Decoding the GenAI Revolution: Technical Shifts and Their Impact on Your Applications en

The landscape of Large Language Models (LLMs) and Generative AI (GenAI) is rapidly transforming. For developers, understanding the core technical changes driving this evolution is essential for building cutting-edge products and applications. This talk will provide an intermediate-level exploration of recent advancements in LLM and GenAI models, moving beyond the surface-level buzz to examine the key architectural innovations, scaling achievements, and training methodologies that are shaping the field.

We will then translate these technical shifts into practical implications for your work. Discover how these advancements are enabling new application possibilities, improving existing features, and influencing development workflows. Learn about the impact of longer context windows, more capable models, improved instruction following, and the emergence of multimodality. This session will equip you with actionable insights and a clearer understanding of how to leverage the power of modern GenAI in your projects.

Target Audience: This talk is designed for developers with an intermediate level of technical skill and some basic familiarity with AI/ML concepts. They are likely interested in understanding how these technologies work under the hood and, more importantly, how they can be applied in their daily work.

Key Takeaways: Attendees will gain a better understanding of the recent technical changes in LLMs and GenAI, learn about the practical implications of these changes for application development, and be inspired with new ideas for leveraging these technologies in their projects.

AI Engineering: From Prompt Architecture to Production Infrastructure en

Stop building AI demos. Start shipping AI systems that actually work.

Most developers can call an API and write a prompt. Few can build AI systems that consistently deliver production-quality results in enterprise environments. This all-day workshop teaches both.

Morning: Engineer prompts that work. Learn structural patterns and constraint systems that eliminate garbage outputs. No more prompt lottery.

Afternoon: Build production infrastructure. Use gateway architecture (PortKey) to handle multi-LLM failover, A/B testing, governance, and guardrails. The critical production concerns tutorials skip.

Walk away with: A systematic framework for reliable prompts. A production-ready AI gateway. Architecture patterns that pass compliance reviews.

Perfect for: Backend developers, solutions architects, and technical leads shipping AI products in enterprise environments.

Bring: Laptop with ChatGPT API or Claude console account. We focus on engineering that makes AI work when it matters.

Core Learning Modules:

🔧 **Multi-LLM Integration**
- Connect and manage multiple AI providers (OpenAI, Anthropic, Cohere, local models)
- Implement intelligent fallback strategies and load balancing
- Handle rate limits and cost optimization across providers

🧪 **Production A/B Testing**
- Design and deploy model comparison experiments
- Implement traffic splitting for performance evaluation
- Measure and analyze AI system effectiveness in real-time

🛡️ **AI Governance & Compliance**
- Establish organizational AI policies and approval workflows
- Implement audit trails and usage monitoring
- Design cost control and budget management systems

⚡ **Guardrails That Actually Work**
- Build content filtering and safety mechanisms
- Implement input/output validation and sanitization
- Create custom business logic guards and compliance checks

**Who Should Attend:**
- Backend developers moving into AI integration
- Solutions architects designing AI-powered systems
- DevOps engineers responsible for AI infrastructure
- Technical leads planning enterprise AI adoption

**Prerequisites:**
- Basic API development experience
- Familiarity with cloud services (AWS/Azure/GCP)
- Understanding of microservices architecture
- Laptop with Docker installed

**Workshop Outcome:**
Walk away with a production-ready AI gateway configuration, implementation playbooks, and the confidence to deploy enterprise-grade AI systems that your compliance team will actually approve.

Beyond the Demo: Production AI Architecture That Actually Works en

Your AI prototype works. Your production AI system doesn't. Here's why.

Most developers can call OpenAI's API, but building AI systems that survive real enterprise environments requires a completely different architecture. This talk reveals the production patterns that separate working AI products from expensive demos.
Through live demonstrations using PortKey AI Gateway, you'll see how production AI systems actually work: multi-LLM orchestration, real-time failover, A/B testing at scale, and the governance layers that keep everything from falling apart.
You'll discover:

Why single-LLM integrations fail in production (and the multi-provider patterns that don't)
How Netflix-style A/B testing applies to AI model selection
The hidden governance requirements that kill AI projects in the enterprise
Real guardrails vs. the "prompt engineering" solutions that don't scale

Perfect for: Developers planning AI integrations, architects designing AI-powered products, and anyone tired of AI talks that ignore production reality.

Walk away with: Battle-tested architecture patterns, implementation blueprints, and the confidence to build AI systems that actually ship.

Demystifying Micro Frontends: A Practical Guide to Modern Web Architecture en es

Are you curious about transforming your web development approach? Join us for an engaging exploration of micro frontends, an innovative architectural pattern that promises greater scalability, faster development cycles, and more satisfied teams.

During this talk, we'll discuss:

Why Micro Frontends? Discover how they simplify managing complex web applications by breaking down monolithic structures.
Real-world Pros and Cons: Get a balanced view of the benefits and challenges of adopting micro frontends.
Architectural Insights: Learn about different composition techniques, from server-side to client-side.
Best Practices: Gain practical tips for a smooth transition to micro frontends.
Is it Right for You? Evaluate whether micro frontends are the perfect fit for your projects.

Whether you're an experienced developer or just starting to explore new concepts, this meetup will offer valuable insights and inspiration. Join us for an informative and interactive session on micro frontends!

Desmitificando los Micro Frontends: Una Guía Práctica para la Arquitectura Web Moderna en es

¿Estás interesado en transformar tu enfoque de desarrollo web? Únete a nosotros para una exploración fascinante de los micro frontends, un patrón arquitectónico innovador que promete mayor escalabilidad, ciclos de desarrollo más rápidos y equipos más satisfechos.

Durante esta charla, discutiremos:

¿Por qué Micro Frontends? Descubre cómo simplifican la gestión de aplicaciones web complejas desglosando estructuras monolíticas.
Pros y Contras del Mundo Real: Obtén una visión equilibrada de los beneficios y desafíos de adoptar micro frontends.
Perspectivas Arquitectónicas: Aprende sobre diferentes técnicas de composición, desde el lado del servidor hasta el lado del cliente.
Mejores Prácticas: Obtén consejos prácticos para una transición fluida a los micro frontends.
¿Es Adecuado para Ti? Evalúa si los micro frontends son la solución perfecta para tus proyectos.

Ya seas un desarrollador experimentado o recién estés comenzando a explorar nuevos conceptos, este meetup ofrecerá valiosos conocimientos e inspiración. ¡Únete a nosotros para una sesión informativa e interactiva sobre micro frontends!

Stop Fighting Your AI: Engineering Prompts That Actually Work en

Your prompts suck. Your AI outputs prove it.

Most developers treat prompt engineering like magic - throw words at the AI and hope for the best. But getting consistent, production-quality results from AI requires actual engineering principles, not creative writing.
This session reveals the systematic approach to prompt engineering that produces reliable results: using AI itself to debug your prompts, building constraint systems that prevent garbage outputs, and creating prompt architectures that scale across your entire development workflow.
You'll master:
- Why "be creative" prompts fail (and the structural patterns that don't)
- How to reverse-engineer successful prompts using AI feedback loops
- Constraint engineering that eliminates 90% of useless AI outputs
- The prompt versioning and testing strategies that actually work in production

Perfect for: Developers integrating AI into workflows, technical writers automating documentation, and anyone tired of playing prompt lottery with inconsistent results.

Live demonstrations: Real prompt debugging sessions, before/after output comparisons, and the systematic refinement process that turns vague requests into precise instructions.

Walk away with: A repeatable prompt engineering framework, debugging techniques that actually work, and the systematic approach to get AI outputs you can actually use.