25+
Years of software engineering, since 2001
Engineering AI Agents Systems
Building intelligent systems that scale.
Senior Software Engineer, AI Systems Architect, Author and Technical Speaker. Exploring enterprise engineering, autonomous AI agents, developer productivity and reliable software systems.
Impact at a glance
14,000+
Playwright tests across the Power Platform ecosystem47
Engineering teams supported with test infrastructure1
Published book. A second book from Packt arrives November 2026.
Figures are reported by the author. Experience is calculated from a July 2001 start.
Selected work
Engineering projects
AI agents and testing tools I have built, with the problem each one solves.
Test Automation
NL2Test - AI-Assisted Testing
Transform natural language descriptions into executable Playwright web integration tests with AI-powered test automation.
- Playwright
- OpenAI GPT-4
- TypeScript
- Node.js
AI and Agents
Coffee Ordering Barista Customer Support System
AI-powered customer support system with multiple specialized agents for coffee ordering, recommendations, and troubleshooting.
- AI Agents
- LangChain
- GPT-4
- FastAPI
AI and Agents
AI-Powered Travel Platform
Comprehensive travel platform using AI agents for vehicle rentals, itinerary planning, and personalized travel recommendations.
- Vercel AI SDK
- Next.js
- AI Agents
- TypeScript
How I build
NL2Test, from a sentence to a Playwright test
How NL2Test turns a plain-language description into an executable Playwright test, with a model planning the test and an MCP server driving a real page.
10 stepsPress play, or use next and previous to follow the flow one step at a time.
Read all 10 steps
AI and Agents
How an MCP request flows
A walk through one Model Context Protocol request, from the client through authentication, memory and the model to a server that coordinates tools.
8 steps 8 parts Simplified view
AI and Agents
Multi-agent supervisor
A supervisor agent receives a request, hands sub-tasks to specialist agents one at a time, keeps shared memory, and combines their results into one answer.
8 steps 7 parts Simplified view
AI and Agents
RAG pipeline
How retrieval-augmented generation works end to end, from loading documents into a vector store to answering a question with the closest passages.
8 steps 7 parts Simplified view
Technical writing
Latest articles
Guides and field notes on AI agents, MCP, Playwright and developer tooling.
AI and Machine Learning
AI Agents: From Chatbots to Autonomous Digital Workers
What changes when AI moves from answering questions to completing business workflows, and how to assess the benefits, risks and oversight it needs.
9 min read
- AI
- Agents
- Enterprise AI
AI and Machine Learning
Building an Agent Factory with Deep Agents, LangGraph and Langfuse
An independent Agent Factory architecture using the LangChain stack and Langfuse, with scoped tools, durable workflows, evaluations and human approval.
15 min read
- AI
- Agents
- LangChain
AI and Machine Learning
Inside an AI Agent: Architecture, Memory, Tools and Planning
How an AI agent's reasoning model, memory, planning and tools fit together, and where permissions, human approval and evaluation belong.
10 min read
- AI
- Agents
- Software Architecture
Books & publications
Written for builders
Books I have authored or technically reviewed on AI, the Model Context Protocol and test automation.
Published
Author
LangChain in Action
Architecting multi-modal and context-aware agents
Build production-ready AI agents with LangChain, multimodal reasoning, persistent memory, RAG, autonomous workflows, and multi-agent collaboration.
BPB Publications
Coming November 2026
Author
Hands-On MCP Server using C# and .NET
A practical guide to the Model Context Protocol on the .NET platform
A hands-on guide to building Model Context Protocol (MCP) servers with C# and .NET, published by Packt.
Packt
Early Access
Technical Reviewer
Hands-On Automated Testing with Playwright
Create fast, reliable, and scalable tests for modern web apps with Microsoft's automation framework
A practical Playwright book by Faraz K. Kelhini and Butch Mayhew. Deepak Kamboj contributed as a technical reviewer, not as an author.
Packt
Speaking
Talks & workshops
Conferences, community workshops and podcasts on AI and test automation.
UpcomingLive Workshop
AI-Powered Test Failure Investigation: From Failed CI to Root Cause
Innovate QA
- November 15, 2026
- Bellevue, Washington - venue to be announced
Completed
CompletedInvited Talk
From AI Demo to Production-Ready Enterprise Product
Seattle Data AI & Security
- October 1, 2026
- Microsoft campus, Redmond, WA
Community & recognition
Giving back
Hackathon judging, mentoring and open-source work.
CompletedFinal Judge & Expert Panelist
AI Defense Lab 2026
Seattle Data AI & Security
- September 24–26, 2026
- Online
CompletedJudge & Mentor
Secure AI Hackathon 2026
Seattle Data, AI & Security Community
- July 30, 2026 – August 2, 2026
- Online
Workshops & mentoring
Hands-on sessions for QA and engineering communities.
Open source
Public repositories and developer tools.