Mirantis Announces Agent Platform That Strengthens Human Oversight of Production AI Agents

Business Wire

KUBECON—Mirantis, delivering open, standards-based infrastructure for the next generation of AI clouds, today announced the general availability of Mirantis Agent Platform that gives organizations a self-hosted, governed environment for running AI agents in production on Kubernetes.

Mirantis is pairing the Agent Platform with Forward Deployed Engineering (FDE), in which senior Mirantis engineers work directly with client teams to design, integrate, and operationalize custom agents.

Announced at KubeCon + CloudNativeCon North America 2026, Mirantis Agent Platform helps platform engineering, site reliability engineering (SRE) and IT operations teams control agent access, enforce spending limits and track agent actions while maintaining human approval over operational fixes.

AI agents can help operations teams detect and resolve infrastructure problems faster, but moving them into production introduces questions: what an agent can touch, how much it can spend and who is accountable when it acts. Nearly half (49.8%) of organizations surveyed by Salt Security confirmed or suspected that an AI agent took an action in the past year that no one intended or authorized, yet only 17.5% can automatically stop a misbehaving agent in production. In a survey of 300 U.S. CISOs and CSOs by Agen.co by Frontegg, 78% said their organizations have pulled permissions from an AI agent running in production. Mirantis Agent Platform addresses these risks with sandboxed, policy-governed execution and human oversight built in.

“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.”

The need for stronger controls is growing as enterprises evaluate agentic AI. In many organizations, security and compliance concerns over autonomous agents have kept them from moving forward into production. Mirantis Agent Platform delivers the controls that organizations need to manage agent execution at scale.

Key capabilities:

Policy-based governance and sandboxed isolation – Define what each agent can access and run each one in an isolated sandbox to limit unauthorized or unintended activity.
Configurable spend caps – Set spending limits at the organization, project and agent levels to control financial exposure.
Full audit trails – Record every agent action to support operational reviews, incident investigations and compliance.
One-click cut network access – Cut off network access for all agents at once when administrators need to intervene.
Human-approved remediation – Require a person to approve proposed fixes before agents apply them.

From issue detection to approved remediation

Mirantis Agent Platform supports Mirantis’s built-in Prism agent and third-party agents customers already use. For infrastructure operations, it proactively detects production issues, diagnoses root causes and proposes fixes. Once a person approves a proposed fix, the agent applies it, helping teams move from investigation to remediation while retaining control over changes.

The platform also integrates with existing developer tools for direct agent management so that the Mirantis Agent Platform can serve as a single dashboard over every agent in the organization.

“Detecting a problem is only the beginning of an operations workflow,” said Lee Xie, product manager for Mirantis Agent Platform. “Teams also need to understand the proposed fix, decide whether to approve it and review what happened afterward. By connecting agent execution with human approval and a full audit trail, we make it safe for teams to put AI agents to work in production operations.”

Forward Deployed Engineering to get agents into production

Mirantis Forward Deployed Engineering embeds senior Mirantis engineers with customer teams to design, integrate and operationalize custom agents, then hands the platform to the customer team to run.

Availability and KubeCon demonstrations

Mirantis Agent Platform is generally available. Attendees can visit Mirantis at Booth 232 during KubeCon + CloudNativeCon North America, November 9–12 in Salt Lake City, or schedule a one-to-one demo.

About Mirantis

Mirantis delivers the fastest path to scalable, efficient GPU cloud infrastructure for neoclouds and enterprise AI factories, with full-stack AI infrastructure technology that removes complexity and streamlines operations across the AI lifecycle, from Metal-to-Model. Through k0rdent AI and strategic partnerships, Mirantis helps organizations maximize GPU utilization, improve cloud economics, and accelerate time to revenue with production-grade multi-tenancy, intelligent workload orchestration, and automated operations.

Mirantis serves many of the world’s leading enterprises, including Adobe, Ericsson, Inmarsat, MetLife, PayPal, and Societe Generale. Learn more at www.mirantis.com.

Mirantis is a registered trademark of Mirantis, Inc. Metal-to-Model is a trademark of Mirantis, Inc. All other trademarks are the property of their respective owners.