Elastic announced Agent Builder, a complete set of capabilities powered by Elasticsearch, that makes it easy for developers to build custom AI agents on company data—all within minutes.
Agent Builder also provides an out-of-the-box conversational experience for exploring, analyzing, and optimizing any data in Elasticsearch.
As AI agents evolve to take on more complex and data-driven enterprise tasks, reliability and accuracy depend on delivering accurate context. In most enterprises, this context is scattered across various unstructured data sources, including documents, emails, business apps, and customer feedback. The process for getting the relevant context into agents at the right time is known as context engineering. While Elasticsearch has always been a leading platform for the core of context engineering, Agent Builder dramatically expands on this strength. It simplifies the entire operational lifecycle of agents, their development, configuration, execution, customization, and observability directly into Elasticsearch.
”AI agents don’t just need lots of data, they need the right data and tools, with relevance, guardrails, and observability built in,” said Ken Exner, chief product officer at Elastic. “Developers already rely on Elasticsearch to find the right answer from their messy business data. Agent Builder goes further by making Elasticsearch one of the fastest platforms to build precise AI agents that use your data, where retrieval, governance, and orchestration all operate in one place, natively.”
With Agent Builder, developers have built-in tools that go beyond basic run queries of open-standard Model Context Protocol (MCP) endpoints. Users of Agent Builder on Elasticsearch can ask natural language questions, identify which indexes to query, configure searches, define agent parameters and more.
With Agent Builder, developers can:
- Immediately Chat with Company Data: Agent Builder includes a built-in, native conversational agent. Right out of the box, you can ask questions and interact with any data you have in Elasticsearch, turning your data into an active, conversational partner.
- Leverage Intelligent Built-In Tools for Relevance: Agent Builder comes with a set of built-in tools, including a powerful search capability that selects the right index, understands the structure of that data, translates natural language into optimized semantic, hybrid or structured queries, and returns only the most relevant context to the Large Language Model (LLM).
- Build Powerful Custom Tools: Define tools that give the agent new skills, harnessing the full power of Elasticsearch’s query language (ES|QL) to precisely control what data is used for context. This gives granular control over the relevance, accuracy, and security of your agent's responses.
- Define Custom Agents: Create your own custom agent from the ground up, going beyond the built-in options. You control the agent’s entire persona with a custom system prompt, decide exactly which tools it can access, and configure its specific security profile to meet your needs.
- Integrate with MCP and A2A Safely: Connect external agents and applications via MCP and A2A, while maintaining governance through the Elasticsearch execution layer.
Agent Builder in Elasticsearch is available today in Technical Preview on Elastic Cloud in serverless and coming soon in version 9.2.
The Latest
As AI adoption accelerates, operational complexity — not model intelligence — is becoming the primary barrier to reliable AI at scale, according to the State of AI Engineering 2026 from Datadog ... The report highlights a compounding complexity challenge as AI systems scale ... Around 5% of AI model requests fail in production, with nearly 60% of those failures caused by capacity limits ...
For years, production operations teams have treated alert fatigue as a quality-of-life problem: something that makes on-call rotations miserable but isn't considered a direct contributor to outages. That framing doesn't capture how these systems fail, and we now have data to show why. More importantly, it's now clear alert fatigue is a symptom of a deeper issue: production systems have outgrown the current operational approaches ...
I was on a customer call last fall when an enterprise architect said something I haven't been able to shake. Her team had just spent four months trying to swap one AI vendor for another. The original plan said three weeks. "We didn't switch vendors," she told me. "We rebuilt half our integrations and discovered what we'd actually been depending on." Most enterprise leaders don't expect that to be the experience ...
Ask any senior SRE or platform engineer what keeps them up at night, and the answer probably isn't the monitoring tool — it's the data feeding it. The proliferation of APM, observability, and AIOps platforms has created a telemetry sprawl problem that most teams manage reactively rather than architect proactively. Metrics are going to one platform. Traces routed somewhere else. Logs duplicated across multiple backends because nobody wants to be caught without them when something breaks. Every redundant stream costs money ...
80% of respondents agree that the IT role is shifting from operators to orchestrators, according to the 2026 IT Trends Report: The Human Side of Autonomous IT from SolarWinds ...
40% of organizations deploying AI will implement dedicated AI observability tools by 2028 to monitor model performance, bias and outputs, according to Gartner ...
Until AI-powered engineering tools have live visibility of how code behaves at runtime, they cannot be trusted to autonomously ensure reliable systems, according to the State of AI-Powered Engineering Report 2026 report from Lightrun. The report reveals that a major volume of manual work is required when AI-generated code is deployed: 43% of AI-generated code requires manual debugging in production, even after passing QA or staging tests. Furthermore, an average of three manual redeploy cycles are required to verify a single AI-suggested code fix in production ...
Many organizations describe AI as strategic, but they do not manage it strategically. When AI plans are disconnected from strategy, detached from organizational learning, and protected from serious assumptions testing, the problem is no longer technical immaturity; it is a failure of management discipline ... Executives too often tell organizations to "use AI" before they define what AI is supposed to change. The problem deepens in organizations where strategy isn't well articulated in the first place ...
Across the enterprise technology landscape, a quiet crisis is playing out. Organizations have run hundreds, sometimes thousands, of generative AI pilots. Leadership has celebrated the proof of concept (POCs) ... Industry experience points to a sobering reality: only 5-10% of AI POCs that progress to the pilot stage successfully reach scaled production. The remaining 90% fail because the enterprise environment around them was never ready to absorb them, not the AI models ...
Today's modern systems are not what they once were. Organizations now rely on distributed systems, event-driven workflows, hybrid and multi-cloud environments and continuous delivery pipelines. While each adds flexibility, it also introduces new, often invisible failures. Development speed is no longer the primary bottleneck of innovation. Reliability is ...