Agentic AI architecture requires a database, not just a vector store, according to a blog post that outlines five layers—reasoning, tools, memory, state, and guardrails—and argues that vector search a…
A new guide from an unnamed source explains that AI applications require four persistence layers—memory, files, operational state, and retrieval data—and argues that serverless databases, which scale …
TiDB SCaiLE 2026, a single-day conference hosted by PingCAP at the Computer History Museum in Mountain View, CA on October 15, 2026, will feature two tracks—AI-Native: Infinite Agents and Enterprise: …
PingCAP, the company behind the open source TiDB database, argues that open source data layers will win the AI future because AI makes application code cheap to rewrite while durable state remains cos…
At TiDB SCaiLE Europe 2026, Mattias Jonsson, Principal Software Engineer at TiDB, argued that agentic AI applications do not need a separate vector database, as distributed SQL databases like TiDB can…
A single TiDB cluster raised analytical agent confidence from 74% to roughly 93%, according to Bernard Kavanagh, Solutions Architect at TiDB, speaking at TiDB SCaiLE Europe 2026. An EV-charging platfo…
An EV-charging platform burned $50,000 in a single day of testing and projected $130,000 a month at scale due to agent loops on a warehouse, according to Bernard Kavanagh, Solutions Architect at TiDB.…
PingCAP argues that production AI agents need a database capable of controlled writes, deduplication, staleness management, and cross-type queries, not just read-optimized retrieval. The company says …
Novita Artifact Hosting now lets developers deploy AI-generated applications with a single SDK call, and adding a TiDB Cloud database requires only one parameter. The platform, which turns an AI codin…
PingCAP argues that Databricks' newly introduced LTAP architecture is not a breakthrough but a validation of the HTAP architecture that TiDB has provided for years. The company states that AI agents, …
PingCAP CEO Siddon Tang argues that choosing a database for scale is a ten-year decision that caps a company's growth potential, and that as AI agents become primary users, infrastructure choices refl…
TiDB completed a 45-day white-box security assessment by NCC Group, which found zero critical, high, or medium severity issues across 20 repositories. All eight findings were rated Low, covering defau…
A fintech engineering team built an AI agent platform using five separate data systems, leading to consistency bugs that caused a double-spend under load. The author argues that fintech teams operatio…
PingCAP's research team introduced TINE, a system that binds every AI agent iteration to a Git commit, a TiDB branch, and a sandbox runtime to solve schema drift, irreproducible state, and rollback ga…
A wave of large software companies in 2026 are cutting tens of thousands of roles and restructuring, driven by the need to consolidate data systems for AI agents. Conway's Law is operating in reverse:…
TiDB has introduced a unified database approach for AI agent memory that stores text, vectors, and metadata in a single table, eliminating the need for separate vector stores and sync jobs. The system…
AI agents that remember user preferences but forget their own prior actions appear unintelligent due to state failures, not model limitations, according to engineers who shipped a memory layer in prod…
A user's RAG-powered customer-support agent incorrectly approved a laptop return because it retrieved a 2023 return policy document instead of the current 14-day policy, despite the query being semant…
Production agents require durable memory systems that support persistence, updates, expiration, and deletion across sessions, not just context windows that carry information into single model calls. A…
In early March 2026, a customer request for persistent agent memory led PingCAP to rapidly prototype and ship mem9, a product born from workflow pain rather than a strategic roadmap. The company learn…