Cockroach Labs

Why does AI require a new approach to infrastructure? AI is changing enterprise infrastructure requirements by increasing demand for continuous data availability, high concurrency, and real-time decision-making. Customers expect uninterrupted experiences, and AI-driven systems depend on continuous, reliable access to current data. Even a few minutes of downtime can result in significant financial and reputational loss.

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. That's not unique to AI, but AI changes the timeline: According to the Cockroach Labs State of AI Infrastructure 2026 report, 83% of engineering leaders believe AI-driven demand will cause their data infrastructure to fail without major upgrades within 24 months. Nearly two-thirds say their leadership teams underestimate how quickly that breaking point will arrive.

The thundering herd of the past was externally triggered. A service restores after downtime. A notification fires to a million users at once. A cache expires and everyone hits the database simultaneously. The fix is well-documented: exponential backoff with jitter, circuit breakers, staggered TTLs. These work when you can identify where the synchronized load originated. Agentic AI creates a different version of this hazard: Here, the synchronization is internally generated.

What happens when you connect a fleet of autonomous AI agents to your enterprise data stack? You quickly discover that agentic workloads do not behave like human-driven applications: Autonomous agents do not pause between clicks. They issue frequent tool calls, run tasks in parallel, retry aggressively, and expect low-latency access to current data.

Experience real-world lessons on resilience, AI, and scale Explore the future of database architecture and AI agents Connect with engineers, customers, and CockroachDB experts 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. Yes, I’m the Technical Evangelist for CockroachDB, but it’s not the contractual obligation that keeps me coming back.

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.

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. The reason is almost never the model. Agentic AI is forcing every enterprise to solve distributed systems problems, whether they realize it or not.

Organizations across fintech, healthcare, retail, gaming, SaaS, and scores more verticals are embedding AI into business-critical offerings. You name an application, and AI is powering it: agent-driven automation, real-time fraud detection, RAG-powered search and personalized recommendations, and far beyond. While the models get the attention, it's the data layer underneath that determines whether those capabilities work reliably or crumble under production load.

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?

When your AI agent makes a bad decision in production, what do you blame? The problem isn't the model. It's what the model doesn't know. Most teams go straight to the model: Wrong temperature setting, not enough examples in the prompt, the model isn't smart enough yet. That answer feels intuitive because the model is the most visible thing in the stack.