Elastic has expanded its collaboration with OpenAI to help organisations build AI applications and agents using OpenAI models with Elasticsearch, enabling enterprises to ground AI responses in their own data.
The partnership combines Elasticsearch’s search, retrieval and governance capabilities with OpenAI’s reasoning models to improve the accuracy, security and reliability of enterprise AI applications.
According to Elastic, the integration addresses a key challenge in enterprise AI, where the majority of organisational information exists as unstructured data spread across documents, logs, security alerts, tickets and other sources. Citing Gartner, the company said 70% to 90% of enterprise data is unstructured.
Elastic said Elasticsearch provides a unified retrieval layer that combines lexical and vector search, semantic reranking and access controls, allowing AI agents to retrieve permission-aware enterprise information while reducing unnecessary data sent to AI models.
The companies said they will focus on three areas: context-aware AI agents, AI-driven observability for site reliability engineering (SRE) teams, and agentic security operations that help security analysts investigate alerts. They also plan to integrate OpenAI’s GPT-5.5 Cyber models into Elastic Security workflows through the OpenAI Daybreak Cyber Partner Program.
“By combining OpenAI’s advanced reasoning with Elasticsearch’s retrieval and governance capabilities, we’re helping enterprises build AI agents that are accurate, secure and useful in production,” said Greg Tademoto, Global Vice President, Business Development & Strategic AI Partnerships at Elastic.
“We’re excited to collaborate with Elastic to bring OpenAI’s models closer to the data businesses rely on, helping them build AI agents that are more accurate, more secure, and ready to deliver real-world results,” said Colleen Kapase, Vice President, Strategic Global Partnerships & Ecosystems at OpenAI.