Blog

Technology 19th March 2026

NVIDIA’s Agentic Era: The Bottleneck Isn’t GPUs, It’s Your Database

NVIDIA predicts a $120B expansion in data infrastructure to support Agentic AI. But for AI agents to reason and act, they need a ‘ground truth’ that legacy databases can’t provide. Explore the technical proof of how RegattaDB handles massive transactional loads with strict serializable isolation.

RegattaDB TPC-C Benchmark: 750,000+ TPS at 1.5 Million Warehouses on a 50-Node Cluster 

TPC-C benchmark for RegattaDB at 1.5 million warehouses across a 50-node GCP cluster, sustaining over 750,000…
Read More >

File under “now possible”: A 20B row JOIN and 50,000 UPDATES/second in a single distributed database 

Distributed joins are among the most demanding operations in large‑scale data systems. Trying to do this at the same…
Read More >

The Shift to Agentic AI and a Modern Database

Agents need to both think and act The core objective of Agentic AI is to deliver systems capable of executing functions…
Read More >

RegattaDB: Concurrency Control – Serializable Isolation Without Locks, Snapshots or Clock Sync

In this blog I’ll cover Regatta’s concurrency-control protocols, and how our approach allows us to avoid many of the…
Read More >

Connect Your Spring Boot Application to Regatta

In this tutorial, we’ll show you just how simple it is to deploy a Spring Boot application that interacts with Regatta…
Read More >

Regatta’s Architecture: A Bird’s Eye View

In this blog I will provide a high level overview of Regatta’s design and architectural principles. While I keep this…
Read More >
Skip to content