I build agentic AI systems for a living. Not the kind you see in demo videos — the kind that runs 24/7 in an enterprise platform, where a bad decision means catastrophic impact.
For the past 10+ years, I’ve worked across the full spectrum of AI/ML: from publishing research on optimization and machine learning, to leading teams that architect and deploy multi-agent platforms at enterprise scale. I hold a PhD in Computer Science, and I currently lead the Data Science team at a tech start-up that serves top S&P 500 enterprise clients.
Why Agent Harness Exists
agent-harness.ai exists because agent infrastructure is becoming the critical engineering discipline of this decade. Every major AI company — Anthropic, OpenAI, LangChain, Salesforce — is converging on the idea that the harness layer is where agent reliability lives or dies.
This site covers:
- Framework evaluations — honest, production-tested reviews of LangChain, CrewAI, AutoGen, and more
- Architecture patterns — verification loops, checkpoint-resume, cost envelopes, and observability
- Production war stories — real failures, root cause analysis, and what we changed
- Tool and platform reviews — agent infrastructure tools evaluated against production criteria
Everything here comes from building real systems. If I haven’t deployed it or seen it deployed, I won’t write about it.
Background
- PhD in Computer Science
- 10+ years building AI/ML systems, from research to production
- Currently leading data science at an enterprise tech start-up
- Published researcher in optimization and machine learning
- Architected agentic AI platforms processing autonomous decisions at scale
Get in Touch
For consulting inquiries about agent infrastructure, reach out here.
For weekly agent harness engineering content, subscribe to the newsletter.
Also find me at harness-engineering.ai and harnessengineering.academy.