When a Jev-powered check gets something wrong, and a person corrects it, where does that correction go, and how can you ensure the correction is implemented in future results? This blog explains why a decision model correction should live outside the model, what a system needs to ensure corrections carry into the next request, and the code review check that prevents the system from raising a finding after a reviewer has overruled it.
If your agents hand work to each other, or to a teammate’s agents, this is the difference between the next agent building on a decision and rebuilding a dead end. Discover how to solve the agent handoff problem with Meko, the agent-native context engine for multi-agent AI systems.
Developers and engineering teams building production multi-agent AI applications need their agent systems to learn and improve collectively, not just store and retrieve data. This blog explores Meko’s agent memory features and showcases a short video by Yugabyte Developer Advocate Heather Downing that demonstrates exactly how Meko gives AI agents persistent, shareable memory.
Meko is the agent-native data infrastructure that enables multi-agent systems to learn together, building collective memory and shared knowledge that compounds across the entire system. Meko solves the data infrastructure headaches developers and engineering teams face when building and shipping production multi-agent AI applications. Find out more.
Your AI isn’t broken, it’s just trained on a database that isn’t distributed. This blog covers the design of our new distributed SQL benchmark, examines what breaks and why, and offers a handy open-source fix you can drop in today.
AI doesn’t change the importance of data, it simply exposes weaknesses faster and at a much larger scale. If you’re building or modernizing AI-driven systems, the database you choose matters more than ever. Download our new white paper to discover what to look for in a next-generation data platform and how YugabyteDB meets those demands.
YugabyteDB is officially supported in Google’s MCP Toolbox for Databases, making it easier for you to build production AI agents with confidence. Discover how developers can access YugabyteDB’s distributed SQL capabilities, including load balancing, topology-aware routing, and data sovereignty controls, as documented and tested configuration options rather than custom workarounds.
Discover how you can integrate YugabyteDB’s Retail Analytics sample dataset with an MCP server (Google’s MCP Toolbox for Databases). We demonstrate how to define simple SQL tools using tools.yaml and illustrate how an Agent Development Kit (ADK) agent can discover and utilize these tools. All necessary files and a minimal ADK Python agent are provided, ready for you to copy, paste, and run locally!
Thanks to the pgvector PostgreSQL extension, YugabyteDB functions as a highly performant vector database. Its scalability allows it to store and search billions of vectors. This blog starts by detailing why a vector database is essential to agentic AI and how YugabyteDB meets key requirements for global organizations, including data sovereignty and zero-downtime. In the second part, we demonstrate how you can easily leverage this technology to provide AI with your organization’s information using n8n, a no-code orchestration tool.
This blog examines the increasing challenges of fraud in today’s UPI and digital payments ecosystem, highlights the key risks faced by banks and fintechs, and explains how Retrieval-Augmented Generation can provide valuable context from past cases and policies. Discover the benefits of multi-agent collaboration using YugabyteDB Vector’s A2A (Agent-to-Agent) Orchestration, which involves specialized agents working together to deliver smarter, real-time fraud detection.
