Red Hat has announced Ansible Automation Platform 2.7 with a new Automation Orchestrator in tech preview. The platform combines task-based, event-driven, and AI-driven automation into a single controlled workflow, enabling organizations to use existing playbooks as the foundation for AI-driven IT operations.
The platform now positions itself as a ‘trusted execution layer’ where AI agents and existing IT automation converge. Not as a replacement for existing workflows, but as the connecting layer that translates AI insights into concrete, auditable actions.
Three modes, one control layer
The Automation Orchestrator enables combining task-based automation (such as server patching), event-driven responses to observability signals, and AI-driven recommendations into a single workflow. Regardless of the origin of an action—whether it’s a human, an event, or an AI agent—everything goes through the same RBAC (Role-Based Access Control) checks, the same approval mechanisms, and the same audit trail.
That is also Red Hat’s governance approach. An AI agent can analyze a situation and recommend an action, but it is always a pre-approved, human-curated playbook that is actually executed on the infrastructure. The level of trust in AI determines how much human approval is required. In a development environment, that step can be skipped; in production, it remains in place by default.
Also check out the video below, in which Red Hat explains how Ansible is evolving into the execution layer for agentic AI. Version 2.7 builds on that with the trusted execution layer.
MCP Server and AIOps Acceleration
Another addition is the Model Context Protocol (MCP) server for Ansible. This allows third-party AI tools and Red Hat’s own AI tools to communicate directly with the platform without custom integrations. Teams inject organization-specific policies and technical best practices into the RAG pipeline, ensuring that AI responses are tailored to their own environment. This “bring-your-own-knowledge” feature builds on Retrieval-Augmented Generation.
For AIOps, Red Hat is introducing opinionated solution guides for partners IBM Instana Observability, ServiceNow, and Splunk. Instead of having to build integrations themselves, teams are provided with a guided starting point that links detection, analysis, and remediation. Red Hat announces that more partners will follow.
Ansible Lightspeed, closely linked to Event-Driven Ansible, is being expanded to other LLMs with version 2.7. This allows organizations to use the model already present in their enterprise.
Tip: Event-Driven Ansible is set to usher in a new era of automation
Self-service, dashboards, and identity management
In addition to the AI integrations, version 2.7 also includes operational improvements. The automation portal features simplified workflows that enable teams to develop and package content faster, including a visual execution environment builder. With the automation dashboard, organizations can view ROI metrics and performance insights directly based on their own data.
In terms of security, the platform now functions as an OpenID Connect (OIDC) authentication provider for HashiCorp Vault. Each task is assigned a short-lived, task-specific token, eliminating the need for static service accounts. This combats credential sprawl and is particularly relevant for organizations operating in zero-trust environments.
Ansible Automation Platform 2.7 will be available in the coming weeks. The Automation Orchestrator will follow later this year.