WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2025 • Aug 20, 2025 • Session details

Three years of putting LLMs into Software - Lessons learned

Simon A.T. Jiménez

Models do not think, they are simply high-dimensional pattern matchers. Learn how to treat LLMs as an unreliable API tier using robust error handling, strict constraints, and secure architectures.

Pause
Mute Enter Fullscreen
#1 about 1 min

Introduction to practical lessons for AI software integration

Applying fundamental lessons from early AI adoption helps streamline language model integration into existing software architectures.

#2 about 3 min

Recognizing the inherent unreliability and illusion of model reasoning

Recognizing that language models mimic human reasoning through text prediction rather than cognitive thought prevents misplaced reliance.

#3 about 3 min

Handling stateless language model APIs and context window limits

Managing stateless API interactions by carefully designing context windows mitigates token limits and long-term performance degradation.

#4 about 2 min

Configuring language model parameters for deterministic application outputs

Configuring parameters like temperature and penalties enables deterministic text outputs that can be reliably unit tested.

#5 about 2 min

Visualizing token generation dynamics inside multidimensional vector spaces

Visualizing how models navigate multidimensional token vector spaces clarifies the algorithmic reality behind generated text.

#6 about 3 min

Emerging instruct model capabilities from massive internet training datasets

Leveraging the strict logic of modern instruct models trained on immense datasets enables the creation of robust custom system prompts.

#7 about 2 min

Treating language models as advanced textual pattern matching engines

Treating language models as advanced pattern matchers rather than intelligent entities improves the effectiveness of problem-solving prompts.

#8 about 3 min

Utilizing available language models as predictable text calculation APIs

Treating multiple interchangeable language model endpoints as standard text calculation APIs builds redundancy and simplifies continuous application delivery.

#9 about 3 min

The limitations of mathematical calculations and explainable artificial intelligence

Avoiding assumptions about a model's arithmetic or self-awareness prevents hallucinations and uncovers the deceptive nature of explainable AI.

#10 about 3 min

Integrating audio models, text rewriting, and reliable JSON formatting

Utilizing multimodal capabilities with strict instructional prompting guarantees specific output structures like valid JSON for downstream processing.

#11 about 3 min

Navigating data privacy constraints and commercial API usage rights

Evaluating self-hosted open-source models versus paid commercial APIs resolves underlying issues regarding corporate data privacy.

#12 about 2 min

Implementing EU AI Act compliance via human-in-the-loop workflows

Establishing human-in-the-loop workflows ensures compliance with the European AI Act while legally transferring final accountability to the end user.

#13 about 2 min

Mitigating prompt injection vulnerabilities in external AI tool integrations

Restricting external data permissions neutralizes extreme security vulnerabilities like automated prompt injections found in active agent protocols.

Matching moments

5:30 min

Building components of a real-world LLM lifecycle

Maxim Salnikov Maxim Salnikov · LIVE

4:29 min

Designing AI applications defensively for inevitable failures

Krzysztof Cieślak Krzysztof Cieślak · WWC Europe 2026

1:59 min

Building culturally aware LLMs for global audiences

Werner Vogels Werner Vogels +1 · WWC Europe 2026

2:21 min

Transitioning from AI co-pilots to AI-native products

Jordan Tigani Jordan Tigani · WWC Europe 2026

3:26 min

Introducing LLMs as judges for automated testing

Sebastian Messingfeld Sebastian Messingfeld · WWC Europe 2026

2:54 min

Establishing context and limitations for artificial intelligence platforms

Anna Fritsch-Weninger · LIVE

More from World Congress 2025

GenAI Security: Navigating the Unseen Iceberg thumbnail
24:33
10 months ago

GenAI Security: Navigating the Unseen Iceberg

Maish Saidel-Keesing

Behind the Code: How Women Are Powering the Future of AI thumbnail
30:28
12 months ago

Behind the Code: How Women Are Powering the Future of AI

Alexandra Wudel, Laura Moritz, Madalina Florean

The AI Hype Filter: What’s Real, What’s Investable, What’s Noise? thumbnail
28:12
12 months ago

The AI Hype Filter: What’s Real, What’s Investable, What’s Noise?

Justus Lumpe, Konstantin Vinogradov, Nils Eiteneyer, Stephan Wirris

AI in Leadership: How Technology is Reshaping Executive Roles thumbnail
28:19
12 months ago

AI in Leadership: How Technology is Reshaping Executive Roles

Bernd Datler, Jasmin Kaiser, Jeff Hausmann, Sonja Alvarez

The AI-Ready Stack: Rethinking the Engineering Org of the Future thumbnail
28:09
12 months ago

The AI-Ready Stack: Rethinking the Engineering Org of the Future

Alex Laubscher, Jan Oberhauser, Keno Dreßel, Mirko Novakovic

AI Sovereignty: What Does It Take? thumbnail
29:13
12 months ago

AI Sovereignty: What Does It Take?

Boris Hecker, Clemens Wasner, Robin Hermann, Sonja Alvarez

Upcoming sessions on this topic

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

Reinventing Testing Practices in the AI Era

Eric Deandrea

Java Champion & Senior Principal Software Engineer, IBM

Eric Deandrea
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

The Things Your AI Isn't Telling You

Desmond Lamptey

Lead Software Engineer @ Capital One

Desmond Lamptey
Open session

World Congress 2026 North America

Understanding LLM Architectures: Inside the Design of Modern Models

Jofia Jose Prakash

Enterprise AI Architect at American Chemical Society

Jofia Jose Prakash
Open session

World Congress 2026 North America

Developer Liability in the AI Agent Era: Building Responsibly

Alla Barbalat

Freelancer Trade Show Spokesmodel and Tech Event Host

Alla Barbalat

Related videos

You are not an AI developer thumbnail
23:55
WWC 2024 • almost 2 years ago

You are not an AI developer

Zan Markan

How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge thumbnail
42:26
Coffee With Developers • over 1 year ago

How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge

Meta Atamel, Guillaume Laforge

Using LLMs in your Product thumbnail
31:12
WWC 2024 • almost 2 years ago

Using LLMs in your Product

Daniel Töws

Prompt Injection, Poisoning & More: The Dark Side of LLMs thumbnail
23:24
WWC 2025 • 12 months ago

Prompt Injection, Poisoning & More: The Dark Side of LLMs

Keno Dreßel

How AI Models Get Smarter thumbnail
35:16
WWC 2025 • about 1 year ago

How AI Models Get Smarter

Ankit Patel

The Limits of LLMs in Real-World Applications thumbnail
31:07
WWC Europe 2026 • about 1 month ago

The Limits of LLMs in Real-World Applications

Deivids Vilkinsons, Guillaume Esnou, Laura Moritz, Mariam Hakobyan

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.