Elastic announced the general availability of Agent Builder, a complete set of capabilities that helps developers quickly build secure, reliable, context-driven AI agents.
AI agents need the right context to perform complex tasks accurately. Built on Elasticsearch, Agent Builder excels at context engineering by delivering relevance in a unified platform that scales, searches, and analyzes enterprise data. It dramatically simplifies the entire agent workflow with native data prep and ingestion, retrieval and ranking, built-in and custom tools, native conversational experience, and agent observability. Developers can use Agent Builder to chat with their data or build a context-driven custom agent in minutes.
"Agent Builder has native MCP and A2A protocol support, enabling seamless deployments within Microsoft Foundry and Microsoft Agent Framework,” said Amanda Silver, CVP, Microsoft CoreAI. “This gives our users a way to build context-rich, agentic AI leveraging Elasticsearch as a Knowledge Source and powered by Microsoft Foundry."
"Agentic systems fail today because connecting AI to tools and data is complex," said Sam Partee, co-founder at Arcade.dev. "Elastic Agent Builder with Arcade.dev gives developers a structured, secure way to handle how agents retrieve context, reason, and act, taking agents from demo to production grade."
“Unlocking enterprise context from unstructured data sources is key to building effective agents,” said Jerry Liu, CEO at LlamaIndex. “Elastic Agent Builder combined with LlamaIndex’s complex document processing strengthens the critical context layer, helping teams retrieve, process, and prepare data so agents can reason more accurately and deliver better outcomes.”
Introducing Workflows
Elastic also introduced Elastic Workflows (tech preview), a new capability that extends Agent Builder’s functionality by enabling agents to reliably take action across systems.
Many agent-building frameworks require LLMs to plan and manage every step of the automation. However, AI lacks the reliability of rule-based actions, a critical capability for organizations. Workflows closes this gap. Now, agents built with Agent Builder can leverage Workflows to orchestrate internal and external systems to take actions, gather and transform data and context with precision. Agent Builder and Workflows enable developers to build context-driven agents that can reason accurately and execute predictably.
"Agent Builder simplifies working with messy enterprise data, giving developers a secure, reliable foundation to build context-driven agents at scale,” said Ken Exner, chief product officer at Elastic. “Elastic Workflows complements this foundation by giving those agents built-in, rules-based automation for simple tasks. By enhancing Agent Builder with Workflows, teams get a single system that delivers both intelligent reasoning and dependable automation, which is exactly what enterprises need to move from pilots to real-world impact.”
Agents developed with Agent Builder are model-agnostic and compatible with managed model-as-a-service providers, including the cloud hyperscalers.
Availability
Agent Builder is available in Elastic Cloud Serverless and is included with the Enterprise Tier in Elastic Cloud Hosted and self-managed Elastic Stack releases for existing customers.
Workflows is available in tech preview.
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 ...