Short: ChatGPT's product feed requires eight fields: item ID, title, description, URL, brand, image, price and availability. Start there, then add the specs.
Read the full write-up: What is agentic commerce?
More shorts from this video
Forrester: 1 in 5 B2B sellers would negotiate with buyers' AI agents in 2026 (0:19)
Why AI agent checkout is not ready for B2B buying yet (0:18)
ACP, UCP, AP2 or MCP: which agentic protocol should you pick? (0:13)
What is agentic commerce? The short definition (0:24)
Custom catalogs and tiered pricing in BigCommerce B2B Edition (0:46)
Do you need BigCommerce B2B Edition, or is standard enough? (0:46)
Getting ERP prices into BigCommerce B2B Edition (0:43)
BigCommerce B2B Edition buyer roles in 30 seconds (0:30)
4 things BigCommerce B2B Edition doesn't do (0:48)
What a BigCommerce ERP integration actually syncs (0:45)
Duplicate orders, stock and ERP outages in BigCommerce (0:42)
Every ERP has a catch: BigCommerce integration quirks (0:39)
How to pick a BigCommerce ERP connector: test three hard cases (0:40)
Why BigCommerce ERP connectors break on pricing (0:44)
Your business still runs on dBASE files. Now what? (0:30)
FoxPro indexes in 11 code pages, byte for byte (0:29)
50 hard power cuts while writing dBASE files (0:33)
Kill a FoxPro write mid-change: who leaves a silent bad index? (0:41)
49x faster DBF lookups than the VFP OLE DB driver (0:30)
Transcript
None of this requires picking a protocol. It requires data an agent can trust, and rules an agent can follow. Start with product data. ChatGPT's product feed spec requires an item ID, title, description, URL, brand, image, price and availability. Google added Merchant Center attributes such as product FAQs and compatible accessories for conversational search. Missing specifications leave you out of the comparison.
Narration is an AI voice (Azure). The facts come from the linked write-up.