Middle Mann  /  Work  /  Data Warehouse and AI Agents

Your own Power BI. Your own AI workforce. Built around how you actually run.

A self-hosted data warehouse that pulls every system you use into one place, kept current with webhooks and scheduled syncs. AI agents on top of it can read the unified data and act on it: qualify leads, follow up with prospects, generate reports, watch metrics, raise alerts. Owned end to end. Custom to the operator. No per-seat license, no monthly subscription, no vendor sitting between you and your own data.

Role Designed and built end to end
Type Custom warehouse and AI agent platform
Stack Node, Express, SQLite, Claude
Because

Operating data lives in four, six, ten systems. None of them talk to each other.

  • One Warehouse
  • Real-Time Sync
  • AI Agents
  • Custom Dashboards
  • Owned Data
  • Flexible Backups
  • Hardened Server
  • Encrypted Vault
  • Audit Trail
  • No Subscriptions

Most operations run on a stack of disconnected tools. A CRM, a payments processor, an operational pipeline, an accounting package. Anyone asking a real question has to ask several systems and reconcile by hand. Power BI exists to solve exactly this, rented per seat per month, forever.

A custom warehouse pulls every record from every source into one place and exposes the unified data to whatever dashboards, reports and AI agents the operator actually needs. Shaped to the workflow, not to whatever a SaaS vendor decided was the common case. Owned, not rented.

The Build

One warehouse. Any sources. Any agents.

A Node and Express backend with better-sqlite3, Knex migrations and a node-cron scheduler. Real-time webhooks for sources that support them. Scheduled incremental syncs for everything else. AI agents on top, scoped to the work and logged on every action. Runs under a process supervisor on the operator's own server, behind a hardened reverse proxy, with TLS and access locked down at the edge.

01Warehouse. One local database aggregating every connected source, queryable from anywhere
02Sync. Webhooks plus incremental pulls, on whatever schedule the workload calls for
03Agents. AI agents on top of the warehouse, each scoped to a workflow and grounded in real data
04Reports. Custom dashboards and pipeline visualizations rendered from live data, not from a vendor's template
05Vault. Encrypted secrets behind a second factor, admin-only access, session-timed
06Backups. Scheduled backups on whatever cadence makes sense, with manifest and audit log per run
The Agents

AI agents that know what the business actually knows.

An agent reads the warehouse, decides on an action and writes the result back. Some respond in real time. Some run on a schedule. Some chat with humans, some chat with other systems, some only speak up when something needs a human eye.

This build runs three agents as a working example: a qualifier handling inbound SMS, a reactivation worker nurturing cold contacts, a follow-up worker handling warm leads with full conversation context. The next build runs whatever agents fit the work. Same engine. Different shape.

The Cockpit

Every surface the operator needs, none of the ones they don't.

A self-hosted dashboard sits in front of the warehouse. Sync status, agent health, campaign control, custom reports and the secrets vault all live behind one login. KPI dashboards render from live warehouse data and can be shaped to whatever metrics actually matter to the operator. Hosted on the operator's own server, behind a hardened reverse proxy with TLS, rate limits and locked-down firewall rules. Anything privileged sits behind a second factor.

Sync
Status
Agent
Health
Pipeline
Receivables
KPI
Dashboard
Campaign
Control
Source
Connectors
Agent
Designer
Report
Builder
Secrets
Vault
Backup
Console
Audit
Log
The Stack

Boring on the outside. Production-grade underneath.

Every choice optimizes for ownership, durability and operational sanity. SQLite holds the truth. Express moves the bytes. Cron does the work. Claude (or whatever model the operator prefers) writes the messages.

Frontend
HTML Reports Live Dashboard Pipeline Diagrams Vanilla JS Server-Rendered
Backend
Node.js Express better-sqlite3 Knex node-cron axios bcryptjs AES-256-GCM TOTP 2FA
Infrastructure
Process Supervisor Nginx Reverse Proxy TLS Firewall Rules Encrypted Vault Self-Hosted
Integrations
Anthropic Claude BYO AI Provider CRM Connectors Payments Connectors Accounting Connectors Calendar APIs Webhook Signature Verification
The Outcome

A back office shaped to the way you actually work.

Every system pours into one warehouse. Every dashboard answers a real question. Every AI agent acts on data the operator can see and audit. What's shown here is one example. The next build looks like whatever the next operator actually does for a living. Same engine. Different shape. Owned.

AI agents, one platform
1
Source of truth, every system
0
Per-seat licenses required
Build yours

Want a platform like this for your operation?