Blog
View all
ai
|Scale & Resilience
Durable Execution with DBOS and CockroachDB
Modern AI applications are no longer single-shot inference calls. They are long-running agents that plan, act, observe, and retry across time.
Amine El Kouhen, Ph.D.
July 8, 2026
AI
ai
How CockroachDB and IBM LinuxONE Rockhopper 5 Power Resilient AI Infrastructure
Why does AI require a new approach to infrastructure?
Kyle Basile
July 7, 2026
RoachFest
RoachFest London 2026 Recap: An Astronaut, AI Agents, Amazingness
RoachFest London 2026 has been and gone, and I'm still buzzing.
Rob Reid
July 2, 2026
ai
Why Agent Loops Fail in Production (and the Database Patterns That Fix Them)
Agent loops fail in production for reasons that have little to do with the model, and everything to do with what happens to their state between iterations.
Quentin Packard
July 1, 2026
ai
PostgreSQL-Compatible Databases for AI at Scale: What to Evaluate from Day One
The database you choose at the start of an AI project is the one you'll be living with, or paying to escape, for years.
David Weiss
June 29, 2026
The Thundering Herd Problem in Agentic AI: Why Traditional Fixes Fall Short
The thundering herd of the past was externally triggered.
Quentin Packard
June 19, 2026
Agentic AI Architecture: How CockroachDB Supports Memory, Context, and Control
What happens when you connect a fleet of autonomous AI agents to your enterprise data stack? You quickly discover...
Alejandro Infanzon
June 11, 2026
ai
Business
The Bill Arrives: How to Manage Agentic AI Costs at Scale
What do the Uber budget blowout, a 24x token multiplier, and context teach us about building a real business case for AI Agents in production?
Quentin Packard
June 10, 2026
RoachFest
RoachFest London 2026 Preview: AI Agents and an Astronaut Walk Into a Database Conference
Cockroach Labs has been hosting our annual database conference since 2022, and I'm honored to be MCing RoachFest London for the third year running.
Rob Reid
June 9, 2026
ai
What Breaks When Agentic AI Reaches Production?
Most enterprise AI teams have built an agent that was impressive; far fewer have shipped one without a production incident that made someone question the whole program.
Quentin Packard
June 4, 2026
Get started for free
