Accelerate your IT automation with AI

More than ever, IT teams are faced with complexity. Organizations are operating more applications and systems across hybrid and multicloud environments, responding to an ever-growing volume of security and compliance requirements, and managing infrastructure that often evolves faster than teams can keep up with manually.

Enterprise-wide automation can help overcome these issues. In fact, the efficiency, resilience, governance, and scale afforded by automation is no longer just nice to have—automation is now critical to every modern organization.

However, while automation provides significant benefits, demands on the teams that build, manage, operate, and orchestrate that automation are also intensifying. This includes challenges related to:

Automation development. Organizational skills gaps persist, leaving automation content creation up to a handful of experts. This makes it difficult to democratize the content creation process across a diverse set of teams and users. Engineers have limited time to learn new skills, and even experienced content creators find code maintenance repetitive and mundane.

Automation administration. Growing adoption of automation can add additional challenges. On 1 hand, automation can substantially increase enterprise IT productivity and performance. On the other, it means more users to manage, more jobs to troubleshoot, more playbooks to audit, and more integrations to configure. Onboarding new team members, resolving issues, and maintaining overall platform health can consume time that could be spent on higher-value work.

The responsibilities of IT operators and infrastructure engineers. For many IT Ops teams, the volume of alerts generated by applications, observability platforms, and security systems has reached unmanageable levels. Which alerts require an immediate response and which can wait? In practice, many teams are still spending too much time investigating automated error reports, diagnosing performance degradations, and coordinating remediation efforts across tools and teams.

Putting AI to work with automation

The pace of AI technology is evolving so fast that exploring advanced forms of automation in practical terms often risks obsolescence in a matter of months or even weeks. However, when organizations remain focused on the fundamental goals of their IT automation strategy—greater efficiency, resilience, and scale—then technologies such as AI become another tool to elevate existing automation performance, not a trend to chase.

In this e-book, we’ll explore the intersection of automation and AI. We’ll examine how AI and automation can both complement and support each other. And we’ll outline how the AI capabilities within Red Hat® Ansible® Automation Platform provide an enterprise-ready approach to:

• Create trusted automation content.
• Simplify platform management.
• Unlock AIOps.

High-impact automation starts with crafting high-quality automation playbooks. Even with the relative simplicity of YAML-based Ansible code syntax, skills gaps keep automation content development concentrated among a few users. Automation performs best as a team sport—available to a wide range of users.

Beyond the skills challenges, there is the question of code quality. Automation content needs to meet organizational policies and standards without introducing subtle errors that wreak havoc on production environments. Fortunately, coding assistants have evolved rapidly in recent years, but automation developers still need to validate that the content output is consistent with automation best practices and their organizations’ own policies and standards. This chapter goes over some of the ways that Ansible Automation Platform helps you do that.

Automation coding assistant 

The automation coding assistant (formerly Red Hat Ansible Lightspeed) is a gen AI service that helps busy automation teams create Ansible Automation Platform content more efficiently.

It generates single tasks, multitask sequences, or entire playbooks and roles from a single prompt. It is accessed through the Ansible Visual Studio (VS) Code extension, allowing developers to stay in their editor of choice.

From natural language prompts to trusted code

The coding assistant generates recommendations aligned with Ansible Automation Platform best practices. Post-processing from Red Hat optimizes suggestions beyond what the underlying model produces on its own. And because the assistant works within the existing Ansible development toolchain, content still flows through the same review, testing, and approval processes your organization already uses.

Organizations have the flexibility to choose the model provider that fits their unique environment, such as IBM watsonx Code Assistant, Google Gemini (Vertex), or Red Hat AI. For IBM watsonx Code Assistant users, deployment options include on premise, hybrid, or Software-as-a-Service (SaaS).

MCP server-enabled assistant in the Ansible Visual Studio Code extension

Automation developers are often required to switch between different tools and contexts—browser, documentation, command-line, etc.— throughout the content creation lifecycle, which can increase cognitive load and reduce overall productivity.

AI-powered development workflow support

The model context protocol (MCP) server-powered assistant in the VS Code extension puts AI at the center of the content development lifecycle. Built around an embedded MCP server, it transforms the VS Code editor, helping developers scaffold compliant content, catch errors in context, debug faster, and ship reliable automation. Rather than toggling between documentation and editor, developers get environment-aware guidance where they are already working.

With the MCP server-powered assistant, you scaffold content using your organization’s specific templates and standards, so that the resulting content is compliant by design, requiring less rework later. You can run context-aware validation of an Ansible Playbook against a target environment, reducing potential errors in production. You can also quickly locate and reuse existing automation content, including Ansible Content Collections.

As your automation footprint expands, so do the demands of managing the automation itself. Busy administrators are called upon to onboard new team members, answer recurring questions, troubleshoot job failures, grant user access, and maintain the overall health and lifecycle of the platform.

When resources and expertise are scattered across multiple sources (both internal and external), administrators can struggle to find answers they trust quickly. This contextswitching can delay response times and negate some of the benefits found with automation in the first place. This chapter goes over some of the ways that Ansible Automation Platform helps manage those challenges.

The always-on automation expert 

The automation intelligent assistant is a chat-based gen AI service built directly into the Ansible Automation Platform user interface. It helps busy administrators and operators learn about the platform and troubleshoot issues without leaving the environment they’re managing.

Rather than searching through documentation, filing support tickets, or asking a colleague, users can ask the intelligent assistant questions in plain language and receive contextual, referenced answers drawn from trusted Red Hat data sources. Linked references allow users to validate responses, perform research, and expand their knowledge.

The intelligent assistant also supports model provider flexibility through Red Hat AI platforms, OpenAI-compatible models, and more, so organizations can align their AI infrastructure choices with their existing AI investments.

Your organization’s knowledge, built in

Every organization has internal policies and procedures that product documentation does not cover. The intelligent assistant supports “bring-your-own-knowledge” capabilities, allowing administrators to inject internal documents into the service’s retrieval-augmented generation (RAG) pipeline. This means model responses more accurately reflect the enterprise’s specific standards and best practices, and makes sure everyone on the automation team is making decisions and taking action based on consistent information.

MCP server for Red Hat Ansible Automation Platform

The intelligent assistant addresses one half of the platform management challenge: bringing trusted knowledge into the context of where administrators work. But platform management is about more than finding answers for how to use new features or solve issues generally. Understanding and taking action on your unique automation deployment based on real-time conditions requires a different approach.

The MCP server for Ansible Automation Platform offers a fundamental shift in how teams can manage their automation estate. The MCP server allows users to interact with their automation environment directly through natural language prompts using their preferred AI tool (such as Claude, Cursor, or other popular integrated development environments).

Explore 5 use cases for MCP Server for Ansible Automation Platform

Importantly, the MCP server inherits Ansible Automation Platform’s existing security model with the role-based access controls already in place. Administrators can configure the server in read-only mode for safe querying and monitoring, or in read-write mode to allow AI agents to execute jobs and implement changes. Every action the AI agent takes is scoped to the permissions of the authenticated user. Senior administrators spend less time answering routine questions or performing lookups on behalf of others. Newer team members can query the platform, investigate issues, and take action with confidence, bound by the same governance guardrails that apply to every other user.

Creating automation content and managing the platform are essential, but the ultimate purpose of automation is execution. The value of automation is realized when data and intelligence translate into operational outcomes. Incidents are resolved before they introduce risk or outages and compliance is continuously enforced rather than periodically audited.

Act on intelligence By integrating AI into operational workflows, organizations can close the loop between detection and remediation. Using AI-driven insights to inform actions, and automation to execute them instantly, accurately, and at scale, is at the core of AI for IT operations (or AIOps). Importantly, the existing playbooks, roles, and guardrails that enterprises have built through years of task-based, deterministic automation aren’t made obsolete by AI. In fact, they become the governance layer that makes AI-driven operations safe to deploy in production environments. This chapter goes over how Ansible Automation Platform gives you the tools to implement effective AIOps.

Event-Driven Ansible

Event-Driven Ansible closes the gap between incident detection and response. It works with your existing observability and monitoring tools to respond to specific conditions and alerts with predefined actions, without waiting for a human to intervene.

Teams define these responses as rulebooks—i.e., if this event occurs, run this job template. The logic is explicit, the actions are predetermined, and execution happens immediately. For known, repeatable scenarios such as restarting a failing service, clearing disk space, or scaling resources ahead of demand, Event-Driven Ansible turns what used to be a midnight support call to automated, governed response.

Ecosystem integrations

Third-party integrations connect Ansible Automation Platform to the observability, monitoring, and IT service management tools your organization already relies on. Ansible Content Collections provide prebuilt integrations with platforms like ServiceNow, Splunk, Dynatrace, and more. For instance, Red Hat and Splunk recently collaborated to create content and integrations to help boost mean-time-to-resolution (MTTR) and ease management of changing conditions. Together, these collections support “Splunk insights to Ansible action” scenarios.

The path to AI-accelerated automation does not require a wholesale transformation on Day 1. It starts with the automation foundation you already have and builds from there.

If you are running Ansible Playbooks today, you have already begun to codify your operational knowledge. Your playbooks form the living documentation, governance policies, and reusable, trusted code that is the foundation for more advanced forms of automation. From this starting point, you can activate the gen AI capabilities built into Ansible Automation Platform to:

• Help developers create content faster and more reliably.
• Give administrators intelligent platform support.
• Allow engineers to turn observability data and insights into governed action.

Start with a few high-value automation pilots tied to your organization’s top business objectives, then introduce event-driven automation within a single domain. Pilot AIassisted DevOps in low-risk scenarios, then scale as your team’s confidence, trust, and capabilities mature.

Additional resources

Build a trusted automation foundation in the AI era. Explore multimodal automation, automation maturity stages, and the path from task-based to autonomous operations using real-world use cases.

Unlock the full potential of AIOps with automation. Discover how to integrate automation into AI workflows to close the loop between detection and response.

Closing the AIOps gap: Why AI insights need trusted action. View Futurum Research’s paper on the insightto-action gap and how event-driven automation bridges it.