SALT LAKE CITY -- Mirantis announced at KubeCon + CloudNativeCon North America 2026 the general availability of Mirantis Agent Platform, a self-hosted, governed environment for running AI agents in production on Kubernetes. The company is pairing the platform with Forward Deployed Engineering (FDE), in which senior Mirantis engineers work directly with customer teams to design, integrate and operationalize custom agents before handing the platform over to them.
The platform is aimed at platform engineering, site reliability engineering (SRE) and IT operations teams that want to control agent access, enforce spending limits and track agent actions while keeping human approval over operational fixes. Key capabilities include policy-based governance with sandboxed isolation for each agent, configurable spend caps at the organization, project and agent levels, full audit trails of every agent action, a one-click control to cut network access for all agents at once and human-approved remediation.
From Issue Detection to Approved Remediation #
Mirantis Agent Platform supports the company’s built-in Prism agent as well as third-party agents customers already use. For infrastructure operations, it detects production issues, diagnoses root causes and proposes fixes, which an agent applies only after a person approves them. The platform also integrates with existing developer tools so it can serve as a single dashboard over every agent in an organization.
“Enterprise AI adoption is losing momentum not because models lack intelligence, but because organizations lack governance and execution support,” said Ronen Kofman, vice president of product management at Mirantis. “By combining sandboxed execution and real-time human oversight in the Mirantis Agent Platform with Mirantis Forward Deployed Engineering, we’re providing the guardrails that organizations need to run AI agents safely in production.”