From Autocomplete to Orchestrators en
Two years ago, I enabled GitHub Copilot, and the first thing it did was suggest method names that didn't exist. Two weeks later, I disabled autocomplete entirely. That was actually the turning point.
This session is an honest account of how my use of GitHub Copilot evolved across real client projects — from autocomplete frustration, to using Chat to navigate unfamiliar codebases, to spec-driven development for greenfield work, and eventually building a custom multi-agent orchestrator with JIRA integration.
The talk is built on a simple idea: Copilot is not just one tool, but many, and the key is knowing when to use each one. You’ll leave with hands-on techniques for every mode, a realistic look at where each method falls short, and a recorded demo on building and guiding a custom agent stack. No hype—just what worked, what didn’t, and why.
Onboarding a Legacy Codebase into AI Tooling en
Every AI coding demo runs on a fresh project with clean conventions. The code most of us are paid to maintain is 10+ years old, carries generations of patterns, and has a wiki that stopped being accurate in 2021, while most of the actual business logic lives in developers' heads.
That gap is where AI rollouts quietly stall. The licenses get bought, the tooling helps on new files, and it stays close to useless on the code that fills most of the week. Not because the tools are weak, but because nobody has told them anything about the system.
I spend a couple of days on site with teams fixing this, and the work is stranger than it sounds. Almost none of it is configuration or specific tooling. Most of it is getting a machine to read the code and describe the system back to you. Reviewing the output with the people who have maintained it for years while they argue with what the tooling wrote. The arguing is the valuable part. By the end of the day, the repository knows things that used to live in three people's heads. This way, no tooling needs to guess how the codebase works and behaves; it's all documented.
I'll show what comes out of that day, what a model reliably gets wrong about a system it has only just read, and why the teams that do this in the wrong order walk away convinced AI has nothing to offer old code.
Vendor-agnostic. Copilot, Claude Code, and Codex all need the same thing.
The modular monolith - the bridge between monoliths and microservices en nl
In this talk, I provide an overview of how and why a modular monolith is one of the best solutions for modern applications. I share my real-life experiences working with a modular monolith and explain how to implement it in existing applications and new greenfield projects.
Modular monolith - de brug tussen monoliet en microservices en nl
In deze lezing geef ik een overzicht van hoe en waarom een modulaire monoliet een van de beste oplossingen is voor moderne toepassingen. Ik deel mijn ervaringen uit de praktijk met het werken met een modulaire monoliet en leg uit hoe je deze kunt implementeren in bestaande applicaties en nieuwe greenfield-projecten.
5 key lessons learned while modernizing applications en nl
After a decade of modernizing applications, I’ve certainly had my share of mistakes—and learned so much along the way! In this one-hour session, I’ll share the highlights, the challenges, and those memorable 'oops' moments, helping you avoid the tougher lessons and head straight to success. Together, let’s make your modernization journey as smooth as possible!
5 lessen die ik geleerd heb bij het modernizeren van applicaties en nl
Na een decennium van het moderniseren van applicaties, heb ik zeker mijn deel van de fouten gehad - en onderweg zoveel geleerd! In deze sessie van een uur deel ik de hoogtepunten, de uitdagingen en die gedenkwaardige 'F**K'-momenten, zodat je de moeilijkere lessen kunt vermijden en direct naar succes kunt gaan. Laten we samen uw moderniseringsreis zo soepel mogelijk laten verlopen!
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top