Markdown source

Building agents is trivial now, context is the next frontier

Conference Context

Session Description

Standing up an agent used to be the hard part. A new class of cloud-agent frameworks has made it almost trivial: in an afternoon you can ship a fleet that reasons, plans, and calls any API you point it at. So why do so many of them fail the moment they touch real work? Because a capable agent still doesn't know the organization it operates in: its decisions, history, incidents, and how a particular team actually operates. That knowledge isn't in the model or the API, and no amount of construction adds it. This talk exposes the missing component, then shows how to build it live on a real workflow — the same move that helps a coding agent helps a support or operations one. Construction is solved. The missing context, tacit and tribal knowledge is the bottleneck that's left, and it sits upstream of everything verification attempts to catch after the fact.

Media Evidence

No related AI Engineer channel video found yet.

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

No linked video, transcript, or slide source has been attached yet.

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

No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

People

Notes

Synthesis

Synthesized Breakdown

Building agents is trivial now, context is the next frontier ## Conference Context - Date/time: 2026-06-29 · 2:25pm-2:45pm - Track/room: track TBD · Expo Stage 3 SW - Speaker(s): Jeff Ng - Session type/status: session · confirmed - Track: track TBD - Room: Expo Stage 3 SW - Session type: session - Status: confirmed ## Session Description Standing up an agent used to be the hard part. A new class of cloud-agent frameworks has made it almost trivial: in an afternoon you can ship a fleet that reasons, plans, and calls any API you point it at. So why do so many of them fail the moment they touch real work? Because a capable agent still doesn't know the organization it operates in: its decisions, history, incidents, and how a particular team actually operates.

Speaker And Company Context

Topics Covered

Derived Links And Source Material

Novel Concepts / Clever Methods

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.