WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 9, 2026 • Session details

Building Sovereign AI: Lessons from Deploying Secure RAG Systems using Confidential Computing

Isha Salania

How do you deploy generative AI under strict compliance laws? Learn to architect secure, truly sovereign RAG pipelines using confidential computing to protect data in use.

Pause
Mute Enter Fullscreen
#1 about 3 min

Requirements for deploying secure AI systems in public sectors

Overcoming sensitive data and compliance constraints requires shifting from promising prototypes to robust production platforms.

#2 about 3 min

Current state of multi-agent systems and token limitations

Decoupling agents and utilizing orchestration layers helps circumvent inherent token limitations in complex data networks.

#3 about 2 min

Accessing frontier models through the Microsoft Foundry platform

Utilizing a centralized platform delivers direct access to thousands of leading open-source and proprietary foundation models.

#4 about 4 min

Mitigating misinformation and economic manipulation at machine scale

The rapid evolution of automated actions necessitates sovereign boundaries to prevent unchecked policy or economic exploits.

#5 about 2 min

Defining digital sovereignty and a four-part solution framework

Ensuring regulatory compliance requires utilizing local execution, secure enclaves, national cloud partnerships, and highly portable application code.

#6 about 5 min

Securing data in use with confidential cloud computing

Trusted execution environments and confidential GPUs isolate sensitive retrieval-augmented generation pipelines from infrastructure provider access constraints.

#7 about 2 min

Partnering with national providers for sovereign private clouds

Deploying models via local data center partners ensures strict structural compliance while retaining crucial auto-scaling cloud benefits.

#8 about 4 min

Running offline artificial intelligence models using Foundry Local

Leveraging an open-source development kit enables offline execution across diverse hardware environments without recurring token expenditures.

#9 about 5 min

Building portable AI applications to survive changing environments

Abstracting agent structures from vendor dependencies streamlines immediate transitions between cloud processing and isolated local hardware.

#10 about 5 min

Architectural checklist for reliable and secure agent deployment

Ensuring resilient production systems involves implementing model gateways, assigning agent identities, integrating open telemetry, and rehearsing failovers.

#11 about 3 min

Recapping the four tiers of AI data sovereignty

Balancing isolation and scalability requires correctly matching workloads against confidential, private, disconnected, or highly portable infrastructure tiers.

#12 about 2 min

Accessing open-source repositories and agent framework development resources

Evaluating provided reference materials unlocks practical engineering frameworks for building independent local fallbacks into existing automation architectures.

Matching moments

2:00 min

Reviewing key architectural decisions for federated AI computing

Jeremy Murray Jeremy Murray · World Congress 2026 Europe

1:33 min

Designing modular AI architectures for data sovereignty

Markus Hacker Markus Hacker +1 · World Congress 2025

2:09 min

Securing AI agents against internal and external threat vectors

Julia Kordick Julia Kordick · World Congress 2026 Europe

2:56 min

Implementing AI governance and adoption strategies

Olga Woschitz Olga Woschitz +1 · Europe 2026 Virtual

1:40 min

Addressing data sovereignty and compliance blind spots within AI

Sebastian Kister Sebastian Kister · World Congress 2026 Europe

2:43 min

Best practices for implementing reliable AI agent frameworks

Marcel Scherenberg Marcel Scherenberg · World Congress 2025

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

Upcoming sessions on this topic

Open session

World Congress 2026 North America

September 24, 2026 · 11:40–12:10

Stage 2

The Private AI Platform: Why Agentic Apps Need a Private Application Platform

Oren Penso

Global field CTO, Tanzu division, Broadcom

Oren Penso
Open session

World Congress 2026 North America

September 24, 2026 · 17:30–18:00

Stage 5

Securing AI Agent Infrastructure: Identity, Attestation, and Trust at Scale

Abdel Fane

Founder of OpenA2A

Abdel Fane
Open session

World Congress 2026 North America

September 24, 2026 · 14:10–14:40

Stage 5

Edge AI: Running Agentic Intelligence Where Internet Can't Reach

Nitin Eusebius

AWS - Principal Solutions Architect

Nitin Eusebius
Open session

World Congress 2026 North America

September 24, 2026 · 11:00–11:30

Stage 5

The Missing Infrastructure for AI Agents

Chris Waterson

CTO of Guild.ai

Chris Waterson
Open session

World Congress 2026 North America

September 24, 2026 · 14:50–15:20

Stage 7

When Agents Became Users: Rearchitecting Identity and Permissions for AI at Scale

Yoav Gal

Product Lead

Yoav Gal
Open session

World Congress 2026 North America

September 24, 2026 · 11:00–11:30

Stage 7

Responsible AI Architecture with Zero Trust Agents

Ashok Prakash

Staff ML Engineer at Apple

Ashok Prakash

Related videos

Building, securing and governing AI infrastructure in the Era of Agentic AI thumbnail
27:13
World Congress 2026 Europe • 3 months ago

Building, securing and governing AI infrastructure in the Era of Agentic AI

Rob Nertney

Azure AI Foundry for Developers: Open Tools, Scalable Agents, Real Impact thumbnail
23:33
World Congress 2025 • about 1 year ago

Azure AI Foundry for Developers: Open Tools, Scalable Agents, Real Impact

Oliver Will

The Private AI Platform: Why Agentic Apps Need a Private Application Platform thumbnail
29:02
World Congress 2026 Europe • 3 months ago

The Private AI Platform: Why Agentic Apps Need a Private Application Platform

Oren Penso

Running AI at Scale: The Secret Ingredients thumbnail
30:04
World Congress 2026 Europe • 3 months ago

Running AI at Scale: The Secret Ingredients

Boris Hecker, Max Tschochohei, Peter Kürpick, Tomislav Tipurić

Bringing AI Everywhere thumbnail
26:25
World Congress 2024 • about 2 years ago

Bringing AI Everywhere

Stephan Gillich

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

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.