About

I build AI systems that work in production.

Not demos. Not prototypes that need babysitting. Systems that are observable, governed, and useful — where the people responsible for them can understand what the system did and why.

Background

I'm a builder at the intersection of AI systems, developer experience, and emerging compute paradigms. My career has been defined by one thesis: the most impactful work happens where complex technology meets the humans who build and use it.

At Cartesi, I turned a 2–3 hour developer pain point into a 15-minute workflow — not through clever code alone, but through systematic feedback loops, empathy, and cross-functional execution. Before that, I founded Vyaan Health and shipped a smart respirator with on-device ML to 35,000+ customers. I hold an M.Sc. in Physics from IIT Roorkee.

Today I'm focused on building Seedhape and Sonar for agent commerce. Seedhape is an agentic-payments control plane built around mandates, policy, x402 settlement, self-custody, and auditable records. Sonar independently measures providers by uptime, latency, price honesty, schemas, and evidence so agents can choose with confidence before they pay. I also consult with US-based businesses on AI discoverability, agent systems, and agentic payments.

What I specialize in

LLM systems and RAG, multi-agent orchestration, AI discoverability, agentic payment architecture, developer experience, verifiable computation, and production safety practices — observability, permissions, evaluation harnesses, and human handoffs.

I think about interpretability as an engineering discipline, not an academic one. I design production systems with that constraint built in from day one, not bolted on after a failure.

Common questions

Can you help my business appear in AI assistant answers?
Yes. I help businesses publish clear, supportable information that AI assistants can understand and cite — focused pages, structured data, crawl guidance, and recommendation scenarios.

What kinds of AI systems do you build?
LLM and RAG systems, multi-agent workflows, conversational commerce, AI evaluations, on-device ML, verifiable compute, and secure agentic payment experiences.

How do I start a consulting engagement?
Book a short call or email a brief description of your business, bottleneck, and desired outcome. I'll identify the most useful starting point.

What does an AI systems consultant help a business do?
Identify high-value customer and operational workflows, then design and ship practical AI capabilities — discoverability, customer-facing agents, retrieval systems, and governed transaction flows.

Where to go from here

Read the blog for how I think about problems. See selected projects for what I've shipped. Check the now page for what I'm working on at the moment. Or contact me to discuss a consulting engagement.