The Data Exchange with Ben Lorica Is Your Database Ready for an Army of AI Agents?
11 snips
Nov 6, 2025 Mike Freedman and Ajay Kulkarni, co-founders of Tiger Data, discuss their innovative creation, Agentic Postgres, a database tailored for AI agents. They explain how traditional Postgres struggles with search and scalability when used by agents and introduce concepts like Fluid Storage for instant database forks. The conversation covers the importance of developer-friendly features and the unique capabilities of their MCP server, which enhances model training while ensuring security. They also touch on using Postgres for unstructured data and the future of database tooling.
AI Snips
Chapters
Transcript
Episode notes
Agents Need Different Database Ergonomics
- Agents operate differently than humans and require rethought database ergonomics rather than identical human-focused tooling.
- Evolving Postgres to serve agents preserves operational simplicity while adding agent-specific features like search and forkability.
Design Storage For Safe Agent Experimentation
- Rethink storage and add features like fast zero-copy forks, hybrid search, and improved vector scaling for agent workloads.
- Provide sandboxing so agents can experiment without risking production data or budget blowouts.
Instant Forks Unlock Parallel Agent Workflows
- Fast block-storage snapshots and zero-copy forks let you create isolated, production-scale forks in ~500ms.
- Forks are copy-on-write so multiple agents can test in parallel while paying only for diffs.