Speakers
Gediminas Sadaunykas
Senior Data Scientist
8 years of data science experience, building and deploying models in domains such as facilities management, medical information, sports, document ai.
Pydantic has become a cornerstone of AI development over the past few years, serving as a critical component in major SDKs including OpenAI, Anthropic, LangChain, and CrewAI. Through tools like Instructor (and later Structured Outputs), Pydantic has enabled the deployment of apps enhanced via LLMs in production environments. Now, PydanticAI is extending this capability to AI Agents. As AI communicates through data, Pydantic's data validation framework has become the internal language for AI systems.
Basic Python and interest in AI/LLMs
Main Concepts and some backstory behind Instructor, allowing to shape LLM outputs and build modern ai apps. (7 min)
Pydantic AI entering AI agent framework world redesigning the way we create AI agents from core pydantic principles. (7 min)
Demo on how to apply pydantic (Instructor/Pydantic AI) to analyze some pop culture literature (such as Harry Poter, currently an idea, as Eu Ai Act agent still might be very relevant). (15min)
Senior Data Scientist
8 years of data science experience, building and deploying models in domains such as facilities management, medical information, sports, document ai.