Cohesity’s new Agent Resilience lets companies roll back AI agents that go wrong

Data security company Cohesity Inc. today introduced Cohesity Agent Resilience at its Catalyst conference.

The new Cohesity Data Cloud capability backs up the memory and configuration of enterprise artificial intelligence agents so they can be rolled back to a trusted state when something goes wrong. Also on the Catalyst agenda was a plan to automate Cohesity’s five-step cyber resilience framework with agentic workflows, and an early piece of that plan is generally available now. A free course on AI agent risk opens the new Cohesity AI Resilience Academy.

Agents inside large companies already query databases and act with privileged credentials, sometimes with nobody reviewing each step. Governance and observability tools can flag unexpected behavior. According to Cohesity, those tools have no way to restore the data or systems an agent has changed, corrupted or deleted.

“Detection can tell you an AI agent went off course,” said Vasu Murthy, Cohesity’s chief product officer. “It cannot undo the changes.”

Most organizations are not protecting agent state today, Cohesity said in a blog post introducing Agent Resilience, and a prompt injection can leave an agent that looks normal on the surface acting on information it should never have trusted. An agent with no clean recovery point may have to be wiped and rebuilt. Memory and configuration are covered at launch, protected by the same immutable backups and clean-room recovery Cohesity already runs for on-premises, cloud and software-as-a-service workloads.