Agent Orchestration in Amprealize

What It Is

Amprealize implements a supervisor-pattern multi-agent system where the orchestrator routes tasks to specialized agents based on role declarations, behavior conditions, and task requirements.

How It Maps to Concepts

Architecture

Task Request
    ↓
[Agent Orchestrator]
    ├── Role Detection (Student/Teacher/Strategist)
    ├── Behavior Retrieval (BCI)
    ├── Context Composition
    └── Agent Dispatch
         ↓
[Agent Execution Loop]
    ├── Tool Calls (MCP tools)
    ├── Self-Monitoring (adherence tracking)
    └── Result / Handoff
         ↓
[Handoff Work Item] (if ADOPT/ADAPT verdict)

Key Components

• agent_orchestrator_service.py — Routes tasks to agents
• agent_execution_loop.py — Runs the agent cycle (think → act → observe)
• agent_registry_service.py — Registers available agents and their capabilities
• adherence_tracker.py — Monitors whether agents follow their behaviors

Handoff Pattern

When an agent's work produces an actionable verdict (e.g., research evaluation yields ADOPT), the orchestrator creates a work item for the next agent. This is the sequential pipeline pattern from Multi-Agent Orchestration.

See Also

• BCI In Practice — How agents get their behaviors
• Context Composition In Practice — How agent prompts are built