Back to Works
Multi-Agent AI System

Arc - AI Multi-Agent Planning System (Product Management AI)

Solo-built LangGraph(StateGraph) multi-agent planning system that routes across specialized agents (research/analysis/planning/critic) to turn a goal into an executable plan. Includes WebSocket streaming, DB persistence for conversations/token usage, and checkpoint-based resume.

Arc - AI Multi-Agent Planning System (Product Management AI)

Tech Stack

PythonFastAPILangGraphWebSocketPostgreSQL

Year

2025 - Present

Executive Summary

The Challenge

Needed realtime visibility into multi-step agent runs, plus reliability features like checkpoint/resume and consistent persistence across reconnects.

The Solution

Implemented StateGraph workflows and a FastAPI WebSocket endpoint that validates project ownership and streams workflow events/state sync. Added token/cost tracking backed by a pricing table and a checkpoint-driven resume flow for long-running executions.

Technical Documentation

Methodology & Implementation

Overview

  • Solo-built LangGraph-based multi-agent planning system (Arc/PMAI).

Purpose & User Flow

Purpose

  • Automate planning: take a goal and produce structured deliverables via agent division of labor + critique loops.

User Flow

  • Input goal/context → run workflow (agent routing) → stream step-level progress and artifacts (WebSocket) → resume from checkpoints → export deliverables.

Key Components

  • StateGraph workflows with conditional routing between agent roles (backend/agents/graph.py)
  • FastAPI WebSocket streaming endpoint with state sync/resume (backend/api/websocket.py)
  • Token/cost tracking with pricing table + provider balances (backend/agents/token_tracker.py)
  • Checkpoint-based resume flow (resume_workflow)