Markdown source

The Agentic Commerce Stack

Conference Context

Session Description

Agents are already handling product discovery, cart building, and checkout — no human clicking required. But what's the protocol stack actually making this work? This talk maps the real infrastructure: MCP for tool access, A2A for agent coordination, the ACP spec (backed by OpenAI) and the UCP spec (backed by Google) — two competing approaches to standardizing the full agentic commerce lifecycle — and AP2 for agentic payments. We'll cover what each does, how they compose, and where they're still forming. Then we'll see it live — a working demo with a protocol inspector showing every tool call, task transition, and checkout event in real time. You'll leave with a clear mental model of the agentic commerce landscape and a reference implementation you can use.

Media Evidence

No related AI Engineer channel video found yet.

Evidence Graph

This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

Media Signals

No linked video, transcript, or slide source has been attached yet.

Agent Reading Notes

Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

Summary

Ahnaf Prio's Agentic Commerce track session treats agentic retail as an infrastructure and standards problem: how an autonomous shopping agent moves through product discovery, cart construction, checkout, and payment while leaving an inspectable trail of tool calls and state transitions. The official description identifies the protocol layers directly: MCP for tool access, A2A for agent coordination, ACP and UCP as competing commerce-lifecycle specifications backed by OpenAI and Google respectively, and AP2 for agentic payments. That makes the talk less about a single shopping assistant UX and more about the protocol boundaries needed for agents to operate across catalogs, carts, checkout systems, and payment flows.

The speaker context sharpens the practical angle. Prio is a Senior Engineering Manager at Best Buy building next-generation, AI-driven retail experiences at scale, after earlier startup CTO and co-founder roles. In the July 1 multi-track program, this positions the session as part of the World's Fair's applied commerce layer: a retailer-facing map of how emerging agent standards might compose inside real buying workflows. The promised live demo and protocol inspector are important evidence signals because they imply an implementation-oriented walkthrough, showing each tool invocation, task transition, and checkout event rather than only describing the standards at a conceptual level. Until an official matched recording transcript is available, the schedule description and speaker profile remain the strongest grounded sources for the page.

Transcript Status

No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

People

Notes

Synthesis

Synthesized Breakdown

The Agentic Commerce Stack ## Conference Context - Date/time: 2026-07-01 · 2:25pm-2:45pm - Track/room: Agentic Commerce · Track 2 - Speaker(s): Ahnaf Prio - Session type/status: sponsor · confirmed - Track: Agentic Commerce - Room: Track 2 - Session type: sponsor - Status: confirmed ## Session Description Agents are already handling product discovery, cart building, and checkout — no human clicking required. But what's the protocol stack actually making this work? This talk maps the real infrastructure: MCP for tool access, A2A for agent coordination, the ACP spec (backed by OpenAI) and the UCP spec (backed by Google) — two competing approaches to standardizing the full agentic commerce lifecycle — and AP2 for agentic payments. We'll cover what each does, how they compose, and where they're still forming.

Speaker And Company Context

Topics Covered

Derived Links And Source Material

Novel Concepts / Clever Methods

Evidence Boundary

This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.