PlanetScale on scaling databases for the AI era: agents, sharding, and graceful degradation
AI Engineer · youtube · 2026-10-07
Ben Dicken of PlanetScale argues you no longer have to choose between moving fast and staying up as AI agents multiply database traffic overnight.
- Isolation and redundancy are foundational: at scale, failures become a weekly event, so design for them.
- Scaling comes from sharding, back pressure, and decoupling — the same ideas PlanetScale uses to run databases for fast-growing AI companies like Cursor.
- Agents can safely manage infrastructure: a simple VSchema JSON file lets an agent design a Vitess sharding plan; Traffic Control sets resource budgets so agent traffic surges degrade gracefully instead of crashing.
- Database branching, deploy requests, and one-click reverts let agents change schemas without data loss.
- His takeaway: good developer experience turns out to be exactly the right primitives for AI agents.
More from coding & agent
- Dreadnode releases ScopeBench, a benchmark for agent scope adherence in offensive security — dyn___ · 2026-10-07
- Brett Adcock shows off Handoff, a computer-use agent for shopping and travel — adcock_brett · 2026-10-07
- EvalRouter adds Traces: auto-trace every agent benchmark with a few lines of code — ycombinator · 2026-10-07
- Decisions API is out; users pitch baking it into ChatGPT for real-time gameplay — flowersslop · 2026-10-07
- Feeding years of WhatsApp and Instagram data to a personal AI agent — we93 · 2026-10-07
- AgentMail launches AgentID, a 'Sign in with Google' for AI agents — ycombinator · 2026-10-07