Overview

Robert Brennan demonstrates how to automate large-scale software refactoring using parallel agents. Agent orchestration enables tackling massive tech debt that’s too big for single-shot solutions by coordinating multiple AI agents working simultaneously on decomposed tasks like CVE remediation and code modernization.

Key Takeaways

  • Break massive refactors into agent-sized chunks - decompose large tasks into parallelizable pieces that single agents can complete in one commit/PR
  • Design for 90% automation, not 100% - maintain human review loops at intermediate steps rather than trying to fully automate complex refactoring workflows
  • Use dependency ordering for systematic refactoring - start with leaf nodes in your dependency graph and work backwards to entry points for more principled migrations
  • Context sharing prevents repeated failures - implement strategies for agents to share solutions when multiple agents hit the same problems during parallel execution
  • Orchestration scales beyond individual productivity - while most developers get 20% productivity gains from single agents, orchestrated agents can achieve 30x improvements on specific tasks like CVE remediation

Topics Covered