Agentic AI in Action: From RAG to Agents and Bringing Archives Back to Life

We’re thrilled to announce our first PyData Amsterdam edition with some The Hague flavor on Thursday, October 30, at the Odido office in The Hague!

This edition focuses on Agentic AI in Action - from lessons learnt from levelling up from RAG to Agentic systems to Chatting with Amsterdam's 750 year history (gotta put Amsterdam in there somehow :) ).

Come for the deep insights, live demos, and real-world lessons on building next-generation Agentic AI systems - and stay for great conversations, networking, and a fun evening of learning with the PyData community!

Agenda

• 18:00 - 18:45: Walk-in with drinks & food
• 18:45 - 19:00: Odido Introduction
• 19:00 - 19:45: Talk 1 : From RAG to Agentic System: lessons learnt from the transition by Zhengru Shen
• 19:45 - 20:00: Short break
• 20:00 - 20:45: Talk 2 - Chat with History – Bringing an archive to life using AI by Lucas Puddifoot and Niket Saurabh
• 20:45 - 21:30: Networking + drinks & bites

Talk 1 : From RAG to Agentic System: lessons learnt from the transition by Zhengru Shen

Talk Summary:
What does it really take to move from a RAG chatbot to an agentic AI system? In this talk, I’ll share the technical and organizational lessons from our migration: the importance of framework choice, common design patterns for building AI agents, the hidden blockers in data foundations, and how we approach evaluation using Langfuse. Through live demos, I’ll illustrate key challenges and design decisions that shaped our system. Beyond the technical aspects, we’ll explore the evolving skill sets for AI teams, the impact of AI-assisted coding, and practical ways to measure real business impact.

Zhengru Shen is a Senior Data Scientist at Odido, leading a team in building AI-powered solutions that drive efficiency and innovation. With over a decade of experience spanning Generative AI, MLOps, and data-driven product development, Zhengru has delivered large-scale applications such as voice analytics pipelines, RAG-based AI assistants, and financial email automation systems. Passionate about solving complex challenges, he brings a blend of technical expertise and leadership to advance real-world AI adoption.

Talk 2 : Chat with History – Bringing an archive to life using AI by Lucas Puddifoot and Niket Saurabh

Talk Summary:
Discover how 750 years of Amsterdam’s history became searchable, speakable, and accessible to everyone. Chat with History uses Agentic AI to unlock the Amsterdam City Archive — sixty kilometres of handwritten documents — allowing users to ask natural-language questions and receive answers drawn directly from historical sources.
Lucas Puddifoot and Niket Saurabh share the technical journey behind the project, including how Semantic Kernel and a multi-agent system were used to orchestrate intelligent interactions. They also discuss the challenges of working with historical data and building a scalable, multilingual experience that was even showcased to Satya Nadella.

Lucas Puddifoot is an AI engineer at Capgemini, where he designs and builds cutting-edge GenAI solutions used across the globe — from agentic chatbots to document intelligence platforms. His work exemplifies how AI can drive real-world impact across industries.

Niket Saurabh is a Senior Azure Cloud Engineer and Generative AI Developer with hands-on experience delivering Gen AI solutions for diverse clients. He specializes in leveraging cutting-edge tools and frameworks such as Prompt Flow, Semantic Kernel, and other modern AI technologies to build scalable, intelligent applications. Passionate about development, Niket thrives on solving complex problems and driving innovation through cloud-native and AI-powered solutions.

Directions
The venue for this meetup is the Odido headquarters in Den Haag (Waldorpstraat 60, 2521 CC, Den Haag). The office is situated next to the train station Den Haag HS. It is also reachable from Den Haag Centraal via trams 15, 17 and buses 22, 28 (with a bit of walking).