Why Agentic AI Architecture Needs a Database, Not Just a Vector Store
Agentic AI architecture is the system design that lets an AI agent perceive context, reason over it, call tools, maintain memory, and take actions across multiple steps. It spans the model, the orchestration layer, and the data infrastructure that makes an agent’s work durable rather than disposable. Most teams get the model and framework right […]
The Complete Agent State Stack: Memory, Files, and Serverless Database Persistence for AI Apps
A serverless database is a fully-managed database that automatically scales compute and storage with demand, requires no server provisioning or capacity planning, and bills only for actual usage, including scaling to zero when idle. The provider handles infrastructure; you handle data. That definition covers the category. It doesn’t cover the problem most teams actually face […]
Migrating Real-Time Data into TiDB with Debezium CDC
Moving data into a new database is rarely a one-shot copy. Migrating off a legacy system, adopting a distributed SQL database, carrying out a heterogeneous database migration, or standing up an analytical replica all share the same challenge. You have to move a large, already-populated dataset and keep it continuously in sync until you are […]
Vector Search Meets Distributed SQL: Why Agentic AI Does Not Need Another Database
Key Takeaways Add a vector database to the existing stack. Sync it. Maintain it. Debug it when it drifts. Teams building agentic applications have largely accepted that sequence as the price of admission for working with embeddings, and the fourth step is the one worth pausing on. Drift is not an incidental bug waiting to […]
The Agent Context Plane: How One Cluster Fixed the $50K Agent Bug
Real-time data has been the promise of the analytics stack for a decade. Dashboards refresh, pipelines run, and a human reads the result. That model holds right up until you ask an agent to act on the data instead of look at it. At TiDB SCaiLE Europe 2026 in Stockholm, Bernard Kavanagh, Solutions Architect at […]
Why Agent Memory Needs a Database That Can Write Back
I’ve spent the last year helping enterprise teams put AI agents into real workflows: Fraud detection, infrastructure monitoring, customer intelligence. The conversations follow a predictable pattern. The first question is always about the model. Which LLM? Which orchestrator? The second question, about six weeks after go-live, is always about the data. Why is the agent […]
ACID at Scale: Where ORMs and MySQL Disagree
If you have ever watched an ORM-heavy application meet a sharded MySQL backend, you know the moment I mean. The code looks right. The tests pass. Then production traffic arrives, and you start seeing the impossible: An order without its line items, a user whose profile says one thing and whose billing record says another, […]
From One Week to 22 Minutes: How Bolt Migrated MySQL to TiDB
When a table crosses one terabyte, MySQL does not fail. It just starts charging for everything. A single index change takes over a week, blocks every other change queued behind it on the cluster, and demands a full shadow copy of the table just to run. At Bolt, whose ride-hailing, micromobility, delivery, and car rental […]
Novita Artifact Hosting + TiDB: Deploying AI-Generated Apps With One SDK Call
AI coding agents such as Cursor, Claude Code, and Devin can now produce a working application from a single prompt. However, most of this code still never reaches production. The blocker is rarely code quality. It is deployment. This blog explains how Novita Artifact Hosting turns an agent’s sandbox output into a live application, and […]
TiDB Cloud Cross-Region PITR: Disaster Recovery Without a Second Production Stack
For mission-critical TiDB Cloud Dedicated customers, high availability cannot stop at the region boundary. Single-region HA protects against node failures, availability-zone incidents, and localized infrastructure problems. When an entire cloud region becomes unavailable, customers need a verified recovery point in another region, a predictable restore path, and a cost model that does not require running a second […]
HTAP Was Right. AI Agents Are Proving Why.
When Databricks introduced LTAP (Lake Transactional and Analytical Processing) at this year’s Data + AI Summit, it sparked an important conversation about the future of enterprise data platforms. The announcement deserves attention because it recognizes a fundamental shift: modern AI applications can no longer treat transactional and analytical data as separate worlds. We agree. Where […]
The Infrastructure You Choose Is the Company You Become
Believing in Growth: A Hard Question From a Distributed Systems Veteran A few years ago, I was talking with the chief architect of a very well-known global company that offers a home sharing marketplace. He opened with a genuinely tough question. “Siddon, I have spent decades building distributed systems. Google Bigtable, for one. I have […]