Elastic announced an expanded collaboration with OpenAI to help organizations build production-ready AI applications and agents using OpenAI models with Elasticsearch.
By combining Elasticsearch's retrieval, search and governance capabilities with OpenAI's advanced reasoning models, organizations can ground AI in their own enterprise data to enable more accurate, secure and reliable AI at scale.
AI agents are only as useful as the enterprise context they can access. Yet most of that information remains out of reach. According to Gartner®, “unstructured data, such as documents and multimedia files, accounts for 70% to 90% of organizational data.”1 That context is spread across documents, tickets, logs, metrics, traces, and security alerts, changes continuously, and is governed by different permissions. Without access to the right enterprise context, even advanced AI models struggle to deliver accurate, reliable results.
Elasticsearch provides the retrieval layer, combining lexical and vector search, semantic reranking, filtering, and access controls in a single platform. It helps agents find relevant, real-time context with the right permissions, reducing unnecessary data sent to the model and improving retrieval quality, all with lower token costs. Together with OpenAI models, developers can build reliable, cost-efficient AI agents for critical enterprise workflows.
“The success of enterprise AI depends on connecting powerful models with the knowledge businesses already possess,” said Greg Tademoto, global vice president, Business Development & Strategic AI Partnerships at Elastic. “Much of that knowledge is buried in unstructured data. 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.”
“Great AI needs great context. 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.
Elastic and OpenAI will focus on delivering three customer outcomes:
- Context-aware AI agents that retrieve accurate, permission-aware enterprise knowledge at scale, while improving agent efficiency.
- Agentic observability that correlates telemetry and accelerates root cause investigation for SRE teams.
- Agentic security operations that turn high volumes of alerts into evidence-backed investigations for analyst review and action.
Elastic has supported OpenAI models through AI Assistants and connectors since 2023. This collaboration expands that foundation through deeper product integration and joint work to help customers build enterprise AI applications grounded in governed data.
The companies plan to deepen their collaboration further across enterprise AI, security and observability. Through the OpenAI Daybreak Cyber Partner Program, Elastic plans to integrate OpenAI’s GPT-5.5 Cyber specific models into Elastic Security agentic workflows and extend governance to the OpenAI platform, enabling detection of anomalous OpenAI activity alongside endpoint and network threats. For developers using OpenAI Codex, Elastic will develop integration points that provide governed, real-time access to their unstructured enterprise data.
Developers can get started today by connecting OpenAI models and applications with Elasticsearch using Elastic AI Assistants, Agent Builder and MCP integrations.
The Latest
While organizations want to take control of their telemetry, building telemetry pipelines from scratch can be a very daunting, complicated task, even when leveraging open-source standards like OpenTelemetry. It requires specialized knowledge across distributed systems, data engineering, and security. This fragmented approach across systems causes higher operational costs; it puts a strain on resources and reduces efficiency as teams have to work with different interfaces and processes ...
For decades, enterprise networks were designed around a simple assumption: work happened inside the office. Applications lived in centralized data centers, employees connected through internal infrastructure, and security focused on protecting the perimeter that surrounded everything ... But the way organizations operate today bears little resemblance to that environment. Cloud platforms host critical applications, employees connect from homes and airports as often as they do from offices, and partners collaborate through shared systems that exist far beyond corporate walls. In short, the corporate network no longer resembles the environment it was designed to protect ...
As an analyst who researches how IT organizations design, build, and operate their networks, I find that network data is a constant source of pain. Network teams struggle with data quality, fragmentation, authority, access, and trust. And these issues undermine everything they try to do. Here are the numbers: Only 45% of network teams are completely confident in the accuracy of their network source of truth, which documents the intent of their network ...
The 2026 Global Data Center Survey from Uptime Institute reveals an industry navigating workforce constraints, escalating outage expenses, even as rising costs remain the top concern for management teams ...
The next observability gap may not be in the code. It may be under the rack. That sounds strange until you think about how AI incidents actually feel in the middle of an investigation ... The application dashboard may be accurate. It may also be stopping at the wrong boundary. AI systems depend on software, but they also depend on a dense physical stack: racks, power paths, thermal margin, maintenance activity and, in many environments, liquid cooling. Those physical dependencies can change slowly before they look like a software incident ...
Certificate expiration is the rare outage you can see coming. Every TLS certificate carries the date it stops working, so the moment it will begin breaking connections is knowable in advance. That's what makes an expired certificate such a frustrating way to lose a service. What's changing now is how often that date comes around ...
Enterprises operate different combinations of workloads across cloud, hybrid and multicloud environments. For business-critical workloads, teams need to consider monitoring and observability early so they can detect health issues, investigate failures, and understand operational impact. Organizations place workloads on cloud platforms based on a combination of technical requirements, economics, existing dependencies, organizational standards, and business priorities. Their monitoring priorities therefore depend on what they operate and where those systems run. Those priorities will not look the same for every organization ...
Top-performing businesses prioritize data-driven decision making, enabling leaders to move from intuition and gut feel towards evidence-based judgment. But that judgment is only sound when the data underpinning decisions is accurate. With incident management, data accuracy is particularly important. Long-term revenue, customer trust, and operational stability depend on high-quality data that enables teams to quickly identify and address the root cause of major incidents. Against this backdrop, governance becomes a critical endeavor to ensure the right data drives the right action ...
In MEAN TIME TO INSIGHT Episode 26, Shamus McGillicuddy, VP of Research, Network Infrastructure and Operations, at EMA discusses network compliance ...
Most production autonomous agents do not run in a vacuum. They run inside cloud infrastructure: virtual machines, containers, pods, managed clusters or private servers. That is where most operations teams start monitoring. Is the VM alive? Is the container running? Did the pod restart? Is memory stable? Is CPU too high? Did the health check pass? Those signals are useful. They tell you whether the shell around the agent is alive. They do not tell you whether the agent inside is actually operational ...