Leads developer relations for TabPFN, a foundation model for tabular data.
// 01 / Bio
Tuana Çelik leads developer relations at Prior Labs, the team behind TabPFN, a foundation model for tabular data. Before that, she helped grow the developer communities around Haystack at deepset and around LlamaIndex, creating tutorials, talks and open-source content on LLM apps, RAG and agents. She enjoys making complex ML ideas easy for developers to build with, and speaks regularly at conferences and meetups about AI engineering and foundation models for structured data.
// 02 / The session
Building predictive agents with tabular foundation models
Abstract
Tabular foundation models (TFMs) such as TabPFN are a newer family of foundation models trained specifically on structured, tabular data. They make grounded predictions on data they haven’t seen, which makes them a good fit for agents that need to make predictions too.
Tuana Çelik explains how TFMs work under the hood and what they add to agentic applications. Basic Python reading skills and a general sense of how LLMs or classic ML models work will help.
What you’ll learn
How TabPFN and tabular foundation models work
Grounded predictions on unseen data
Where TFMs fit in an agent
Skills you’ll practice
// 03 / For attendees
Keep learning
Go deeper on what this session covers.
AI DEV · BY DEEPLEARNING.AI
Join us at AI Dev
Meet the engineers shipping AI to production, and leave ready to do it yourself.