AI-Native Engineering: Coding Agents, Memory & Collaboration

About this event

AI Native Netherlands is back! We'll be hosting our 14th edition at the Xebia (https://xebia.com/) office in Amsterdam, and this is our last meetup of the year. A huge thank you to our friends at Xebia for hosting us and providing food and drinks. This is the second time Xebia has had us over, the OGs among you will remember the early editions. This time, we're looking at two challenges that come with AI-assisted software development. First, how coding agents handle memory and context across sessions. Then, how teams can rethink collaboration when AI changes the speed of development and what individuals can accomplish on their own. We'll cover: • What coding agents actually remember, and what survives between sessions. • The difference between session history and persistent memory, and why it matters. • How Claude Code handles memory, with comparisons to Codex and Pi. • Why traditional ways of collaborating may no longer work as AI accelerates development. • How teams can establish clear responsibilities, shared standards, and processes that keep everyone aligned. • What needs to change as individual developers become capable of doing more with AI. Speaker 1: Vladislav Ramazaev (https://www.linkedin.com/in/vladar107/) (BlueDolphin (https://bluedolphin.io/)) Vlad is a Senior Software Engineer at BlueDolphin with 10+ years of experience in architecture and system design, across distributed systems, data pipelines and high-load services in C#/.NET, Kotlin and TypeScript. At BlueDolphin, he works on the microservices behind an enterprise architecture SaaS platform. Previously, he built data pipelines for AI model training and evaluation and led architecture and delivery practices across multiple engineering teams. Talk: Inside Coding Agents: What Survives Between Sessions Your coding agent can recover a decision from months ago, but did it actually remember it? This technical talk goes inside real coding-agent sessions to examine what gets stored, what survives context compaction, and what the model can access later. Using Claude Code as the main example, with focused contrasts from Codex and Pi, we'll separate session history from persistent memory and see how a correct observation can become harmful when its original scope is lost. You'll leave with a clearer model of agent memory and practical principles for deciding what should be loaded automatically, reviewed regularly, or retrieved only when needed. Speaker 2: Alexander Fisher (https://www.linkedin.com/in/alexander-fisher-551198a9/) (Xebia) Alexander has a decade of experience in data, working across the full data stack, and now focuses on dbt. He takes pride in building elegant, scalable solutions and working closely with teams. Teaching, sharing knowledge, and helping others improve code quality are important parts of his work. Talk: Collaboration in the Age of AI: A Process-Based Approach AI is changing how quickly we develop software and how much we can accomplish individually. But many of the formal and informal conventions we've relied on to collaborate effectively aren't keeping up. As individual capabilities grow, how do we make sure teams still work well together? Alexander will explore how a process-based approach can help teams adapt to this shift. How do we establish clear responsibilities, maintain shared standards, and make sure everyone knows where to focus their efforts when the way we work is changing so quickly? The talk looks at what needs to change in team collaboration as AI becomes a bigger part of everyday development. Agenda: 18:00 — Arrival, food & drinks 18:45 — Talk \#1 \| Vladislav Ramazaev 19:30 — Talk \#2 \| Alexander Fisher 20:15 — Open conversation, networking & more drinks 21:00 — Wrapping up What to bring: Just curiosity and your own questions. Whether you're experimenting with coding agents, dealing with context and memory limitations, or figuring out how AI is changing collaboration within your team, we'd love to hear your