# Agentic Sites: Building Hyper Personalized Websites — Carlos Sanchez, Adobe

Source: [AI Engineer](https://www.youtube.com/watch?v=jebp4V0vh30)  
Feed7 permalink: https://feed7.dev/p/agentic-sites-building-hyper-personalized-websites-carlos-sanchez-adobe-1nmnk5n  
Published: 2026-08-29T17:00:17.000Z  
Trust: Source Linked (source_linked)

## Why Included

Adobe’s prototype assembles intent-specific page blocks from existing site content in roughly a second, making model latency and per-site evaluation part of frontend architecture.

## Source Summary

Adobe’s prototype personalizes selected page blocks while grounding generated copy and recommendations in the existing site corpus. Across **15 prompts**, Cerebras with Gemma 4 averaged **1.1 seconds**, versus 4.6 seconds for the next shown result.

## Practical Implication

For agent-generated interfaces, evaluate model and provider combinations against each site’s own content and latency target. Keep brand-controlled structure fixed, generate only bounded blocks, and precompute recommendations when live generation is unnecessary.

## Agent-Ready Context

Adobe’s prototype personalizes selected page blocks while grounding generated copy and recommendations in the existing site corpus. Across **15 prompts**, Cerebras with Gemma 4 averaged **1.1 seconds**, versus 4.6 seconds for the next shown result.

For agent-generated interfaces, evaluate model and provider combinations against each site’s own content and latency target. Keep brand-controlled structure fixed, generate only bounded blocks, and precompute recommendations when live generation is unnecessary.

The demo records browsing and query signals, creating privacy and cost questions that the talk does not resolve. Its speed results come from one example site and do not establish quality or conversion gains across production properties.

## Connected Context

Feed7 judgment across 669 accumulated Signals:

This narrows agentic-site personalization to a controlled rendering pattern: retain brand-owned structure, ground outputs in the site corpus, and generate only selected blocks. The reported latency makes provider benchmarking relevant but remains site-specific evidence, not a quality or conversion result. Privacy, signal collection, and recurring inference cost remain unresolved prerequisites for production adoption.

No material corpus connection was strong enough to record.

## Context Map

- Layer: tools
- Domains: coding
- Topics: generative-media, model-selection, dev-ux

## Uncertainty

- The demo records browsing and query signals, creating privacy and cost questions that the talk does not resolve. Its speed results come from one example site and do not establish quality or conversion gains across production properties.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.