Perception Agents
Conference Context
- Date/time: 2026-06-30 · 9:45am-10:05am
- Track/room: Autoresearch · Main Stage
- Speaker(s): Antje Barth
- Session type/status: keynote · confirmed
- Track: Autoresearch
- Room: Main Stage
- Session type: keynote
- Status: confirmed
Session Description
Human-agent collaboration is changing, becoming more visual. The agents most teams ship today still wait for us to type a paragraph to explain what we're looking at. They cannot see a screen, navigate a UI that changes, or recover when an application throws an unexpected modal. That is the architectural gap between agents that demo well and agents that work alongside real teams in real software. Perception agents close it. They see and use computers the way people do, reason about what they see, and act with clicks and keystrokes.
Media Evidence
Building Agents at Cloud Scale — Antje Barth, AWS (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).
- Source video:
youtube-WJjInLeaJjo - Slide deck: Dense Slides: Building Agents at Cloud Scale — Antje Barth, AWS — 2 visible slide image(s); 2 HTML recreation(s).
- Additional slide evidence: Slides: Building Agents at Cloud Scale — Antje Barth, AWS, Reconstructed Slides: Building Agents at Cloud Scale — Antje Barth, AWS
- Slide-derived themes for
youtube-WJjInLeaJjo: table, contents, open, protocols, part, communication.
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-WJjInLeaJjo— 3 slide-derived text signals- Slide-derived themes for
youtube-WJjInLeaJjo: table, contents, open, protocols, part, communication. - Evidence links for
youtube-WJjInLeaJjo: youtube WJjInLeaJjo, youtube WJjInLeaJjo slides, youtube WJjInLeaJjo dense slides, youtube WJjInLeaJjo 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 WJjInLeaJjo slides — extracted from the related public AI Engineer video.
Slide Evidence
- Slide-only cropped deck: youtube WJjInLeaJjo dense slides (2 viable slide images).
- Related slide/OCR pages:
- youtube WJjInLeaJjo dense slides
- youtube WJjInLeaJjo reconstructed slides
- youtube WJjInLeaJjo slides
- Slide-derived terms:
world,engineering,server,future,amazon,sfair,fair,tools,strands,open,servers,barth,alexa,orld,services,code,developer,rere
Synthesis
Synthesized Breakdown
Perception Agents ## Conference Context - Date/time: 2026-06-30 · 9:45am-10:05am - Track/room: Autoresearch · Main Stage - Speaker(s): Antje Barth - Session type/status: keynote · confirmed - Track: Autoresearch - Room: Main Stage - Session type: keynote - Status: confirmed ## Session Description Human-agent collaboration is changing, becoming more visual. The agents most teams ship today still wait for us to type a paragraph to explain what we're looking at. They cannot see a screen, navigate a UI that changes, or recover when an application throws an unexpected modal. That is the architectural gap between agents that demo well and agents that work alongside real teams in real software.
Speaker And Company Context
- Antje Barth — Member of Technical Staff at Amazon AGI Lab.
Topics Covered
Derived Links And Source Material
- youtube WJjInLeaJjo — related YouTube source page.
- youtube WJjInLeaJjo slides — slide evidence.
- youtube WJjInLeaJjo reconstructed slides — slide evidence.
- youtube WJjInLeaJjo 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.