Jordan, an AI architecture advisor

If engineers are accelerating with AI, architects need to match velocity. 🏃‍♂️💨

I built Jordan — an AI architecture advisor that operates across 100+ repositories to help us do what we do best: understand systems and design integrations at scale. It is built with Claude Code and runs on Anthropic Claude Code.

The problem: 50 applications, 20 teams, knowledge fragmented everywhere. Simple questions like “How does System A actually talk to System B?” consume days.

Jordan deploys five specialized agents:

🔍 Project Gatherer scans repos and builds a system catalog
🔬 System Researcher documents APIs, events, and integration points with file-level citations
🔗 Integration Researcher maps existing connections with sequence diagrams
📐 High-Level Designer generates design options with trade-offs and timelines
📋 Low-Level Designer produces implementation specs: schemas, migrations, scaffolds

The insight: each agent compounds knowledge from the others. It’s cumulative intelligence that scales with every design cycle.

What sets this apart: it reads actual code, generates Mermaid diagrams, cites sources for verification, and grabs data via MCP. ✅

I’m after feedback from architects dealing with complex multi-system integrations:

🤔 What would make this valuable for your work?
🤔 What capabilities are missing?
🤔 Would you actually use this?

The goal isn’t replacement — it’s augmentation. We’re not obsolete; we’re about to get superpowers. 🦸‍♂️