Markdown source

Self-Improving software factories: The new open source model"

Conference Context

Session Description

Alt titles: Agent orchestration with message passing / Agent orchestration for every model / Warp’s approach to agent orchestration With models getting more capable, we’ve quickly scaled from single agent problems to multi-agent problems – How can agents delegate tasks to accomplish ever-larger goals? You may have heard of “agent swarms” or “agent teams” in this arena, but they come with drawbacks: model lock-in, complex UX, or both. We want to share how we’ve tackled orchestration with our model-agnostic platform, Oz. Our approach has some unique goals: - Support any model, and any harness (claude, codex, etc) - Delegate across local instances and across isolated cloud sandboxes - Provide a UX that requires zero tmux or TUI knowledge to use We’ll explore how we implemented message passing across harnesses, how we handle agent sandboxing with Docker containerization + serverless deploys, and how we designed these primitives to make a system that works with any agent. You’ll walk away with a clear outline of how to build agent orchestration well. Plus, we invite you to try our Oz orchestration platform and tell us what you think. Talk format: Primarily a tech demo and code walkthrough. We’ll show multiple examples of tasks that are best served by delegation, and show both local and cloud-based runs. We’ll also walk through the design of our message passing implementation at a high level to show how it works.

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.

Summary

Zach Lloyd’s Main Stage session sits squarely in the Software Factories track: it is about moving from single coding agents toward orchestrated systems where multiple agents can delegate work, pass messages, and run in isolated local or cloud environments. The talk frames Warp’s Oz platform as a model-agnostic approach to agent orchestration, designed to work across harnesses such as claude and codex rather than locking teams into one model or one terminal workflow. Because Lloyd leads Warp, an Agentic Development Environment company rooted in the terminal, the session connects practical developer UX with deeper infrastructure concerns: sandboxing, Docker containerization, serverless execution, and coordination primitives for larger AI-native software workflows.

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

Self-Improving software factories: The new open source model" ## Conference Context - Date/time: 2026-06-29 · 1:55pm-2:15pm - Track/room: Software Factories · Main Stage - Speaker(s): Zach Lloyd - Session type/status: session · confirmed - Track: Software Factories - Room: Main Stage - Session type: session - Status: confirmed ## Session Description Alt titles: Agent orchestration with message passing / Agent orchestration for every model / Warp’s approach to agent orchestration With models getting more capable, we’ve quickly scaled from single agent problems to multi-agent problems – How can agents delegate tasks to accomplish ever-larger goals? You may have heard of “agent swarms” or “agent teams” in this arena, but they come with drawbacks: model lock-in, complex UX, or both. We want to share how we’ve tackled orchestration with our model-agnostic platform, Oz. Our approach has some unique goals: - Support any model, and any harness (claude, codex, etc) - Delegate across local instances and across isolated cloud sandboxes - Provide a UX that requires zero tmux or TUI knowledge to use We’ll explore how we implemented message passing across harnesses, how we handle agent sandboxing with Docker containerization + serverless deploys, and how we designed these primitives to make a system that works with any agent.

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.