← back
Develop at Idea Velocity - Jeffrey Lee-Chan, Snapchat
Takeaway
Persistent coordination, isolated coding workers, and strong feedback loops can reduce the friction between an idea and a working change.
Summary
- Jeffrey Lee-Chan uses OpenClaw as a persistent coordination layer that interprets brief messages using prior goals, specifications, and conversation history.
- Workers execute coding tasks through an agent orchestrator and Claude Code, with Git worktrees and tmux supporting parallel development and supervision.
- Separating orchestration context from implementation context helps the manager retain intent while coding workers focus on repository details.
- The workshop emphasizes CI, automated and browser-based checks, and notification-driven supervision, while acknowledging that the setup still needs debugging and human intervention.
openclawcoding-agentsagent-orchestration
Original description
The biggest gap in production AI agent systems is not the model—it's the harness. After 1,000 hours of orchestrating autonomous fleets under human direction, the pattern is unmistakable: agents that finish complex tasks on the first run routinely fail on subsequent iterations because the surrounding loop lacks persistent memory and contextual guardrails. In this talk, I dissects the key multi-agent primitives required to turn raw models into deterministic teammates. Moving beyond simple API wrappers, we explore how separating your stack into distinct "Agent Orchestrator Managers" and specialized workers prevents low-level implementation bias. Using concrete examples from production systems, we will walk through real-time terminal routing via CMUX, analyze the token-burn tradeoffs between leading models, and look under the hood of high-context consumer applications like WorldAI and Consensus ML. You will walk away with a practical architectural checklist you can drop directly into your own agent infrastructure on Monday morning. Once you're setup you can truly develop at idea velocity ie. natural language to code to automated iteration to evidence produced to human review where human interaction in the middle is pushed to the beginning or end allowing improved parallelization. Speakers: Jeffrey Lee-Chan (Snapchat): Most teams use AI tools wrong — humans still on the critical path. I build parallel multi-agent harnesses so one engineer directs 10–20 coding agents instead of becoming the rate limiter. X/Twitter: https://x.com/jleechan2015 LinkedIn: / jeffrey-lee-chan GitHub: https://github.com/jleechanorg