WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2024 • Aug 22, 2024 • Session details

Lessons Learned Building a GenAI Powered App

Mete Atamel

What happens when you replace deterministic APIs with unpredictable LLMs? Discover the defensive engineering tactics needed to tame generative AI and build reliable, production-ready workflows.

Pause
Mute Enter Fullscreen
#1 about 5 min

Evolving a static app into a generative AI application

How limitations in a rigid trivia app motivated the integration of generative AI.

#2 about 5 min

Demonstrating a real-time generative AI quiz application

A live demonstration of generating custom trivia topics using different language models.

#3 about 2 min

Architecture of a multi-platform generative AI app

Designing a system utilizing Flutter for the frontend, Cloud Run for hosting, and Firestore for storage.

#4 about 2 min

Experimenting with generative models in Vertex AI

Using the prompt gallery to test multiple models and easily extract deployment code.

#5 about 2 min

Writing effective prompts for quiz data generation

How providing clear expectations and formatting constraints yields reliable trivia datasets.

#6 about 1 min

Implementing image generation using different Imagen versions

Transitioning across models to produce relevant quiz imagery through simplified API parameters.

#7 about 4 min

Handling inconsistent and non-deterministic LLM outputs

Preparing backend logic to manage shifting output responses despite identical configurations.

#8 about 2 min

Deciding if large language models are actually necessary

Exploring traditional solutions like fuzzy string matching before defaulting to AI implementations.

#9 about 2 min

Best practices for versioning and managing prompts

Why starting with simple instructions and treating prompts as versioned code prevents regressions.

#10 about 2 min

Defensive coding techniques for unpredictable LLM responses

Implementing retry and validation layers to handle malformed structures or empty responses.

#11 about 1 min

Pinning model versions for stable application behavior

Preventing unexpected breakages by linking system integrations to exact iteration subsets.

#12 about 2 min

Unifying backend integrations with the LangChain framework

Streamlining multiple disparate model libraries into a single integration toolchain.

#13 about 1 min

Applying software engineering principles to optimize LLMs

Reducing latency and usage costs through parallel calls, batched requests, and caching.

#14 about 2 min

Validating structural integrity of generated data formats

Checking expected shapes and structures over subjective output quality to maintain reliability.

#15 about 3 min

Evaluating LLM response accuracy using secondary LLMs

Creating an automated validation loop where a secondary model grades the initial facts.

#16 about 3 min

Grounding language models with external search and custom data

Increasing output relevancy by linking model generation requests to external knowledge sources.

Matching moments

7:28 min

Accelerating product features using generative large language models

David Singleton David Singleton +1 · Coffee With Developers

1:28 min

Core challenges facing the generative AI developer ecosystem today

Prashanth Chandrasekar Prashanth Chandrasekar · WWC 2024

2:20 min

Integrating generative AI into software development workflows

Chris Wysopal Chris Wysopal · WWC 2024

5:18 min

Generating complete web applications using language model prompts

Chris Heilmann +2 · LIVE

3:13 min

Integrating state-of-the-art generative models and automated processing

Kapil Gupta Kapil Gupta · WWC 2025

3:36 min

Overview of generative AI and the presentation agenda

juarezjunior juarezjunior · WWC 2024

More from World Congress 2024

Beyond the Hype: Real-World AI Strategies Panel thumbnail
24:07
10 months ago

Beyond the Hype: Real-World AI Strategies Panel

Mike Butcher, Jürgen Müller, Katrin Lehmann, Tobias Regenfuss

Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation thumbnail
21:17
almost 2 years ago

Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation

Carl Lapierre

Coding an Immersive Copilot using Unity / .NET and Azure OpenAI! thumbnail
31:50
almost 2 years ago

Coding an Immersive Copilot using Unity / .NET and Azure OpenAI!

Zaid Zaim

Building a diverse tech company: The power of Diversity, Equity, Inclusion, and Belonging thumbnail
29:43
almost 2 years ago

Building a diverse tech company: The power of Diversity, Equity, Inclusion, and Belonging

Sue Quackenbush

Dapr in Practice thumbnail
24:08
almost 2 years ago

Dapr in Practice

marcklefter

Minimising the Carbon Footprint of Workloads thumbnail
27:46
almost 2 years ago

Minimising the Carbon Footprint of Workloads

Michael Mueller

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

Building Stuff with GenAI - The Open Minded Workshop beyond OpenAI

Andreas Erben

CTO for Applied AI and Metaverse at daenet

Andreas Erben
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

Who Tests the AI? Building Trustworthy AI Systems at Enterprise Scale

Him Raj Singh

PayPal, Manager, Software Engineer

Him Raj Singh
Open session

World Congress 2026 North America

Fast, Cheap, and Accurate: Optimizing LLM Inference with vLLM and Quantization

Legare Kerrison, Cedric Clyburn

Legare Kerrison
Cedric Clyburn
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

Related videos

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

Make it simple, using generative AI to accelerate learning thumbnail
26:54
WWC 2024 • almost 2 years ago

Make it simple, using generative AI to accelerate learning

Duan Lightfoot

Bringing the power of AI to your application. thumbnail
32:26
WWC 2024 • almost 2 years ago

Bringing the power of AI to your application.

Krzysztof Cieślak

Creating Industry ready solutions with LLM Models thumbnail
58:00
LIVE • about 2 years ago

Creating Industry ready solutions with LLM Models

Vijay Krishan Gupta, Gauravdeep Singh Lotey

AI & Ethics thumbnail
28:27
WWC 2025 • 12 months ago

AI & Ethics

PJ Hagerty

Three years of putting LLMs into Software - Lessons learned thumbnail
26:30
WWC 2025 • 12 months ago

Three years of putting LLMs into Software - Lessons learned

Simon A.T. Jiménez

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.