Tamas Piros
AI enablement for engineering teams and their leaders.
I get your people genuinely capable with AI: hands-on workshops that have engineers building real things with LLMs, agents, and MCP, and clear-headed advice for the leaders deciding what to do about it.
25+ years building and teaching technology. Google Developer Expert. I've taught AI to tens of thousands of developers and run technical workshops around the world.
About
How I got here
I've spent 25+ years across software engineering, developer relations, and technical training, working through EMEA and APAC. Most recently I led developer advocacy at a global cloud media company, where I shaped regional DevRel strategy and delivered AI workshops and enablement programmes across the region. Earlier: principal technical instructor at an enterprise NoSQL database company, developer advocacy at an open-source AI-workflow platform, and founder of an independent training business that's reached tens of thousands of developers globally.
I'm a Google Developer Expert in Web Technologies. I hold an MBA and a BSc in Software Engineering. I've published technical books and video courses through major learning platforms, guest-lectured at a European technology university, and was named a Top 10 Best Young IT Consultant by a major professional body in 2010.
I use and build with AI every day: LLMs, vector search, agentic systems, MCP servers, on-device inference with Gemma. What I write, build, and teach comes from direct hands-on experience, not theory. That's what most AI work is missing right now.
Writing
Selected writing
Selected pieces on agents, MCP, and building real AI systems. More in the full archive.
-
What is agentic AI? A working definition for 2026
A direct definition of agentic AI, what's actually shipping in production today, what isn't, and the five things worth building first. With specifics, citations, and an honest list of what doesn't work yet.
-
Harness - A Local Managed Agent in Four Planes
Anthropic decoupled their agent into brain, hands, and session. I built a local TypeScript version in roughly 2,400 lines to see what the architecture actually feels like when you type it out.
-
MCP Servers - The Bridge Between LLMs and Real-World Tools
Model Context Protocol (MCP) servers expose tools, resources, and prompts to LLMs in a unified, structured way. This post explores how they work, how to build one, and why they are a critical part of the future AI stack.
-
Filesystem as Context: Building an AI Detective with bash-tool
Instead of stuffing documents into prompts, give your AI agent a filesystem and let it retrieve its own context. Here's how, using a murder mystery detective as the demo.
Talks
Speaking
I've spoken at technology conferences worldwide on AI, agents, agent harnesses, MCP, web technologies, and developer education. Recent topics include building with LLMs, agentic systems, and how AI fits into engineering and creative practice.
131 engagements across 11 years
- 2026 1
- 2025 17
- 2024 14
- 2023 16
- 2022 14
- 2021 28
- 2020 21
- 2019 13
- 2016 2
- 2015 3
- 2014 2
- Workshop
The name is Agent. AI Agent.
Warsaw, Poland
- Workshop
Practical AI for Web Developers
George Town, Malaysia
- Workshop
The MCP Workshop: Turning APIs into AI-Ready Tools
Taipei, Taiwan
- Workshop
When AI Stops Talking and Starts Doing
Singapore, Singapore
- Talk
When AI Stops Talking and Starts Doing
Sydney, Australia
- Talk
JSConf JP 2025: Bridging Web Developers
Tokyo, Japan
- Workshop
Build AI-powered web apps with Next.js
Tokyo, Japan
- Workshop
Practical AI for Web Developers
Tokyo, Japan
- Workshop
Practical AI for Web Developers
Hong Kong, Hong Kong
- Workshop
Web Performance
Opatija, Croatia
Books
Two books, two audiences
I'm writing for the two groups I spend most of my time with: the engineers building AI, and the luxury houses deciding how to use it.
For engineers · In progress
AI Systems Engineering
From your first API call to making autonomous agents. A hands-on path through building production AI: LLMs, RAG, evaluation, and agents that hold up outside a demo.
Read the thesis →For luxury leaders · Final draft
Artisanal Intelligence
AI deployed with restraint, judgement, and taste. For luxury leaders and the technologists who serve them.
Read the thesis →Work with me
Two ways to work together
Whether your people need to build with AI or decide what to do about it, the job is the same: I make them capable.
Team enablement
For engineering teams
Hands-on workshops and training programmes that get your engineers genuinely building with AI: LLMs, agents, MCP, and evaluation. Practical and project-based, pitched at the level your team is actually at, so the skills stick after I leave.
Start a conversation →Advisory & literacy
For leaders and non-technical teams
A senior pair of eyes for leaders deciding what to do about AI: strategy, direction, vendor evaluation, regulatory positioning. Plus practical AI literacy for the teams who need to use it well, from marketing to HR to ops.
Book an intro call →Contact
Get in touch about an engagement or a project.