Agent Orchestration and Automation with Codex
Several agents in parallel can save real time, or just burn tokens. Participants learn to tell the difference, then take a multi-agent workflow off the laptop and run it automatically.
- Audience
- Advanced developers and tech leads comfortable with a single agent. Hands-on in Codex; the patterns carry over to Cursor.
- Duration
- 3 to 3.5 hours, hands-on throughout
- Group size
- 15 to 20 participants, on their own laptops with the tools they already use
- Hands-on
- On the team's real tasks, or on prepared exercises I bring
- Includes
- A tailoring call with the group lead beforehand and a follow-up session about 30 days later
- Where
- On-site in Israel, on-site abroad (I fly in for a few days and can run several sessions or teams back to back), or remote
What we cover
- When multi-agent helps and when it doesn't: context isolation, parallelism, cost.
- Orchestration in Codex: built-in and custom agents, a model per agent, sandboxing, worktrees.
- Patterns that work (fan-out/fan-in, explorer, worker and reviewer, verification gates) and how they fail.
- Automation: running agents headless in CI, on a schedule and around the clock, with permissions, cost limits and a human approval step.
What participants do
- 1 Run a parallel review squad on a real branch and compare it to a single-agent review.
- 2 Build a multi-agent pipeline for a real team workflow, with an independent verification step.
- 3 Run that pipeline headless in CI against a real repository.
What they take home
- Custom agents and a working automated pipeline in their repo.
- A checklist for deciding when orchestration is worth it.
- A repo with the workshop's exercises and materials.
Frequently Asked Questions
Can you tailor it to our team?
Yes. Before the session I have a tailoring call with the group lead. The hands-on part then runs on the team's real tasks, or on prepared exercises I bring.
Does it matter what language or stack we use?
No. The agent reads and writes the code, whatever the language. Participants work on their own laptops with the tools they already use. Exercises run on the team's real tasks, or on prepared exercises I bring. The hands-on part is in Codex, and the patterns carry over to Cursor.
Can you run it on-site abroad?
Yes. I fly in for a few days and can run several sessions or teams back to back. It also runs on-site in Israel or remote.
What happens after the workshop?
About 30 days later I run a follow-up session with the group. Participants also keep a repo with the workshop's exercises and materials.
Related workshops
Agents in Production: Reliability at Scale
An agent that works on your laptop is not an agent that runs hundreds of thousands of times. Participants take one agent from prototype to something they can run at scale, measure and trust.
See the Agents in Production workshopRole-Specific Harness Engineering and Token Optimization
Same model, different harness, very different results. Participants build a harness tuned to their role and measure what it saves on a real task.
See the Harness Engineering workshopGet in touch
Tell me about your team and what you want them to walk away with.