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

REST In Peace: Why LLMs Can't CRUD

Martin Sakowski , Martin Karrer

Why do AI agents fail at simple CRUD operations? Traditional REST APIs force probabilistic LLMs into rigid schemas. Discover how intent-based APIs finally bridge this machine communication gap.

Pause
Mute Enter Fullscreen
#1 about 3 min

Evaluating AI agent performance on daily assistance tasks

Benchmarking pure AI assistants against standard API integrations reveals a major gap in task execution reliability.

#2 about 3 min

Why standard REST APIs fail autonomous AI agents

Traditional HTTP-based patterns rely on human developer intuition and do not scale to computational agentic workflows.

#3 about 3 min

Orchestration explosion and error compounding in workflows

Generating and managing multi-step API sequences creates cascading failures due to probabilistic model execution limits.

#4 about 3 min

API parsing inefficiencies and schema rigidity limits

Exposing large static resource objects forces models to consume excessive tokens and hallucinate exact schema matches.

#5 about 5 min

Navigating unhelpful errors and implicit API documentation

Status codes block automated error recovery while implicit design rules prevent agents from correctly deducing field semantics.

#6 about 6 min

Resolving agent challenges with intent-based API architectures

Abstracting technical implementations through outcome-focused interfaces eliminates orchestration overhead and pushes business logic handling to the system.

#7 about 2 min

Building an intent layer over legacy REST APIs

Adopting a backend-for-frontend pattern allows standardized intent handling without requiring a complete rewrite of traditional systems.

#8 about 2 min

Securing agent access through scoped valet keys

Authenticating agent behaviors through time-boxed and scoped operational limits prevents unauthorized execution across the larger resource surface.

#9 about 3 min

Tracking task success metrics and optimizing agent environments

Measuring operation completion rather than individual status codes yields accurate diagnostics for token cost and latency reduction.

#10 about 4 min

The paradigm shift toward intent-based system communication

Adapting model context protocols to wrap backend intent paves the way for scalable and resilient autonomous environments.

#11 about 3 min

Evaluating alternatives like HATEOAS and GraphQL

Analyzing HATEOAS and GraphQL reveals that theoretically sound API specifications often fail agents due to adoption gaps or query complexity.

Matching moments

3:25 min

Understanding foundational concepts of LLMs, agents, and MCPs

Perf + AI

1:48 min

Defining true agent behavior versus traditional enterprise chatbots

Dennis Zielke Dennis Zielke +1 · WWC 2025

4:50 min

Adapting legacy system architectures for agent autonomy

Dana Lawson Dana Lawson · WWC Europe 2026

2:02 min

Redefining the software architect role for AI pipelines

Ingo Eichhorst Ingo Eichhorst · WWC Europe 2026

3:23 min

Integrating intent-based code generation and agent implementation

4:56 min

Building agentic workflows using prompt engineering and language models

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17
about 1 month 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
about 1 month 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
about 1 month 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
about 1 month 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
about 1 month 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
about 1 month 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

Designing APIs That Survive AI Agents at Scale

Phani Pendurthi

Mastercard, Principal Software Engineer

Phani Pendurthi
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

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

Yoav Gal, Dor Cohen

Yoav Gal
Dor Cohen
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

MicroAgents: The Microservices of the Agentic Era

Ashish Shubham

Runs the show bussiness at ThoughtSpot

Ashish Shubham
Open session

World Congress 2026 North America

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

Abdel Fane

Founder of OpenA2A

Abdel Fane

Related videos

Building APIs for Agents vs Systems. Is MCP the answer? thumbnail
27:52
WWC Europe 2026 • about 1 month ago

Building APIs for Agents vs Systems. Is MCP the answer?

Adam Bird

Headless by Design: Building Enterprise Systems That Agents Can Actually Use thumbnail
23:52
WWC Europe 2026 • about 1 month ago

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

Dirk Gronert

When Should You Use an Agent? Architectural Trade-offs in Agentic Systems thumbnail
32:48
WWC Europe 2026 • about 1 month ago

When Should You Use an Agent? Architectural Trade-offs in Agentic Systems

Matheus Guimaraes

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

On a Secret Mission: Developing AI Agents thumbnail
29:03
WWC 2025 • 12 months ago

On a Secret Mission: Developing AI Agents

Jörg Neumann

Beyond Chatbots: How to build Agentic AI systems thumbnail
24:22
WWC 2025 • 12 months ago

Beyond Chatbots: How to build Agentic AI systems

Philipp Schmid

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.