I build AI agents that
hold up in production.
Senior software engineer with six years shipping production AI and cloud platforms across fintech, healthcare, and now agentic analytics. Currently AI Engineer at Anlytic, building a multi-agent system on Anthropic Claude that turns plain-English questions into live dashboards — and where I cut LLM spend 60–70% along the way.
- 60–70%
- LLM cost cut
- 6 yrs
- in production
- Millions
- of records
- Fortune 500
- healthcare
Where the years went
- 01
Anlytic
AI EngineerShipping a production multi-agent AI analytics platform that turns plain-English questions into live dashboards — built on the Vercel AI SDK and Anthropic Claude.
60–70%LLM API cost reduction via dual compression - 02
IQVIA
Senior Software EngineerLed enterprise microservices and AI-powered clinical decision support across IQVIA's global platform, supporting millions of patient records.
40%Reduction in clinician research time - 03
Autonomix
AI Software Engineer (Part-Time)Building Donna Assistant - a full-stack AI-powered productivity platform enabling Inbox Zero across email, calendars, and messaging platforms with AI prioritization, gamification, and distraction management.
4+Communication platforms unified under single API - 04
Selise
Software EngineerFive years across European fintech and on-chain systems — the run that taught me what 'production' actually means.
$2M+Revenue from dashboard solution across EU markets
An agent is a production system first and a model second. The interesting work is everything that happens between “retrieved” and “answered” — the routing, the guardrails, the cost, the failure modes.
Notes from the build
- 10 min read
How We Evaluate Our Agentic Systems: Evals, Evalite, and Humans in the Loop
Shipping a multi-agent system on vibes is a great way to break production. Here's how we made a probabilistic analytics agent measurable — with Evalite, layered scorers, and human review that actually feeds back into the loop.
AIEvalsAgentic AIRead - 8 min read
The AI World Just Had Its Wildest Month — Here's Everything You Missed
From trillion-dollar mergers and AI models that outperform engineers, to Disney characters in AI generators and deepfake scandals — a complete roundup of the biggest AI news from the last few weeks.
AIMachine LearningIndustry NewsRead - 9 min read
Claude Agent Skills: What They Are, Why They Matter, and How to Build Your Own
A deep dive into Anthropic's Agent Skills — the open standard that turns general-purpose AI agents into specialized experts. Learn the architecture, the spec, and how to create your own skills.
AIClaudeAnthropicRead - 7 min read
Mastering Clawdbot: 5 Power Tips to Supercharge Your AI Assistant
Transform your Clawdbot from a simple chatbot into a proactive AI employee. Learn advanced memory optimization, multi-model workflows, and automation techniques.
AIClawdbotOpenClawRead