Designing AI-Intensive Applications

Explore the evolution of AI engineering through this conference talk that examines how applications are transitioning from simple 1:1 user-input to LLM-call ratios (like ChatGPT) to complex 1:100 ratios (like Deep Research and Codex) and even autonomous 0:n ambient agents. Discover how AI engineering practices must adapt as applications become increasingly AI-intensive, moving beyond basic chatbot implementations to sophisticated workflow systems. Learn about the search for a "standard model" in AI engineering and examine candidate frameworks that could define the field's future direction. Understand the SPADE model for designing AI-intensive applications and gain insights into the fundamental shifts occurring in how we architect and build AI-powered systems. Recorded at the AI Engineer World's Fair in San Francisco, this presentation addresses the critical question of how engineering practices evolve when AI becomes the primary driver of application functionality rather than just an auxiliary feature.

Syllabus

Whether you call it a workflow or an agent, AI engineered applications are seeing user-input:LLM-call ratios go from 1:1 ChatGPT to 1:100 Deep Research, Codex and even 0:n Ambient/Proactive agents. How does AI Engineering change as you build increasingly AI intensive applications?
00:00 Conference Welcome and Overview
00:42 Conference Logistics and Growth
01:47 Audience Preferences and Survey
02:22 Innovations in AI Engineering MCP and Chatbots
02:58 Evolution of AI Engineering Past Talks
03:50 Simplicity in AI Engineering
04:17 AI Engineering as a Developing Field
05:23 Seeking the "Standard Model" in AI Engineering
06:02 Candidate Standard Models in AI Engineering
09:26 Human Input vs. AI Output AI News Example
11:05 SPADE Model for AI-Intensive Applications
12:29 Call to Action for Conference Attendees