WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 10, 2026 • Session details

Your Enterprise RAG Has No Legal Basis

David Klemme , Tilman Mürle

Your general-purpose enterprise RAG chatbot is fundamentally violating GDPR. Discover how architecting purpose-scoped routing layers can rescue your AI tools and enforce legal compliance by design.

Pause
Mute Enter Fullscreen
#1 about 3 min

Introduction to building the enterprise chatbot demo

The hosts introduce the session and prepare to live-code a standard enterprise chat application.

#2 about 3 min

Scaffolding the chatbot application using Vercel AI SDK

The underlying application scaffolding uses a subagent to generate standard components via Vercel AI SDK and Tailwind.

#3 about 3 min

Enforcing quality standards using context and subagents

Knowledge graphs provide context to the agent to enforce production standards and fulfill custom quality gates.

#4 about 4 min

Selecting Anthropic models and anticipating UI styling updates

Claude Sonnet is selected for inference speed over Opus while waiting for the interface styles to compile correctly.

#5 about 2 min

Testing the retrieval application against a vendor proposal

An uploaded vendor proposal demonstrates how the generic application retrieves specific answers from the provided context.

#6 about 3 min

Why general-purpose chatbots violate GDPR purpose limitation

Standard general-purpose RAG architecture fundamentally breaches GDPR guidelines because it lacks a documented, limited legal purpose.

#7 about 3 min

Designing a purpose-scoped architecture for legal compliance

The system needs to map requests through a bot picker and an explicit legal configuration before accessing language models.

#8 about 3 min

Defining usage boundaries and legal basis for auditors

Organizations must proactively govern and document access constraints for specific personal data before execution to satisfy compliance auditors.

#9 about 5 min

Refactoring the chat interface to enforce documented use cases

Developers must integrate a frontend selection layer that enforces organizational limits on data processing and establishes explicit usage guidelines.

#10 about 5 min

Communicating constraints to users and finding compliance resources

Organizations must explicitly collect user consent and communicate limitations within the interface to maintain data accountability.

Matching moments

3:06 min

Handling compliance, logging definitions, and AI agent output

Juraci Paixão Kröhling Juraci Paixão Kröhling · World Congress 2026 Europe

5:50 min

Answering questions on compliance, architecture, and cultural adoption

Agur Jõgi Agur Jõgi · World Congress 2026 Europe

1:40 min

Addressing data sovereignty and compliance blind spots within AI

Sebastian Kister Sebastian Kister · World Congress 2026 Europe

2:43 min

Setting effective guardrails for enterprise agentic AI adoption

Julia Kordick Julia Kordick · Coffee With Developers

4:17 min

Navigating emerging AI legal frameworks and business risks

Kilian Kluge +1 · World Congress 2022

3:10 min

Balancing rapid artificial intelligence development with strict compliance regulations

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17
3 months ago

Building the Nervous System of AI - Michael Kagan (NVIDIA)

Michael Kagan, Sead Ahmetović

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote thumbnail
19:41
3 months ago

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote

Christian Heilmann

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend thumbnail
32:06
3 months ago

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

David vonThenen

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes thumbnail
35:13
3 months ago

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes

Irina Branovic

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬 thumbnail
24:23
3 months ago

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬

Jeremy Murray

Angstfreude - AI and Corporate Culture - The Thrill and the Threat thumbnail
30:26
3 months ago

Angstfreude - AI and Corporate Culture - The Thrill and the Threat

Axel Ebert, Karin Krobath

Related videos

The day the chatbot asked for sudo thumbnail
27:48
World Congress 2026 Europe • 3 months ago

The day the chatbot asked for sudo

Alex Olivier

Make it simple, using generative AI to accelerate learning thumbnail
26:54
World Congress 2024 • about 2 years ago

Make it simple, using generative AI to accelerate learning

Duan Lightfoot

From Shadow AI to Secure Intelligence: Safe AI Usage in the Enterprise thumbnail
34:52
Europe 2026 Virtual • 3 months ago

From Shadow AI to Secure Intelligence: Safe AI Usage in the Enterprise

Péter Farkas

Testing AI Agents: Automated Evaluation for Chatbots & RAG Systems thumbnail
30:34
World Congress 2026 Europe • 3 months ago

Testing AI Agents: Automated Evaluation for Chatbots & RAG Systems

Sebastian Messingfeld

Headless by Design: Building Enterprise Systems That Agents Can Actually Use thumbnail
23:52
World Congress 2026 Europe • 3 months ago

Headless by Design: Building Enterprise Systems That Agents Can Actually Use

Dirk Gronert

AI for Enterprise Developers - Dr. Damir Dobric thumbnail
32:55
Coffee With Developers • 7 months ago

AI for Enterprise Developers - Dr. Damir Dobric

Damir Dobric

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.