I design and ship production AI systems: agent orchestration, retrieval, and evaluation that hold up under real-world constraints. Hands-on across architecture and delivery, from first prototype to production.
I've built and scaled production systems across enterprise, growth-stage, and regulated environments, including a ~60-person engineering org at PwC, a Series A team I grew from 3 to 20+ at Spekit, and regulated platforms in fintech and healthcare.
I founded Beesla, an AI-native platform integrating agent workflows, retrieval pipelines, and production guardrails from day one, reaching 1M+ impressions across search engines and AI assistants and 80K+ unique users. My current work is agentic systems that transact: autonomous agents that hold their own wallets, buy and sell services in USDC, and back every claim with a verifiable receipt.
I work at the intersection of product decisions and engineering execution: translating business priorities into systems that ship cleanly, and sitting with the customers who use them.
AI agents now buy services from other agents over the x402 payment protocol: USDC micropayments, no accounts, no API keys. What nobody built was the trust layer underneath. Actuary402 is an autonomous watchdog that buys from the services on Circle's Agent Marketplace with real, policy-capped USDC, measures uptime, latency, and protocol conformance, has Gemini grade every paid response in production, and sells the resulting trust scores back to other agents at $0.001 per lookup. We pay. Directories index.
An unattended probe fleet runs a round every 30 minutes with no human in the loop, every purchase and sale settles through Circle Gateway with a verifiable receipt, and the agent holds its own MPC wallet whose spending rules are enforced by the wallet itself, not by the code that could misbehave. Submitted to the $2M Build with Gemini XPRIZE with the $50K Circle Agentic Economy Prize opt-in.
Circle Agent Stack (Agent Wallets, Gateway Nanopayments, x402 v2) · Gemini · Google Cloud Run · TypeScript.
Every fifteen minutes, Mender wakes up, reads the last hour of traces from another agent via the Arize Phoenix MCP server, clusters failures, hypothesizes a root cause, generates a focused eval set, drafts a prompt patch, re-runs the same evals against the patched version, and, if it measurably improves, posts a structured incident card to Slack with one-click human approval. He also reads his own traces every cycle and tunes himself: how many evals to generate, what confidence threshold to use, when to ask for help.
End-to-end verified: detected a real regression in a target agent ("ambiguous source currency silently defaulted to USD"), generated 10 focused eval cases, lifted pass rate from 4/10 to 10/10 on the patched version, a +60% lift, ready for one-click Slack approval.
The pattern generalizes: an agent that reads production traces, clusters failures, generates targeted evals, and validates its own patches before a human ever sees them. It's the same observe/evaluate/improve loop that any production LLM system needs.
Stack: Google ADK (Python) · Gemini 3 on Vertex AI · Arize Phoenix + Phoenix MCP · Slack Block Kit · Cloud Run · Cloud Scheduler · Firestore.
Independent studio work through Strawberry Digital: designed, built, and shipped in-house.
Interactive tournament-poker trainer. 136 lesson hands street-by-street plus a graded 100-hand exam covering push/fold, ICM, and M-zone play.
Curated events and places discovery across 50+ US metros. Chosen, not crowdsourced.
Automated product-research and deals engine with live marketplace pricing and buying guides.
Cozy offline math game for kids: arithmetic through fractions, decimals, and shapes.
A speed reader with a point of view: one word at a time, at a pace authored for each piece, with no library, no import, and no slider. You tune in, you don't operate it.
Call-and-response vocal-pitch trainer built on the classic expanding-scale warm-up. Plays each phrase on piano, listens as you sing it back, and scores every note in cents.
Designing and deploying autonomous agent architectures with orchestration, memory, and reliability patterns.
Context engineering, structured outputs, evaluation frameworks, and retrieval-augmented generation at scale. Hands-on across Anthropic Claude, OpenAI, and Google Gemini.
Scalable system design, microservices, API-first platforms, and operational reliability at enterprise scale.
AWS, GCP, and Azure architecture. Infrastructure-as-code, CI/CD pipelines, and cloud-native operational patterns. Python, TypeScript, PostgreSQL, Docker, Kubernetes, Terraform.
Team building, delivery discipline, cross-functional alignment, and shipping culture in fast-paced environments.
Production readiness frameworks, guardrails, risk assessment, and compliance in regulated domains.
Ship the real thing. A live system with receipts beats a deck with projections.
Sit with the customer. The best product decisions happen inside someone else's workflow.
Automate the work, keep the judgment. Agents run the loops; a human owns the rules.
Momentum is a decision. Most projects stall waiting on choices, not code.