Andy Pavlo: AI agents could drive 10-100x database queries, LLMs hit 85% of tuning quality
mattturck · x · 2026-10-08
On the MAD Podcast, Andy Pavlo (VP of Database Research, ClickHouse) joins Matt Turck for a 1h17m conversation.
- AI agents could drive a 10-100x increase in database queries, reshaping database architecture.
- Agents need sandboxed branches and permissions to avoid destroying production data.
- LLM-based tuning reaches roughly 85% of database-tuning quality in about 15 minutes.
- The discussion traces the shift from the vector-DB/RAG era to the agent era, including text-to-SQL workflows.
Related event: Andy Pavlo on How AI Agents Will Reshape Databases(3 posts)→
More from coding & agent
- Dev releases free 'AI Software Factory' ebook on agentic SDLC — Pavan_Belagatti · 2026-10-09
- Infisical Launches Agent Vault to Give AI Coding Agents API Access Without Real Credentials — ycombinator · 2026-10-09
- Forbes debuts Agentic 20 list spotlighting AI agents doing real-world work — annatonger · 2026-10-09
- Dev ships MCP server that lets Claude Code publish and share its tools — Zalaso · 2026-10-09
- No coding background: he shipped a Steam game in 9 months with Claude Code — Tommyruin · 2026-10-09
- Agent Plasticity: top-performing agents aren't the most efficient learners — RulinShao · 2026-10-09