Skip to main content

For the CTO

The Orchestration Engine is the BEAM-native runtime for governed agent execution. It solves:
  • How to run task agents and orchestrators durably
  • How to govern decomposition, execution, review, and reflection
  • How to supervise sessions and intervene safely
  • How to preserve provenance, audit trails, and promotion history

How It Works

  1. Define work as Nodes in a Graph (problems to solve, features to build, research to do)
  2. Decompose large problems into smaller Tasks through orchestrator agents
  3. Assign Tasks to agent sessions with explicit authority, tools, and timeouts
  4. Execute through governed harnesses (Claude Code, Codex, Gemini, or any adapter)
  5. Review outputs through mandatory independent review (multi-model GAN or human)
  6. Reflect on what went well and what the system should learn
  7. Promote reviewed artifacts through workspace claims and governed mutation

Key Properties

  • Declarative API — spec/status pattern, reconciliation-based (like K8s but for agents)
  • Model-agnostic — swap Claude for Gemini for a local model; governance doesn’t change
  • Policy-based admission — no work starts without passing the governance pipeline
  • Monotonically narrowing authority — children can never exceed parent’s grants
  • Producer can’t certify own output — structural provenance separation, not just different endpoints
  • Budget through timeouts and retry limits — not token counting (that’s billing, not governance)