Building Robust AI Systems with Battle-tested Frameworks

Deploying Large Language Models (LLMs) in production brings a host of challenges well beyond prompt engineering. Once they're live, even the smallest oversight—like a malformed API call or unexpected user input—can cause failures you never saw coming. In this talk, Vaibhav Gupta will share proven strategies and practical tooling to keep LLMs robust in real-world environments. You'll learn about structured prompting, dynamic routing with fallback handlers, and data-driven guardrails—all aimed at catching errors before they break your application.

You'll also hear why the naïve use of JSON can reduce a model's accuracy, and discover when it's wise to push back on standard serialization in favor of more flexible output formats. Whether you're processing 100+ page bank statements, analyzing user queries, or summarizing critical healthcare data, you'll not only understand how to prevent LLMs from failing but also how to design AI-driven solutions that scale gracefully alongside evolving user needs.

”1202 ALARM! 1202 ALARM!” These words from Buzz Aldrin during Apollo 11’s lunar descent weren’t a crisis announcement - they were proof that Margaret Hamilton’s resilient software design worked exactly as intended. When faced with an overflow of data, the Apollo Guidance Computer prioritized critical tasks and kept going, ultimately landing humans on the moon with just seconds of fuel remaining.

Today’s data pipelines face similar challenges: complex systems, distributed dependencies, and high-stakes outcomes where failure is inevitable. As data workflows evolve from monolithic ETL jobs into distributed microservices, they demand the same resilience patterns that revolutionized application development. This talk explores how the lessons from Apollo - from Hamilton’s priority scheduling to NASA’s rigorous engineering mindset - directly inform modern data engineering practices and are embodied in Prefect 3.0’s transactional orchestration.

Building an application on the cloud doesn't have to suck. Even if it uses GPUs and foundation models! In this talk, I'll present Modal, the serverless Python infrastructure you didn't know you always wanted.