Elastic Announces General Availability of Agent Builder with Expanded Capabilities

Key Terms

ai agents technical

AI agents are computer programs designed to perform tasks or make decisions automatically, often by learning from data and adapting to new information. They act like virtual assistants or robots that can handle complex activities without human intervention, which can help businesses and individuals save time and improve efficiency. For investors, AI agents matter because they can enhance decision-making and automate processes that influence markets and financial outcomes.

context-driven technical

An approach where decisions, communications or actions are guided by the surrounding circumstances, data and priorities rather than by fixed rules. For investors, a context-driven strategy means evaluating a company or market by looking at current conditions — such as economic trends, competitive moves, regulatory signals or recent performance — and adjusting expectations, valuation and risk assumptions accordingly, much like changing your route when traffic or weather alters your original plan.

agent observability technical

Agent observability is the ability to see and understand what an automated decision-maker or software agent is doing, why it made certain choices, and how well it is performing. For investors this matters because visible behavior reduces surprises and helps assess operational risk, regulatory compliance and reliability—like having a clear dashboard on a car that shows how the driver and engine are behaving, so you can judge safety and likely future performance.

agentic ai technical

Agentic AI refers to computer systems that can make their own decisions and take actions without needing someone to tell them what to do each time. It's like giving a robot a degree of independence to solve problems or achieve goals on its own, which matters because it could change how we work and interact with technology in everyday life.

llms technical

Large language models are advanced computer programs that read and generate human-like text by learning patterns from huge amounts of written material; think of them as digital employees that can draft reports, answer questions, summarize documents, or generate code. They matter to investors because they can change a company’s costs, speed of product development, customer service, and competitive edge — and they also create new risks and regulatory questions that can affect profits and valuation.

model-agnostic technical

An approach, tool, or test that works with any predictive or analytical model rather than depending on a single algorithm or vendor. For investors, model-agnostic methods let you compare, audit, and trust results across different forecasting systems—like using a universal charger that fits many phones—reducing reliance on one provider, making performance easier to validate, and lowering the risk that a single model’s quirks drive investment decisions.

model-as-a-service technical

Model-as-a-service is an online offering that lets customers rent access to ready-made predictive or generative models (software that makes forecasts, classifies information, or generates content) instead of building them in-house. For investors it matters because it creates recurring, scalable revenue—like subscribing to a tool library—while exposing providers to costs and risks tied to data quality, compute expenses, customer lock-in and regulatory scrutiny.

tech preview technical

A tech preview is an early demonstration or limited release of a new technology, product feature, or software to show how it works before the final version is finished. Think of it like a prototype shown at a car show: it reveals potential and design direction but may change and is not guaranteed to reach market as shown. For investors, tech previews signal innovation and potential future revenue but also carry higher uncertainty about timing, costs, and commercial success.

Elastic Agent Builder grounds AI agents in enterprise data, executes context-driven answers and actions

SAN FRANCISCO--(BUSINESS WIRE)-- Elastic (NYSE: ESTC), the Search AI Company, 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.

Additional Resources

• Blog: Agent Builder Now GA: Ship Context-Driven Agents In Minutes

About Elastic

Elastic (NYSE: ESTC), the Search AI Company, integrates its deep expertise in search technology with artificial intelligence to help everyone transform all of their data into answers, actions, and outcomes. Elastic's Search AI Platform — the foundation for its search, observability, and security solutions — is used by thousands of companies, including more than 50% of the Fortune 500. Learn more at elastic.co.

Elastic and associated marks are trademarks or registered trademarks of elasticsearch BV and its subsidiaries. All other company and product names may be trademarks of their respective owners.

View source version on businesswire.com: https://www.businesswire.com/news/home/20260122544127/en/

Media Contact

Elastic PR

PR-team@elastic.co

Source: Elastic N.V.