iii-agentic-backend

name	iii-agentic-backend
description	Creates and orchestrates multi-agent pipelines on the iii engine. Use when building AI agent collaboration, agent orchestration, research/review/synthesis chains, or any system where specialized agents hand off work through queues and shared state.

Agentic Backend

Comparable to: LangGraph, CrewAI, AutoGen, Letta

Key Concepts

Use the concepts below when they fit the task. Not every agentic workflow needs all of them.

• Each agent is a registered function with a single responsibility
• Agents communicate via named queues (ordered handoffs) and shared state (accumulated context)
• Approval gates are explicit checks in the producing agent before enqueuing the next step
• An HTTP trigger provides the entry point; agents chain from there
• Pubsub broadcasts completion events for downstream listeners

Architecture

HTTP request
  → Enqueue(agent-tasks) → Agent 1 (researcher) → writes state
    → Enqueue(agent-tasks) → Agent 2 (critic) → reads/updates state
      → explicit approval check (is-approved?)
        → Enqueue(agent-tasks) → Agent 3 (synthesizer) → final state update
          → publish(research.complete)

iii Primitives Used

Primitive	Purpose
registerWorker	Initialize the worker and connect to iii
registerFunction	Define each agent
trigger state::set, state::get, state::update	Shared context between agents
trigger({ ..., action: TriggerAction.Enqueue({ queue }) })