Overview

You're not learning to prompt — you're learning to lead an engineering team that happens to be made of agents. This intensive takes you across the full software lifecycle: turn a messy brain dump into a phased, spec-driven roadmap with OpenSpec, then stand up autonomous workers behind a test pipeline and pre-commit gates where nothing merges until it passes. You'll orchestrate specialist agents working in parallel — coordinating over files and Matrix, with a release-manager agent handling the merges — while you stay the senior engineer, gating everything with checklists, automated security review, and prompt-injection filtering. Give your agents persistent memory that self-corrects from its own failures, kill recurring bugs for good with TDD and Playwright E2E, and run the whole team from your phone. You leave shipping real software, not demos — with control at every checkpoint.

Where This Class Leads

What you leave able to do

  • produce a list of where untrusted input enters a system
  • characterise an applications injection surface
  • verify model written code against its specification
  • verify a program does what you claimed with a test
  • design a review gate that catches what the doer cannot see
  • synthesise an accountability regime for an unattended agent
  • synthesise an agent that carries notes across its own runs

How you show it. Paired runs of the same multi-step task with the note store kept and cleared, where the cleared run repeats a step the noted run skips, plus the note text the agent wrote and the later turn that cites it.

Join Us

Want to schedule this class for your team?

Contact us: liz@themultiverse.school