The Hidden Layers of AI Systems: Memory, Retrieval, and Search

About Event

Most AI systems don’t fail because of models — they fail because of memory, retrieval, and evaluation.

Agents accumulate too much context and lose signal. RAG pipelines degrade due to poor chunking. Search systems return results, but not always the right ones. And evaluating retrieval quality remains one of the hardest problems in production AI.

This meetup explores what it actually takes to build reliable, production-ready AI systems, with a focus on:

how agents store, retrieve, and forget informationhow to improve context quality in RAG systemshow to evaluate search performance beyond simple metricshow embeddings behave outside traditional text-based use cases

We’ll hear from engineers working on real-world AI infrastructure, followed by Q&A and time to connect with other builders in Amsterdam.

Topics We’ll Explore

Agentic Memory Architecture

Why memory matters in production AI systemsAvoiding context bloating and managing long-term memoryWhen agents should forget: memory lifecycle, drift, and degradationPractical patterns using persistent memory systems (e.g. mem0 with Qdrant)

Late Chunking in Production RAG Systems

Why naive chunking leads to poor retrievalMoving from sentence-level embeddings to contextual chunkingPreserving document-level meaning across chunksImproving recall and relevance in real-world systems

Evaluating Search Quality

Why evaluation is often overlooked in retrieval systemsComparing exact match vs semantic (fuzzy) retrievalPractical mental models for measuring search performanceInsights from recent research on retrieval evaluation

Embeddings Beyond Text

Working with embeddings for code, tables, time-series, spatial, and image dataRetrieval patterns for non-text modalitiesReal-world example: computer vision at the edgeMulti-camera product verification and semantic search across visual datasets

Agenda

5:30 – 6:15 PM | Doors Open — Arrival & NetworkingCheck-in, food, drinks, and informal networking

6:15 – 6:25 PM | Welcome & KickoffOpening remarks from MLOps Community

6:25 – 7:05 PM | Qdrant[Talk Title TBC]Deep dive into memory architecture, retrieval quality, and evaluation in production AI systems

7:05 – 7:35 PM | Speaker TBC[Talk Title TBC]

7:35 – 8:05 PM | Speaker TBC[Talk Title TBC]

8:05 – 9:00 PM | Panel Discussion, Audience Q&A + NetworkingShared discussion across speakers, audience questions, drinks, and networking

Who Should Attend

AI / ML engineersBackend and data engineersEngineers building RAG or agent systemsTechnical founders and product buildersAnyone working on search, retrieval, or AI infrastructure

Seats are limited.