- WebMCP for ecommerce: what to prototype now and what not to fund
WebMCP can make a storefront callable inside an agent-driven browser, but in 2026 it belongs in a small prototype—not a production roadmap.
- Which AI crawlers matter for your shop (and which are only policy tokens)
Separate answer crawlers, user-fetchers, training bots and policy tokens so your shop blocks intentionally without turning away buyers.
- The AI access audit: get fetched, get read, get understood
Audit AI access in dependency order: fetchability, edge blocks, rendering, product truth, permissions, then optional agent protocols.
- llms.txt: what seven months of server logs say about who actually reads it
Seven months of logs found no verified frontier-lab llms.txt fetches. Keep the file small, current and outside your AI-visibility KPIs.
- Where AI optimization actually pays for an online store in 2026
Prioritize AI-shopping work that improves discovery now: crawler access, product feeds, schema and policies—not speculative protocols.