Engineering

Key Takeaways AI coding agents are no longer a novelty. From Claude Code to Cursor’s agent mode, from GitHub Copilot Workspace to OpenAI Codex, “generate an app from a prompt” demos flood developer feeds. Each one follows the same arc: a developer types a prompt, an application appears, and the audience applauds. What those demos […]

Agentic AI did not create a new kind of database. It revealed which ones were already built for it. Across 2026 so far, a wave of large software companies have cut tens of thousands of roles and explained the cuts in nearly identical language: Too many layers of leadership, too many coordination-heavy roles, a need […]

I gave a session at Microsoft Build 2026 on agent memory with TiDB. A few people asked for the code afterward, so here’s a complete write up of the session: The same pattern as the talk, with copy-paste-ready schema and queries. You can watch the original Microsoft Build 2026 session here. Why an Agent Memory […]

Key Takeaways There is a moment using an AI agent that ruins you a little, because once you have felt it, you cannot go back. The agent remembers something from three weeks ago that you had half-forgotten you mentioned. Not in a strange way, but in a useful way. It picks up where you actually […]

Editor’s note: This post originally appeared on The New Stack and is republished with permission. The original version is available here. A few months ago, one of our users filed a bug report that stuck with me. They had built a customer-support agent on top of a RAG pipeline. A user asked whether they could return […]

Most teams shipping AI agents in 2026 hit the same wall around the same time. The prototype works. Ten users or even a thousand users mostly work. But then one user action triggers thousands of agent instances, context has to branch per agent in milliseconds, and vector lookups stack on top of transactional reads. The […]

Agentic AI changes the database problem. A single user action can trigger many agent steps. However, each agent needs state, memory, transactions, analytics, and retrieval to stay consistent under real production load. That pressure exposes the weak points in stacks built from separate OLTP databases, vector stores, warehouses, and sync pipelines. TiDB SCaiLE Europe 2026 […]

The stories sound the same in every engineering review. A team ships a working AI prototype in a week. The demo is impressive. Leadership greenlights production. Six months later, the app is still not in production. The failure rarely traces back to the model. The team did not pick the wrong LLM. They did not […]

Cloud-native databases have made it easier to ship transactional applications. Managed services, automatic failover, and elastic storage are now table stakes. The harder problems show up later: When a multi-tenant SaaS app starts hitting tail-latency spikes during compaction, when a serverless tier saturates a noisy neighbor, or when a dedicated cluster sits at 30% utilization […]

Editor’s note: This post originally appeared on The New Stack and is republished with permission. The original version is available here. When enterprises talk about artificial intelligence, the attention usually points to models: larger parameters, faster inference, cheaper tokens. But we at next-gen database maker PingCAP contend that this framing misses the most consequential change now […]

Editor’s note: This post originally appeared on The New Stack and is republished with permission. The original version is available here. In the past, we judged enterprise databases by how useful they were to people like us. We rated them on how well they helped architects create schemas, DBAs plan capacity, and analysts build queries.  We […]

Reducing P999 latency in distributed databases is one of the hardest challenges in modern OLTP systems. A handful of slow requests can cascade across services, break SLOs, and directly impact business outcomes, especially in latency-sensitive environments like trading platforms and real-time applications. This is the challenge of tail latency. As systems scale, variability compounds: queueing […]