Frontier · Deploy
Your customer's next shop starts in a chat window.
UCP, ACP, AP2 and MCP - catalogue readiness for the surfaces where discovery now happens.
Agentic commerce readiness is the work of making a brand's catalogue discoverable and transactable by AI shopping agents. It covers product feed restructuring for agent legibility, protocol implementation across UCP, ACP and AP2, an MCP endpoint, and measurement of agent-originated traffic.
Brand presence in AI assistant answers is becoming the new SEO (McKinsey, State of Fashion 2026). The budget for this already exists - it is currently allocated to search.
Not advice. Working parts.
- 01Catalogue and feed audit for agent legibility
- 02UCP capability implementation
- 03ACP discovery enablement
- 04AP2 mandate handling where payments apply
- 05MCP catalogue endpoint
- 06Answer-engine visibility audit
- 07Agent traffic measurement from day one
Artifacts, not a deck.
Agent-legible product feed
Protocol implementation across the surfaces that matter to you
MCP catalogue endpoint
Agent-originated traffic measurement in place
Nothing here is settled.
Read as of 2026-08-20. One of these was deprecated in March 2026, which is the argument for building against the layer rather than against the protocol.
| Protocol | Status | Confidence |
|---|---|---|
| UCP — Universal Commerce Protocol | Spec public since January 2026 | In force |
| ACP — Agentic Commerce Protocol | Live | In force |
| AP2 — Agent Payments Protocol | Live | In force |
| MCP and A2A | Live, and shared across camps | In force |
The doorway is the product now
Consulting installs it. The platform runs it.
No counterpart yet, and this is the honest case the others are measured against. Agentic commerce readiness is catalogue and protocol work that lands in your own storefront and feeds - there is nothing for us to host.
Deploy. Thirty days onto McLeuker AI, then retained.
Your operation loaded onto agents that already know the fashion domain.
Diagnose
Where agents change the economics, and where they do not.
Design
Which agents, which tools, which data, which guardrails.
Deploy
Shipped into the operation with your context loaded.
Operate
Retained partnership, monthly sessions, continuous updates.
What buyers ask first.
Is this not too early to invest in?
The measurement is not. Knowing how much of your traffic already originates from an assistant costs little and decides everything after it. Protocol work is then sized to what that number says, rather than to enthusiasm.
Which protocol should we implement?
It depends on where your customers actually are, and the answer changes. One in-chat checkout product was deprecated in March 2026 while its protocol survived - which is precisely why this is scoped as judgement rather than a checklist.
What makes a catalogue legible to an agent?
Structure and completeness that a human shopper never needed: unambiguous attributes, resolvable variants, real availability, and text that answers a question rather than performing for a search engine.
How do we measure agent traffic?
Instrumented from day one of the engagement, before any protocol work. Implementing first and measuring later leaves you unable to say whether any of it worked.
Rarely bought alone.
Deployment
Research & Intelligence
Trend, competitor, market and consumer research as a loop your team runs - not a report someone delivers.
Deployment
Merchandising & Retail Ops
Assortment gaps, price architecture, competitive audits and sell-through - from live retail, not last quarter's export.
Frontier
AI Governance & Compliance
EU AI Act, content provenance and DPP-ready product data - as an architecture problem, not a policy document.
Start with the diagnostic.
Four weeks, fixed fee, and a ranked map of what is worth automating in your operation - including what is not.