Pinecone has announced a new integration connecting Pinecone Nexus and Microsoft OneLake to revolutionise how enterprise AI agents access information, enabling fast, structured, cited responses built directly from data organisations already have within the Microsoft ecosystem.
“The data enterprises need to power their AI agents already live in Microsoft OneLake,” said Ash Ashutosh, CEO, Pinecone. “Nexus builds task-specific artifacts from this data, and gives AI agents a clean, structured, cited interface through KnowQL, 30x+ faster and at a fraction of what traditional retrieval approaches cost.”
Bringing AI agents directly to enterprise data
Pinecone Nexus dynamically creates structured, task-optimised contexts known as artefacts, pulling relevant data from OneLake, applying access permissions, and formatting the results for direct use by AI agents. The approach shifts much of the data assembly and reasoning work away from runtime retrieval, reducing the burden on large language models.
Agents query artifacts through KnowQL, a query language built for knowledge retrieval. A KnowQL query specifies what the agent needs to know, the required output format, citation requirements, and latency budget. Nexus handles the rest.
The Nexus integration connects directly to OneLake without manual imports or upload steps. It enables technical teams to operate on raw data to build on knowledgeable artifacts that deliver accurate results at scale, without rebuilding data pipelines or managing separate retrieval infrastructure.
KnowQL defines a common language. An agent specifies the question, the required output structure, the citation standard, and the latency budget. A KnowQL-compliant knowledge engine handles the rest.
“Microsoft OneLake offers a unified data foundation for AI applications and Agents,” said Dipti Borkar, VP and GM, Microsoft OneLake and Fabric Ecosystem. “Pinecone Nexus does the hard work of fetching, assembling, and reasoning over OneLake data up front, so our customers’ agents spend less time making tool calls, burn fewer tokens, and get accurate answers faster.”
