Data Agents with Shreya Shankar - Weaviate Podcast #135!

Data Agents with Shreya Shankar - Weaviate Podcast #135!

From Weaviate Podcast by Weaviate

April 6, 2026 · 57 min

About this episode

Shreya Shankar discusses data agents and their challenges in the Weaviate Podcast.

Shreya Shankar from UC Berkeley joins the Weaviate Podcast to discuss data agents, the Data Agent Benchmark, and DocETL. The conversation opens with defining what a data agent actually is, not just text-to-SQL over a single table, but an AI system that can reason across dozens of heterogeneous databases, flat files, and knowledge repositories to answer complex organizational questions. Shreya explains why this multi-database reality makes existing benchmarks insufficient, motivating the Data Agent Benchmark where the best-performing agent achieves only 34–37% pass@1 accuracy. From there, the discussion dives into where agents fail. They don't explore data properly, they generate broken regex patterns, they struggle with different SQL dialects, and they give up when datasets get large. Interestingly, agents tend to pull data into Pandas rather than use database operators directly, likely because LLMs are more fluent in Python than in the nuances of each SQL dialect. The conversation moves into semantic operators, natural language variants of relational algebra, filter, map, join, aggregation, where predicates like "Is this a sports article?" replace handwritten regex…

People in this episode

Host: Weaviate

Guest: Shreya Shankar

Topics covered

  • data agents
  • Data Agent Benchmark
  • DocETL
  • AI systems
  • data exploration
  • SQL dialects

Keywords

  • data agents
  • benchmark
  • AI systems
  • SQL
  • Pandas
  • DocETL
  • unstructured data

Mentioned in this episode

Organizations: UC Berkeley

More episodes of Weaviate Podcast

Explore listener stats, chart rankings, contacts and more on the Weaviate Podcast podcast page.