Building TFCRM: Guarded LangGraph Swarms, Postgres MCP, and Durable Churn Analysis for the OpenAI Hackathon

Avi Sharma — Fri, 17 Jul 2026 12:26:15 +0000

The Problem: Traditional CRMs Are Data Cemeteries

Most B2B SaaS companies, subscription startups, and agencies suffer from the same operational bottleneck: stale CRM data. Traditional CRMs record historical transactions and basic communication logs perfectly, but they fail to act on live application health metrics before a customer decides to churn.

Worse yet, spinning up AI agents to solve this problem introduces massive security anxieties. Granting a Large Language Model direct write access to a production database or an automated email dispatcher is an invitation for operational chaos.

For the OpenAI Hackathon, I built TFCRM—a stateful, customer-success CRM engineered to turn scattered telemetry events and bulk data imports into guarded, evidence-based retention workflows. It bridges the gap between automated AI insights and strict operational discipline.

The Technical Architecture

TFCRM is split into a high-performance web ledger, a real-time event ingestion engine, and a database-backed background execution queue.

Layer	Technology Stack	Responsibility
Frontend	React 19 + Vite	Multi-tenant dashboards, role-aware action mapping, and real-time agent token streams over WebSockets.
Backend	FastAPI + Python 3.12	Asynchronous token verification, workspace-scoped RBAC, and background execution polling loops.
Database	Neon PostgreSQL + `pgvector`	Relational business ledger and durable checkpoint storage for long-running LangGraph state machines.
AI Swarm	LangGraph + OpenAI	Guarded routing, semantic resolution caching, and autonomous evidence collection.
Outreach	Resend API	Human-in-the-loop delivery engine restricted to verified domain identities.


mermaid
flowchart TD
    User[CSM / Workspace Owner] -->|Interactive UI| UI[React + Vite Frontend]
    UI -->|JWT Authenticated Requests| API[FastAPI Application]
    API -->|Async State Management| Queue[Durable Background Dispatcher]
    Queue -->|State Machine Isolation| Agents[LangGraph AI Swarm]
    Agents -->|Restricted Handshake| MCP[Postgres MCP Server]
    MCP -->|Read-Only Queries| DB[(Neon PostgreSQL + pgvector)]
    API -->|Transactional Actions| DB
    API -->|Human-Approved Outreach| Resend[Resend Email API]

DEV Community: Avi Sharma

Building TFCRM: Guarded LangGraph Swarms, Postgres MCP, and Durable Churn Analysis for the OpenAI Hackathon

The Problem: Traditional CRMs Are Data Cemeteries

The Technical Architecture