WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe - Virtual Stage • Jul 2, 2026 • Session details

OLTP in the Lakehouse: Redefining Data for AI Workloads

Oleksandra Bovkun

Why do AI agents often make poor decisions despite perfect logic? Discover how embedding an OLTP database directly into your lakehouse eliminates stale data and fragile synchronization pipelines.

Pause
Mute Enter Fullscreen
#1 about 3 min

The impact of stale data on AI agent decisions

AI agents making incorrect decisions due to broken synchronization pipelines rely on outdated policy information.

#2 about 3 min

Architectural components of an LLM operating system

The LLM operating system requires an orchestration engine and shared memory to provide necessary context without becoming a bottleneck.

#3 about 2 min

Distinguishing between analytical and operational AI data requirements

AI systems simultaneously require large-batch analytical data for training and fast, low-latency operational data for pinpoint updates.

#4 about 2 min

Understanding database types for analytical and transactional workloads

Database technologies vary by optimization goals across large-scale analytical processing, strict ACID transactions, and rapid in-memory caching.

#5 about 4 min

Challenges of synchronizing operational and analytical data loops

Maintaining separate systems creates severe synchronization, unified governance, and development lifecycle friction for continuous AI improvement.

#6 about 3 min

Architectural separation of storage and compute in LakeBase

A managed PostgreSQL implementation decouples compute from storage using a page server, safekeeper, and immutable object storage.

#7 about 2 min

Leveraging compute separation for autoscaling and Git-like branching

Decoupled architecture enables instantaneous compute scaling, scaling to zero, and rapid metadata-based database branching for safe development.

#8 about 3 min

Native synchronization and unified governance across data storage

Built-in sync tables and federated queries seamlessly bridge transactional databases and analytical lakehouses under a single permission model.

#9 about 4 min

Demonstrating database branching and state recovery in production

Creating an isolated development branch protects the production database from destructive queries while maintaining application state.

#10 about 4 min

Practical use cases for unified transactional and analytical databases

Blending operational sub-millisecond latency with lakehouse context accelerates AI agent memory, reverse ETL, and machine learning model serving.

Matching moments

1:16 min

Decoupling storage and compute with open lakehouse architectures

Max Fischer Max Fischer +1 · WWC Europe 2026

3:58 min

Struggling with ungoverned data lakes and massive storage costs

Kateřina Ščavnická Kateřina Ščavnická · WWC 2025

1:21 min

Summary of decoupling analytical compute and storage

Matthias Niehoff Matthias Niehoff · WWC Europe 2026

4:32 min

Evolution of centralized data architectures and open table formats

Matthias Niehoff Matthias Niehoff · WWC 2024

5:00 min

Q&A on analytical databases and market convergence

Andrey Abramov Andrey Abramov · WWC Europe 2026

4:30 min

Introducing data management and the shift to streaming

Mary Grygleski Mary Grygleski · LIVE

More from World Congress 2026 Europe - Virtual Stage

One Does Not Simply Make Architecture Decisions Alone thumbnail
36:15
29 days ago

One Does Not Simply Make Architecture Decisions Alone

Vladas Diržys

From Black Box to Glass Box : Bedrock AgentCore Observability thumbnail
21:15
about 1 month ago

From Black Box to Glass Box : Bedrock AgentCore Observability

Yasemin Aktürk

Leading in Rhythm: How Women Make Better Decisions with Biological Intelligence thumbnail
30:41
about 1 month ago

Leading in Rhythm: How Women Make Better Decisions with Biological Intelligence

Julia Grosse

Better Together: Leveraging Your Observability Tools as a SIEM thumbnail
39:06
about 1 month ago

Better Together: Leveraging Your Observability Tools as a SIEM

Mathias Palmersheim

ChatGPT Apps: From Chat to Checkout thumbnail
30:29
about 1 month ago

ChatGPT Apps: From Chat to Checkout

Aaron Koivunen

Interior Decorating (TypeScript Decorators) thumbnail
29:22
about 1 month ago

Interior Decorating (TypeScript Decorators)

Michael Dowden

Upcoming sessions on this topic

Open session

World Congress 2026 North America

Databases in the Agent Era

Monica Sarbu

Founder and CEO of xata.io

Monica Sarbu
Open session

World Congress 2026 North America

You Can’t Re-Run Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan
Open session

World Congress 2026 North America

AI Agents are Only as Smart as their Context: Building a Real-Time Context Engine at Intuit

Bharat Patel

Lead Software Engineer at Intuit

Bharat Patel
Open session

World Congress 2026 North America

No Single Model to Rule Them All: Building Resilient AI Agents Across Open & Closed LLMs

Emmanuel Acheampong

Senior Manager Developer Relations at Crusoe AI

Emmanuel Acheampong
Open session

World Congress 2026 North America

Agents That Own Their Inference: Building Production AI Agents on Dedicated GPUs

Duan Lightfoot

Sr. AI Engineer, Akamai

Duan Lightfoot
Open session

World Congress 2026 North America

Closing the Visibility Gap: Lessons from Safety Critical Agentic Systems

Vivek Pandit

Principal Engineer at Cadence

Vivek Pandit

Related videos

TiDB, One Layer at a Time: How Distributed SQL Became an Agentic AI Backbone thumbnail
27:27
WWC Europe 2026 • about 1 month ago

TiDB, One Layer at a Time: How Distributed SQL Became an Agentic AI Backbone

Daniël van Eeden, Mattias Jonsson

Analytics in the Age of Agentic AI: A tour of ClickHouse and Langfuse thumbnail
23:38
WWC Europe 2026 • about 1 month ago

Analytics in the Age of Agentic AI: A tour of ClickHouse and Langfuse

Hellmar Becker

OLAP for AI Applications and why you should care thumbnail
30:06
WWC Europe 2026 • about 1 month ago

OLAP for AI Applications and why you should care

Andrey Abramov

3 Ways to Rebuild the Data Stack for Agents thumbnail
28:02
WWC Europe 2026 • about 1 month ago

3 Ways to Rebuild the Data Stack for Agents

Jordan Tigani

Modern Data Architectures need Software Engineering thumbnail
29:25
WWC 2024 • almost 2 years ago

Modern Data Architectures need Software Engineering

Matthias Niehoff

Swapping a Data Warehouse at Runtime: Zero-Downtime Migration Without Changing a Single Client thumbnail
30:28
WWC Europe 2026 • about 1 month ago

Swapping a Data Warehouse at Runtime: Zero-Downtime Migration Without Changing a Single Client

Max Fischer, Michael O'Toole

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.