Agentic Sites: Building Hyper Personalized Websites — Carlos Sanchez, Adobe
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.
hallucination — When a model states something false with full confidence — inventing facts, citations, or APIs that don't exist.
Why it matters
Constraining generation to a few blocks 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 a site-as-corpus keeps personalization off the hallucinationWhen a model states something false with full confidence — inventing facts, citations, or APIs that don't exist.Full definition → path, and latency becomes a model-selection criterion — Adobe's fastest config averaged 1.1s against 4.6s for the runner-up.
videoGuardians of the State: An Air-Gapped AI Fortress for Consumer Data — Rachna Srivastava, DFPI
videoFrom Tokenmaxxing to Trusted Throughput — Mingsheng Hong, Ironclad
videoAgents Are Where Microservices Were in 2015 — Roberto Milev & Uday Kanagala, Navan
videoTribal Dungeons of Global Shipping: AI Agents at Global Scale — Dmitry Buykin, Maersk
