---
title: AI-augmented workflows
description: Combine Elastic Workflows with Agent Builder to build AI-augmented workflows that pair deterministic steps with agent reasoning.
url: https://docs-v3-preview.elastic.dev/elastic/docs-content/tree/main/explore-analyze/workflows/use-cases/ai-augmented-workflows
products:
  - Elastic Cloud Enterprise
  - Elastic Cloud Hosted
  - Elastic Cloud Serverless
  - Elastic Cloud on Kubernetes
  - Elastic Stack
  - Kibana
applies_to:
  - Elastic Cloud Serverless: Generally available
  - Elastic Stack: Preview in 9.3
---

# AI-augmented workflows
Workflows and Elastic Agent Builder are complementary. Workflows give you deterministic, auditable, event-driven automation: the steps always run in the same order and produce the same kind of result. Elastic Agent Builder agents give you reasoning: the ability to interpret unstructured context, classify signals, and generate natural-language summaries. Combining the two lets you build automation that's both reliable and intelligent.
The integration runs in both directions: a workflow can call an agent as a step, and an agent can trigger a workflow as a tool.

## What you can build

- **Call an agent from a workflow.** Use the [`ai.agent` step](/elastic/docs-content/tree/main/explore-analyze/workflows/steps/ai-steps#ai-agent) to invoke any agent built in Elastic Agent Builder. The agent sees the workflow's data through template variables, performs its reasoning, and returns a response that subsequent steps can act on. Refer to [Call Elastic Agent Builder agents from Elastic Workflows](https://docs-v3-preview.elastic.dev/elastic/docs-content/tree/main/explore-analyze/ai-features/agent-builder/agents-and-workflows) for the full `ai.agent` reference and examples.
- **Trigger a workflow from an agent.** Create a [workflow tool](https://docs-v3-preview.elastic.dev/elastic/docs-content/tree/main/explore-analyze/ai-features/agent-builder/tools/workflow-tools) in Elastic Agent Builder and assign it to an agent. The agent can then invoke the workflow from a conversation, extracting the needed inputs from the user's message and surfacing the workflow's output in chat.
- **Classify and route with AI.** Pair [`ai.classify`](/elastic/docs-content/tree/main/explore-analyze/workflows/steps/ai-steps#ai-classify) with [`switch`](https://docs-v3-preview.elastic.dev/elastic/docs-content/tree/main/explore-analyze/workflows/steps/switch) to send each alert, ticket, or signal down a different branch based on a model's categorization.
- **Summarize evidence before action.** Use [`ai.summarize`](/elastic/docs-content/tree/main/explore-analyze/workflows/steps/ai-steps#ai-summarize) to turn gathered evidence into a concise summary for a case description, notification body, or reviewer prompt.
- **Gate AI decisions on human review.** Pair AI classification with [human-in-the-loop](https://docs-v3-preview.elastic.dev/elastic/docs-content/tree/main/explore-analyze/workflows/authoring-techniques/human-in-the-loop) to show the model's output to an analyst before the workflow takes action.
- **Send structured prompts to an LLM.** Use the [`ai.prompt` step](/elastic/docs-content/tree/main/explore-analyze/workflows/steps/ai-steps#ai-prompt) with any [configured AI connector](https://docs-v3-preview.elastic.dev/elastic/docs-content/tree/main/deploy-manage/manage-connectors) to run classification, extraction, or summarization without going through an agent.
- **Compose reusable AI building blocks.** Extract repeated AI step sequences into a [child workflow](https://docs-v3-preview.elastic.dev/elastic/docs-content/tree/main/explore-analyze/workflows/steps/composition) that parent workflows invoke with `workflow.execute`.


## When to use each direction

- Use **agent-from-workflow** when the workflow already knows what it's doing and needs AI only to reason over a specific data set. For example, summarizing an alert, classifying severity, or extracting fields from unstructured text.
- Use **workflow-from-agent** when the user (or another agent) is in a conversation and wants to trigger a deterministic procedure. For example, isolating a host, opening a case, or running a set of enrichment queries.


## Learn more

- [AI steps reference](https://docs-v3-preview.elastic.dev/elastic/docs-content/tree/main/explore-analyze/workflows/steps/ai-steps): `ai.prompt`, `ai.classify`, `ai.summarize`, and `ai.agent` parameters and output structure.
- [Composition steps](https://docs-v3-preview.elastic.dev/elastic/docs-content/tree/main/explore-analyze/workflows/steps/composition): Invoke child workflows and emit outputs.
- [Human-in-the-loop](https://docs-v3-preview.elastic.dev/elastic/docs-content/tree/main/explore-analyze/workflows/authoring-techniques/human-in-the-loop): Pause a workflow for reviewer input.
- [Call Elastic Agent Builder agents from Elastic Workflows](https://docs-v3-preview.elastic.dev/elastic/docs-content/tree/main/explore-analyze/ai-features/agent-builder/agents-and-workflows): End-to-end guide for invoking agents from workflow steps.
- [Workflow tools in Elastic Agent Builder](https://docs-v3-preview.elastic.dev/elastic/docs-content/tree/main/explore-analyze/ai-features/agent-builder/tools/workflow-tools): Configure an agent to trigger a workflow.
- [Elastic Agent Builder overview](https://docs-v3-preview.elastic.dev/elastic/docs-content/tree/main/explore-analyze/ai-features/elastic-agent-builder): Concepts, tools, and agent types.