For all their technical capabilities, large language models (LLMs) still have a memory problem. They can lack the ability to retain context across conversations, and don’t always contain the frameworks to let them access relevant data, ultimately making their results unreliable and untrustworthy.
NoSQL database pioneer MongoDB is taking on this problem, releasing new persistent memory, retrieval, embedding, and re-ranking features, all integrated into one platform. The company is also introducing new security connectivity, open-source plugins, and other framework integrations to support agentic AI workloads.
Supporting agentic memory
“Unlocking the power of agents requires memory,” Pete Johnson, MongoDB’s field CTO of AI, said during a press briefing. “Just like human memory, a good agentic memory organizes knowledge. It helps agents retrieve the right knowledge based on context and learn to make smarter decisions and take optimized actions over time.”
To advance automated retrieval an
MongoDB has introduced a native reranking capability for Atlas, aiming to help enterprises improve AI retrieval quality without adding another service to their technology stack.
The move addresses a longstanding challenge with reranking technology. While it can significantly boost the relevance of AI-generated responses, deploying it has typically required separate vendors, APIs, and orchestration layers that add complexity, governance overhead, and cost as AI applications scale.
The feature named Native Reranking, currently in public preview and powered by Voyage AI, runs directly within the MongoDB aggregation pipeline and can improve retrieval quality by up to 30%, the company said in a statement.
Native integration cuts developer overhead
Embedding reranking directly into the database, according to analysts, will reduce operational toil for developers, resulting in productivity gains.
“Native Reranking reduces the work that developers usually do. The immediate impact is a little le
Enterprise Document Intelligence [Vol.1 #7C] - One LLM call ranks the candidates with reasons. The output is one typed object your auditor can defend
The post Letting an LLM Pick the Right RAG Page: The Arbiter Pattern at the End of Retrieval appeared first on Towards Data Science.
Anthropic has introduced Claude Tag, a new always-on AI integration for Slack that gives enterprise teams a shared, context-aware AI presence directly inside their existing workflows. The feature is rolling out in beta for Claude Enterprise and Claude Team customers. Unlike previous on-demand Slack integrations, Claude Tag maintains persistent memory within a channel, allowing it […]
Enterprise Document Intelligence [Vol.1 #7A] - Stop searching strings. Filter line_df and toc_df. Pick anchors small, expand context large
The post Retrieval Is Filtering, Not Search: A Mental Model for Enterprise RAG appeared first on Towards Data Science.
Grok Build's in-terminal marketplace bundles skills, agents, hooks, and MCP servers, with commit-SHA verification on every remote plugin.
The post xAI Ships Grok Build Plugin Marketplace With MongoDB, Vercel, Sentry, Chrome DevTools, Cloudflare, and Superpowers Plugins at Launch appeared first on MarkTechPost.
xAI's expanded developer tooling could enhance productivity and streamline workflows, potentially increasing its competitive edge in the AI space.
The post MongoDB plugin goes live in Grok Build Plugin Marketplace as xAI expands developer tooling appeared first on Crypto Briefing.
