Agentic Ad Lab: independent analysis of AdCP and AAMP

Two organisations are writing the rules for how software buys advertising, and neither one acknowledges the other. If you hold a budget, that is a procurement question rather than a standards question, and it has an answer this quarter: AdCP is the only one of the two publishing a released contract you can write code against, so a pilot there is fundable now. AAMP’s one finished specification, ARTF, governs bid mutation inside a live auction. Everything else under the label is code without a contract, and I would keep it on a watch list instead of a roadmap.

If you are scoping Q1, that is one integration to fund and one to leave off the roadmap, and the side-by-side prices both. What moves AAMP off the watch list is a versioned AAMP release with a schema behind it. Until a tag exists at the AAMP level, there is nothing to conform to.

Calling the two equally documented would be a lie. IAB Tech Lab announced AAMP 2.3 on 30 July 2026 and the string appears in no file in any of the eight AAMP repositories, which makes 2.3 a programme milestone, not an artefact you can pin; the version matrix shows what does exist instead. agentic-audiences ships specs/v1.0/schema/agent_interface.schema.json at zero bytes, the file whose name promises to define the interface between buyer and seller agents. It defines nothing.

Who writes Agentic Ad Lab

Constantine Mirin. I am CEO of Postindustria and I build agentic systems that run in production. That is the qualification and the conflict, both. Public trail: LinkedIn, GitHub, Crunchbase. The name appears as both Constantine and Konstantin depending on which profile you land on. Same person, and the transliterated spelling is what the LinkedIn and Crunchbase slugs use.

Staff of one. When a page here says “I”, it means me, and it names the thing that would prove the judgement wrong.

Postindustria pays for this

Postindustria does protocol integration and agent-readiness work, and this site is the showroom for it. The site sells nothing and takes no money from anyone it writes about, including for a place in a comparison. The paid work is described at /services/.

The comparison is where a commercial interest could most plausibly bend the writing, so it is the page that carries the file paths and the linked sources. Adgentek, which publishes its own AdCP-versus-AAMP piece, opens by disclosing that it is a founding member of the Ad Context Protocol, which is the right way round to do it.

The comparison is the page to read first

I run six sites on this subject, and this is the one that takes a side.

Fund one integration and watch the other, and AdCP vs AAMP is where that call gets made, with the licence and governance risk priced in. If you want the evidence that anyone has done this for money before you sign off on it, who is running agentic buys is the dated ledger of named deployments.

A publisher needs to know what to put on their own origin before a buying agent arrives. That turns out to be one static file, and agent discovery files is the whole of it, including the part of the schema that survives an agent domain being compromised. An implementer needs field names instead: every registered AdCP operation has a page at AdCP Explorer, AAMP Explorer does the same across the eight AAMP repositories, holes included, the ad tech glossary takes one term per page, and Brief Gateway turns a campaign brief into a validated get_products request. What Is Agentic Buying answers that one question without assuming you care how it is specified.

The builders already exist, so this documents their output

Both sides already run a standards body, a registry and a certification programme, and nobody needs a third of each. AgenticAdvertising.org publishes a brand.json builder and an adagents.json builder, both linked from AdCP’s own intro page, and they are good. Documenting the fields they emit is more useful than rebuilding them.

The subject is those two advertising stacks and the transports underneath them. MCP and A2A are in scope, because AdCP defines its planning-time operations over both and AAMP’s agentic-direct puts OpenDirect 2.1 over MCP. The commerce protocols are not. ACP and UCP standardise checkout, payments and fulfilment inside an assistant, and AdCP’s own glossary files them as the layer next to advertising rather than inside it. Nothing here covers them.

AdCP is maintained by AgenticAdvertising.org, which its FAQ describes as “an independent specification body — not a subsidiary or working group of IAB Tech Lab”, and AAMP is published by IAB Tech Lab.

This site is affiliated with neither and endorsed by neither. “AdCP” belongs to AgenticAdvertising.org, “AAMP” and “IAB” to IAB Tech Lab.

Both corpora move; every claim here is pinned to a commit. If something is wrong, point at the file that contradicts it and mail hello@agenticadlab.com. The page gets edited.