

AI Agents for Data Analysis with Shreya Shankar - #703
58 snips Sep 30, 2024
Shreya Shankar, a PhD student at UC Berkeley specializing in intelligent data processing, shares her insights on the innovative DocETL system. They discuss how this technology optimizes LLM-powered data pipelines, enhancing analysis of complex documents. Shreya highlights the challenges of data extraction from PDFs, the importance of human feedback in AI systems, and the need for tailored benchmarks in data processing. Real-world applications and the future of agentic systems are also examined, showcasing a visionary path in data management.
AI Snips
Chapters
Transcript
Episode notes
Shreya's Research Focus
- Shreya Shankar's PhD research focuses on data management, AI, and HCI.
- She aims to improve how humans interact with unreliable AI systems for data analysis.
Chat Interfaces and LLM Popularity
- Chat interfaces made LLMs accessible and popular, particularly through platforms like TikTok.
- This accessibility has fueled interest and development in the field.
DocETL Use Case: Police Misconduct
- The DocETL project is illustrated with a use case from UC Berkeley.
- This project involves analyzing police misconduct data from California police districts.