Get Out of the Model's Way
Conference Context
- Date/time: 2026-06-29 · 1:30pm-1:50pm
- Track/room: Software Factories · Main Stage
- Speaker(s): Kevin Hou
- Session type/status: session · confirmed
- Track: Software Factories
- Room: Main Stage
- Session type: session
- Status: confirmed
Session Description
From autocomplete to chat to agents to agent orchestration...how do you build a product that scales with intelligence? What core primitives enable agents to operate at the technical (and non-technical) frontier? How can you best squeeze every ounce of capability out of your agentic dev tools? I'll answer all these questions and break down how Google Antigravity creates dynamic agent teams to solve complex tasks like building an OS-Kernal and automating research workflows.
Media Evidence
How Windsurf writes 90% of your code with an Agentic IDE - Kevin Hou, Windsurf (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).
- Source video:
youtube-bVNNvWq6dKo - Slide deck: Dense Slides: How Windsurf writes 90% of your code with an Agentic IDE - Kevin Hou, Windsurf — 4 visible slide image(s); 4 HTML recreation(s).
- Additional slide evidence: Slides: How Windsurf writes 90% of your code with an Agentic IDE - Kevin Hou, Windsurf, Reconstructed Slides: How Windsurf writes 90% of your code with an Agentic IDE - Kevin Hou, Windsurf
- Slide-derived themes for
youtube-bVNNvWq6dKo: agentic, diff, review, first, company, replace, chat, deep.
Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.
Media Signals
youtube-bVNNvWq6dKo— 4 slide-derived text signals- Slide-derived themes for
youtube-bVNNvWq6dKo: agentic, diff, review, first, company, replace, chat, deep. - Evidence links for
youtube-bVNNvWq6dKo: youtube bVNNvWq6dKo, youtube bVNNvWq6dKo slides, youtube bVNNvWq6dKo dense slides, youtube bVNNvWq6dKo reconstructed slides
Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.
Transcript Status
Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.
People
Supporting Slides
- youtube bVNNvWq6dKo slides — extracted from the related public AI Engineer video.
Slide Evidence
- Slide-only cropped deck: youtube bVNNvWq6dKo dense slides (4 viable slide images).
- Related slide/OCR pages:
- youtube bVNNvWq6dKo dense slides
- youtube bVNNvWq6dKo reconstructed slides
- youtube bVNNvWq6dKo slides
- Slide-derived terms:
const,ai.engineer,images,agentengineering,https,cascade,next,documentation,code,dynamic,main,usestate,value,prev,check,crawler,create,first
Synthesis
Synthesized Breakdown
Get Out of the Model's Way ## Conference Context - Date/time: 2026-06-29 · 1:30pm-1:50pm - Track/room: Software Factories · Main Stage - Speaker(s): Kevin Hou - Session type/status: session · confirmed - Track: Software Factories - Room: Main Stage - Session type: session - Status: confirmed ## Session Description From autocomplete to chat to agents to agent orchestration...how do you build a product that scales with intelligence? What core primitives enable agents to operate at the technical (and non-technical) frontier? How can you best squeeze every ounce of capability out of your agentic dev tools? I'll answer all these questions and break down how Google Antigravity creates dynamic agent teams to solve complex tasks like building an OS-Kernal and automating research workflows.
Speaker And Company Context
- Kevin Hou — Engineering Lead @ Antigravity at Google DeepMind.
Topics Covered
Derived Links And Source Material
- youtube bVNNvWq6dKo — related YouTube source page.
- youtube bVNNvWq6dKo slides — slide evidence.
- youtube bVNNvWq6dKo reconstructed slides — slide evidence.
- youtube bVNNvWq6dKo dense slides — slide evidence.
Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.
Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.