What is agentic commerce?
Agentic commerce is what happens when an AI assistant doesn't just suggest a product — it actually buys it.
A shopper types "find me a hypoallergenic baby formula under $35, nickel-free, available for same-day delivery" into ChatGPT or Perplexity. The AI doesn't return a list of links. It reads product feeds, checks inventory, compares compliance data, and places the order. The human approves or the agent acts autonomously, depending on how much trust they've delegated.
That's the shift. Buying decisions are increasingly made by software, not by humans browsing pages.
The cost of being invisible to AI agents
When a shopper asks an AI assistant for a product recommendation, the agent pulls from machine-readable sources — structured data feeds, verified catalogs, protocol-compliant product listings. If your product data is incomplete, the agent doesn't downgrade you. It skips you entirely and moves to a competitor whose feed it can read.
Traditional SEO got you found by humans. Agentic commerce requires software to find you, read your data, and trust what it reads. That's a different bar.
A few things that get merchants skipped:
- Missing or invalid GTINs (Global Trade Item Numbers, the barcodes that uniquely identify products)
- Stale or inaccurate inventory signals (an agent won't recommend something it can't confirm is in stock)
- Thin product descriptions without structured attributes (material, certifications, age-grading, regulatory compliance)
- No machine-readable feed in a format the agent's protocol can parse
This isn't a future problem. ChatGPT has native shopping integrations. Perplexity runs a merchant program. Google's AI Overviews surface product data differently from organic search. These channels are live, and the merchants who show up are the ones with clean, structured, verifiable data.
A well-optimized product page ranks for humans. An AI shopping agent bypasses your page and reads your data feed directly. If the feed is thin, the page doesn't matter.
How an AI agent actually buys a product
The process isn't magic. Agents follow a consistent pattern: discover, evaluate, then transact. Understanding each step tells you exactly where poor data costs you a sale.
Discovery: the agent finds your product
The agent starts with a purchase intent — from the user, or from an automated workflow. It queries product catalogs via structured feeds, protocol APIs, or search indexes. Products that appear here have GTINs, categories, and feed URLs registered with the channel the agent is using (Google Merchant Center, a UCP-enabled store, an MCP server, or an ACP-compatible endpoint).
If your product isn't in a feed the agent queries, it doesn't exist for that transaction.
Evaluation: the agent decides whether to trust the product
This is where most merchants fail. The agent checks whether the product data is credible and complete: Is the inventory count real-time or stale? Do the safety claims have backing data (certification numbers, lab reports, regulatory flags)? Is the material composition structured, or buried in a paragraph? Are there compliance signals for the buyer's jurisdiction?
Regulated products — supplements, baby items, medical devices, jewelry with metal content — face extra scrutiny. An agent helping a parent find a "nickel-free baby teether" needs a nickel content field, not a sentence that says "safe for babies." Unstructured claims don't parse.
Price and availability check
Before committing, the agent checks current price (not the listed price from a stale feed) and real-time availability. Merchants with live inventory feeds and accurate pricing win here. Merchants with daily batch-update feeds sometimes lose orders because the agent sees "in stock" on a product that sold out three hours ago.
Transaction: the agent completes the purchase
If the evaluation passes, the agent places the order through whatever protocol it's using — directly via ACP, through a UCP-enabled store (the Google–Shopify standard), or via a checkout API. The merchant's job at this step is to have a machine-accessible checkout path. Some protocols handle payment directly; others hand off to a human to confirm.
The protocol landscape: ACP, UCP, MCP, and beyond
Merchants currently face four main channels where AI agents transact. The architecture and data requirements differ across all of them.
| Protocol / Channel | What it is | Who it's for | Key data requirement |
|---|---|---|---|
| ACP (OpenAI Agentic Commerce Protocol) | OpenAI's standard for agents to discover and buy products | Merchants who want ChatGPT and GPT-powered agents to transact with them | Structured product feed with GTINs, pricing, availability, and compliance attributes; ACP-compatible checkout endpoint |
| UCP (Universal Commerce Protocol) | Open agentic-commerce standard from Google and Shopify, covering the full shopping journey | Merchants selling via Shopify or Google's AI surfaces | Structured product data + metafields/attributes; real-time inventory; a UCP-compatible storefront |
| MCP (Model Context Protocol) | Open protocol from Anthropic for giving AI models access to tools and data | Developers and advanced merchants who want any AI model to query their catalog as a tool | An MCP server exposing product search, product detail, and (optionally) cart/checkout tools |
| Google Merchant Center | Google's product feed system, now powering AI Overviews and Shopping Graph | Any merchant who wants Google's AI to surface their products | Valid product feed with GTINs, condition, price, availability; compliance with Google's feed spec; no policy violations |
| Perplexity merchant program | Perplexity's native shopping integration for AI-generated product answers | Merchants who want Perplexity's answers to recommend and link to their products | Application to the program; clean product data; structured content that Perplexity can cite |
Start with Google Merchant Center — it's the most established channel and feeds the widest range of AI surfaces. Then add ACP or UCP based on where your buyers actually use AI assistants. MCP is worth doing if your catalog is complex or you sell through channels that agents query directly.
What "regulated verticals" means for agents
AI agents evaluating products in regulated categories do more than check a price. For an agent processing a request like "find an FDA-registered zinc supplement with no proprietary blends, third-party tested, and in the $20-$40 range," your product data needs to answer each of those requirements with a structured field — not prose.
Arbling covers eight regulated verticals, and each one has its own trust requirements:
- Jewelry — metal composition, stone sourcing, hallmarks, conflict-free attestations, nickel content for EU compliance
- Supplements — FDA registration numbers, third-party testing certificates, ingredient lists in structured format, no unauthorized health claims
- Baby products — CPSC compliance, age-grading, material safety data, choking hazard flags
- Beauty — ingredient INCI names, EU/US banned substance flags, cruelty-free certifications
- Electronics — FCC certification, RoHS compliance, energy consumption data
- Medical devices — FDA 510(k) clearance numbers, intended use, contraindications in structured fields
- Luxury watches — movement type, case material, water resistance rating, authentication documentation
- Furniture — GREENGUARD certification, VOC emissions data, load ratings, country of manufacture
If your product is in one of these categories and your feed is missing these fields, an agent evaluating a safety-conscious buyer's request will pass. Not because your product is unsafe — because the agent can't confirm it isn't.
Is your catalog agent-ready? A quick self-check
Run through these before worrying about which protocol to integrate:
- Every product has a valid GTIN (UPC, EAN, or ISBN where applicable)
- Inventory counts update at least hourly (real-time is better)
- Price and sale price are always accurate in your feed
- Product type and category follow a recognized taxonomy (Google's taxonomy is a safe default)
- Regulated products have structured compliance fields, not paragraph-form claims
- Material composition is a structured attribute, not buried in a description
- Your feed validates against the spec for at least one channel (Google Merchant Center's diagnostic tool is free)
- You have no active policy violations on Google Merchant Center (these block AI surfaces too)
If you're hitting three or more gaps, your catalog is likely invisible or deprioritized across AI shopping channels already.
Frequently asked questions
It's shopping where an AI agent does the buying instead of a human browsing a site. The user states what they want, the agent queries product catalogs, checks prices and availability, evaluates compliance and trust signals, and completes the purchase — sometimes without the user clicking anything. The key shift: discoverability now depends on machine-readable data, not on search rankings or paid ads.
They query structured data sources: product feeds registered with Google Merchant Center, ACP-compatible endpoints, UCP-enabled stores (the Google–Shopify standard), or MCP servers. Agents don't crawl your website the way Googlebot does. They read feeds. If your product isn't in a feed the agent has access to, it doesn't find you.
ACP (Agentic Commerce Protocol) is OpenAI's standard for agents to discover and buy products. It defines how a shopping agent authenticates, queries a merchant's catalog, and completes a transaction. MCP (Model Context Protocol) is Anthropic's open protocol for connecting AI models to external data and tools — it's broader than commerce and can expose anything from a product catalog to a support knowledge base. A merchant could use MCP to make their catalog queryable by any AI model; they'd use ACP specifically to connect to OpenAI's shopping agents.
Yes, more than it used to. Google's AI Overviews and Shopping Graph pull directly from Merchant Center feeds. Products with clean, validated feeds surface in AI-generated answers; products with feed errors or policy violations don't. If you're already on Merchant Center, fixing feed quality is the fastest route to AI visibility on Google.
Agents evaluating regulated products check for compliance signals — FDA registration, CPSC flags, certifications, material declarations — as structured fields. A prose description that says "safe and certified" doesn't satisfy this. You need machine-readable fields with actual registration numbers, certification identifiers, or compliance flags. Missing these fields means an agent serving a safety-conscious buyer will pass your product over.
No. Start with the channel where your buyers are most likely to use AI assistants, then expand. Google Merchant Center reaches the most AI surfaces. If you're on Shopify, UCP is relatively low-lift. ACP matters most if ChatGPT is a meaningful discovery channel for your category. MCP is worth pursuing if you have a complex catalog or want to be queryable by a wide range of AI models.
Arbling enriches and verifies product catalog data across the regulated verticals and formats it to meet the requirements of ACP, UCP, MCP, and Google Merchant Center. The gap most merchants face isn't willingness to comply — it's that their existing product data is structured for human-facing pages, not for AI agents. Arbling normalizes that data, fills in missing structured attributes, and verifies compliance signals so agents treat the catalog as trusted and complete.
No. The data requirements are the same regardless of catalog size. A boutique with 200 SKUs needs clean GTINs and accurate inventory as much as a retailer with 200,000. In some ways smaller catalogs are easier to fix — fewer items to audit, less technical debt to clear.
Sources
- OpenAI: Buy it in ChatGPT — Instant Checkout and the Agentic Commerce Protocol — OpenAI's ACP announcement
- Google: an open standard for agentic commerce (UCP) — Google and Shopify's Universal Commerce Protocol
- Model Context Protocol specification — Anthropic's open spec for MCP, including how tools and data resources are exposed to AI models
- Google Merchant Center product data specification — Official Google feed spec, including required and recommended fields
- Google AI Overviews and Shopping — How Google's AI surfaces use Merchant Center data
- Perplexity for Merchants — Perplexity's merchant shopping program overview
Ready to see where your catalog stands? See how Arbling helps you get found by AI.