Episode
Data Agents with Shreya Shankar - Weaviate Podcast #135!
- Podcast
- Weaviate Podcast
- Published
- Apr 6, 2026
- Duration seconds
- 3443
- Processing state
not_requested
Actions
POST https://stenobird.com/v1/public/podcasts/weaviate-podcast-6288219/episodes/data-agents-with-shreya-shankar-weaviate-podcast-135/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/weaviate-podcast-6288219/data-agents-with-shreya-shankar-weaviate-podcast-135.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
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, with implementations ranging from per-row LLM calls to synthesized code. Shreya then presents DocETL, a declarative system for processing unstructured data that uses LLM agents to propose query rewrite strategies like chunking, splitting, and map-then-reduce decompositions, optimizing for both accuracy and cost on long documents. This leads into a broader discussion of declarative versus imperative agent design, the tradeoff between letting agents write arbitrary Python and constraining them within frameworks that handle optimization and caching. The conversation also explores tribal knowledge, s…