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

1:38 min

The AI renaissance and agent-ready APIs

Gbadebo Bello Gbadebo Bello · Europe 2026 Virtual

1:48 min

Defining true agent behavior versus traditional enterprise chatbots

Dennis Zielke Dennis Zielke +1 · World Congress 2025

2:29 min

Key architectural takeaways for building reliable AI agents

Michał Michalczuk Michał Michalczuk · Europe 2026 Virtual

2:09 min

The evolution from LLM workflows to personal agents

Mitesh Patel Mitesh Patel +3 · World Congress 2026 North America

4:37 min

Transitioning to a hybrid human and agent workforce

Thomas Dohmke Thomas Dohmke · 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

Architecting Trusted AI: Coupling Multi-Agent Systems with dbt Semantic Store for Zero-Hallucination

  • Pushkar Mishra

    J.P. Morgan

    Senior Vice President

Open session

Teaching AI Coding Agents to Build It Right the First Time

  • Sajeetharan Sinnathurai

    Microsoft

    Principal Product Manager

Open session

Build a Zero-Cost AI Agent in Your Browser

  • Aishwarya Mathuria

    Adobe

    Computer Scientist

  • Nishant Thakur

    Adobe

    Senior Computer Scientist

Open session

Autopsy of an Autonomous Incident: When the Agent Made It Worse

  • Navin Pai

    StackGen

    Director of Engineering

Open session

Beyond File Dumps: Context Engineering for Coding Agents

  • Animesh Dutta

    Arm

    Senior Software Engineer

Open session

Java is Coming for Python’s Lunch: The Rise of JVM AI Agents

  • Frederik Pietzko

    Jetbrains

    Developer Advocate

Related videos

Building APIs for Agents vs Systems. Is MCP the answer? thumbnail
27:52
World Congress 2026 Europe • 3 months ago

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

Adam Bird

Designing APIs That Survive AI Agents at Scale thumbnail
30:39
World Congress 2026 North America • 19 days ago

Designing APIs That Survive AI Agents at Scale

Phani Pendurthi

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

When Should You Use an Agent? Architectural Trade-offs in Agentic Systems thumbnail
32:48
World Congress 2026 Europe • 3 months 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
World Congress 2026 Europe • 3 months ago

3 Ways to Rebuild the Data Stack for Agents

Jordan Tigani

On a Secret Mission: Developing AI Agents thumbnail
29:03
World Congress 2025 • about 1 year ago

On a Secret Mission: Developing AI Agents

Jörg Neumann

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.