We haven’t talked too much about AI and e-commerce here on this blog, but as much as any other area in our digital life, AI agents will change how we shop online.
Elizabeth Pizzuti, writing on the Automattic Design blog, explains the two definitions for how “agent” can be used in the e-commerce context.
The word “agent” is overloaded in 2026 commerce.
Two unrelated things share it:
- Agentic commerce: AI shoppers buying from stores.
- Agentic merchant operations: AI workers operating for the merchant.
The distinction matters because the two sides ask designers to make different things legible. On the machine-buyer side, Pizzuti’s first principle is basically agent readiness applied to commerce:
AI agents don’t browse websites like humans, they read structured data from the backend. Considerations here include providing an “AI readiness” score or dashboard for a clear, visual indicator of product catalog health, and a preview of how the AI agent sees that data. This demystifies the structure and allows the merchant to see exactly what an algorithm is evaluating. Additionally, make sure that context is part of the catalog—blog posts, buying guides, FAQs, and reviews all determine sentiment and trust and should be linked to the product schema.
For merchant-side coworkers, the problem flips. The interface is there to help a human judge whether the system did the right work. Pizzuti on the interface merchants use to judge and approve the agent’s work:
Designing for trust means exposing the agent’s backend homework. A merchant will never click “Approve” out of blind faith, especially in high-risk areas like pricing or inventory replenishment. Every automated recommendation must include the underlying context and trigger. Instead of “Drop price of item X by 10%”, the UI should show the reasoning chain:
- Observation: Competitor price drop detected.
- Impact: Your listing’s conversion rate fell by 14% over the last 48 hours.
- Reasoning: Lowering the price by 10% restores your competitiveness while preserving an 18% net margin.
That’s the right design shape for AI coworkers: controllable over perfect, with proof of work, a visible undo path, and enough context for the merchant to approve the change without pretending the system is magic.
