Speaker profile

Technical stories that make people want to build.

Henk Boelman is a Principal Developer Advocate at Microsoft, founder of the Global AI Community, and an international speaker who turns complex AI systems into clear mental models, honest lessons, and practical next steps.

Henk Boelman speaking about developer trust on stage
Keynotes, technical sessions, workshops, and candid conversations with developers.
200+sessions delivered
30+countries
Since 2017speaking internationally

From community rooms to flagship stages, every session is built to be useful before it is impressive.

Organizer-ready bio

A speaker who still builds.

Henk Boelman is a Principal Developer Advocate at Microsoft, where he helps developers turn new AI capabilities into systems they can understand, evaluate, and trust.

He founded the Global AI Community, a volunteer-run network of 190 chapters and 170,000 members, and created AgentCon, an independent AI conference series active in 65 cities. Since 2017, Henk has delivered more than 200 sessions in over 30 countries, from community meetups to stages at Microsoft Build, Ignite, the Microsoft AI Tour, and independent developer conferences.

His talks combine live technology, clear architecture, and honest lessons from the work. Audiences leave with a stronger mental model of the subject and the confidence to build what comes next.

Based inDriebergen, The Netherlands
Speaks aboutAI architecture, agents, evaluation, developer trust, and community
FormatsKeynotes, technical sessions, workshops, panels, and podcasts

Talk catalog

Sessions I can bring to your event.

01
Multi-agent systems Microsoft Foundry MCP

Talk 01

Your New Teammates: Architecting a Multi-Agent Workforce

hamba.nl is a live Dutch travel magazine built with the GitHub Copilot App and run by seven Foundry-hosted agents, orchestrated with Agent Framework, covering the full editorial pipeline from draft to published article.

In this session I'll take you under the hood: how the agents are scoped and orchestrated, how they connect to tools and data through MCP, how content, moderation, and fact-checking roles hand off to each other, and how a human-in-the-loop stays in control of final approval. This is a working system with real failure modes, and you'll leave with a concrete reference architecture for agent teams that run a function, not just generate code.

What the audience takes away

  • A concrete reference architecture for a multi-agent editorial team.
  • How to scope and orchestrate agents and connect them to tools and data through MCP.
  • How content, moderation, and fact-checking roles hand off work.
  • How human approval keeps a production system in control, including when things fail.
View slides and read the article →
02
Microsoft Foundry Agents Avatars

Talk 02

Bringing AI Agents to Life with Microsoft Foundry

AI agents are moving beyond text boxes into real-world interactions, combining models, tools, and avatars to deliver human-like experiences. This session explores how to build an end-to-end solution with Microsoft Foundry, weaving together model selection, instruction design, and tool integration into a single workflow.

As a live scenario, the session builds an AI agent that can order a pizza through a connected MCP server, then brings it to life with a real avatar for natural, conversational interactions.

What the audience takes away

  • How to combine model selection, instructions, and tool integration into one workflow.
  • A live demonstration of an agent placing a real order through an MCP server.
  • How avatars turn an agent into a natural, conversational experience.
  • A clear view of how to turn prompts and models into full-fledged, real-world AI agents.
03
Keynote Agentic AI Future of work

Talk 03

Agents of Tomorrow: Building the Next Generation of Intelligence

We stand at the edge of a profound shift in artificial intelligence. Over the last five years, generative AI has moved from novelty to necessity, transforming how we create, code, and collaborate. Now, a new frontier is emerging: AI agents that can perceive, decide, and act toward goals.

This keynote explores the evolution from copilots to fully agentic systems, highlights breakthroughs reshaping industries, and imagines the future horizons where autonomous agents redefine productivity, creativity, and discovery, and the role of humans as leaders guiding how agents operate, align with our values, and amplify our potential.

What the audience takes away

  • The evolution from copilots to fully agentic systems.
  • Breakthroughs that are reshaping industries today.
  • A view of the future horizons where autonomous agents redefine work.
  • Why humans remain the leaders guiding how agents operate and align with our values.

Talk themes

Subjects worth a room's attention.

01

AI application architecture

Clear patterns for context, orchestration, observability, and the decisions that separate demos from dependable systems.

02

Agentic systems

What agents actually are, where they help, where they fail, and how to keep humans in control.

03

Developer trust

How honest technical stories, working code, and visible tradeoffs earn more attention than polished product claims.

04

Communities that scale

Lessons from building a volunteer-led global network by giving local leaders ownership instead of instructions.

For organizers

What you can expect.

Built for your audience

The depth, examples, and framing are adapted to the room rather than copied from a generic deck.

Technical and human

Architecture and code are connected to the people, constraints, and decisions behind them.

Useful after the applause

Audiences leave with language, patterns, and practical next steps they can use with their teams.

Planning an event?

Let's make the session fit the room.

Share the audience, format, and outcome you have in mind. We can shape the right keynote, technical session, workshop, or conversation.