Agentic Sites: Building Hyper Personalized Websites — Carlos Sanchez, Adobe
Source
youtube.com
Author
AI Engineer
Date
Context
Adobe's proposed personalized website changes selected page components in response to a visitor's request. Its conference presentation describes retrieving material from the site's own content and using brand rules to guide the result. A request for a camping coffee machine, for example, determines which products and supporting copy appear.
The design constrains the generation task to choosing and arranging particular components, such as product displays and calls to action. Model evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition → then happens for each site, considering both accuracy and response time. That connects personalization to two concrete requirements: staying groundingTying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.Full definition → in the site's material and producing the page quickly enough to use.
Terms in this piece · Glossary
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.
videoDeploying AI Inside a Bank Is Not an Engineering Problem — Paden Gayle, Applied AI Engineers
videoThe Agent Works. Does Anyone Trust It? — Michele Grant, Leading at Scale
videoWhat Technical Due Diligence Finds When the Deck Says “70% Automated” — Soukaïna Abelhad
videoTokens Are the Cheap Part — Steve Jamison, Jellyfish
