Elastic adds workflow automation for AI agents
Elastic is targeting organisations seeking to automate complex workflows using AI agents that can access and analyse enterprise data with its new Agent Builder.
The platform addresses the challenge of deploying AI systems that can reliably interact with internal documents, databases and systems while maintaining governance and security controls. Agent Builder connects to Elasticsearch to retrieve enterprise data and execute automated tasks.
The company claims the system “dramatically simplifies” agent development through integrated data ingestion, retrieval capabilities and built-in tools. Developers can deploy agents using multiple AI models through cloud providers.
Elastic simultaneously introduced Workflows, currently in technical preview, which adds rule-based automation to supplement AI-driven decision-making. This dual approach responds to enterprise requirements for both intelligent reasoning and predictable, compliant automation – a critical consideration for organisations managing regulated data.
“Agent Builder has native MCP and A2A protocol support, enabling seamless deployments within Microsoft Foundry and Microsoft Agent Framework,” said Amanda Silver, corporate vice president at Microsoft CoreAI.
“This gives our users a way to build context-rich, agentic AI leveraging Elasticsearch as a Knowledge Source.”
Elastic has partnered with Arcade.dev for agent tool integration and LlamaIndex for document processing.
“Unlocking enterprise context from unstructured data sources is key to building effective agents,” said Jerry Liu, CEO at LlamaIndex.
The company claims its document processing capabilities will help agents “retrieve, process, and prepare data so agents can reason more accurately.”
Agent Builder is available in Elastic Cloud Serverless and included with the Enterprise Tier for existing customers using Elastic Cloud Hosted or self-managed deployments.
Ken Exner, chief product officer at Elastic, positioned the release as addressing a gap between AI experimentation and production deployment: “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.”