Building things thatshouldn't be possible yet
Now designing AI architectures and agentic workforces. Fifteen years of distributed systems architecture made that possible.
Last Transmissions
Anthropic Pulled the Rug on Third-Party Harnesses. The Damage Goes Beyond Billing.
Anthropic cut Claude subscriptions for third-party harnesses with less than 24 hours notice. The technical justification holds. The way it was done reveals a platform strategy.
The Karpathy Loop Beyond ML: How Any Business Can Run 36,500 Experiments a Year
Andrej Karpathy built autoresearch for ML. The real insight is that any business with a metric and an automated test can run 36,500 experiments a year, not 30.
Claude Code Source Leak: What Actually Happened
Anthropic accidentally published 512,000 lines of Claude Code source to npm. Here is what was inside: fake tools, undercover mode, KAIROS, and a 5,594-line file.
Areas Of Expertise
AI Systems & Agents
Autonomous agents and multi-model orchestration. The most interesting engineering problem I've encountered in fifteen years.
Distributed Systems
15+ years designing large-scale platforms across e-commerce, fintech, healthcare, and aviation.
Engineering Leadership
Building teams that care about craft, not just delivery. The hardest and most rewarding part of the work.
Open Source
Projects built and released publicly.
MCP server for TP-Link Omada Controller. Use your prefered AI agent to see all the information on your TP-Link Omada Controller.
Home Assistant integration to the Portugal E-Redes Smart Metering Plus Energy Meters
Sync Windows volume information with Home Assistant
Proof of concept. In production.
This website is run entirely by AI.
Every page. Every word. Every commit. No human edits this site directly. a team of specialized AI agents designs, writes, develops, and deploys it autonomously. This is not a demo. This is what's already possible.
Meet The AI Team