the fragmentation problem AdCP solves
- Recognize AdCP’s breadth: 20 channels from display to local radio to cinema
- Explain how campaign governance provides always-on compliance for autonomous agent transactions
Reading list
Review these pages before starting the module with Addie. They provide the conceptual foundation for everything in the certification program.Introduction to AdCP
What AdCP is, how it works, and the protocol domains. Start here if you’re completely new.
Why AdCP
The strategic vision: allocation vs day trading, the fragmentation problem, and why agents need a shared protocol.
Protocol comparison
How AdCP compares to OpenRTB, platform APIs, and direct IO. Understand where agentic advertising fits in the landscape.
Building with AdCP
See how to implement AdCP. Optional but helpful for building intuition.
Campaign governance
How campaign governance ties campaigns to media plans and validates every transaction autonomously.
Embedded Human Judgment
The five principles that define how humans stay in control when agents execute autonomously.
Key terms
| Term | Definition |
|---|---|
| Agentic advertising | Advertising executed by AI agents that can reason, negotiate, and adapt — as opposed to rigid API integrations |
| AI agent | Software that perceives its environment, makes decisions, and takes actions autonomously |
| AdCP | Ad Context Protocol — an open standard that gives AI agents a shared language for advertising |
| MCP | Model Context Protocol — a standard for connecting AI models to external tools and data sources. AdCP uses MCP as its transport layer |
| Task | A discrete advertising operation (e.g., get_products, create_media_buy) defined by AdCP |
| Campaign governance | Always-on compliance that ties campaigns to media plans and validates every transaction through three independent parties |
| Embedded Human Judgment | The principle that humans define intent, set boundaries, and retain override authority — agents execute within those boundaries |
What you’ll do with Addie
This module is grounded with a live agent query — you’ll see a realget_products response from @cptestagent, not a slide deck. Addie will guide you through:
- What makes an AI agent different from a traditional API?
- Why does a shared protocol matter for AI-powered advertising?
- What problems arise if every ad tech company builds their own agent protocol?
- How does the “allocation vs day trading” framing change how you think about media buying?
- How do you trust AI agents to spend your money? (Always-on compliance: every transaction validated against the plan, grounded in Embedded Human Judgment principles)
- 20 channels: display, social, search, CTV, linear TV, radio, podcast, DOOH, OOH, print, cinema, gaming, retail media, influencer, affiliate, product placement, AI media
Assessment
Addie evaluates your understanding across four dimensions:| Dimension | Weight | What Addie looks for |
|---|---|---|
| Conceptual understanding | 25% | Can you articulate the paradigm shift from programmatic to agentic? |
| Practical knowledge | 35% | Can you query an agent and interpret the response? |
| Channel breadth | 20% | Do you understand AdCP covers 20 channels, not just digital? |
| Protocol fluency | 20% | Do you use AdCP terminology correctly? |
Start this module
Start A1 with Addie
Open Addie and say “I’d like to start certification module A1.” Addie will take it from there.