Cequence Security has launched Agent Personas in its AI Gateway, adding infrastructure-level controls designed to govern what autonomous AI agents are allowed to do inside enterprise systems.
The launch addresses a growing problem as organisations connect AI agents to enterprise applications through the Model Context Protocol, or MCP. Cequence said many businesses are treating authentication as if it were sufficient control, even though agents inherit the privileges of their users and can act on those permissions without human judgement about when not to use them.
Agent Personas is designed to narrow that gap by using a plain-English job description to define a scoped virtual MCP endpoint for each agent role. Cequence said a customer service AI agent can be limited to read-only CRM access rather than record changes, while a coding agent can read GitHub issues and create Jira tickets without being able to merge pull requests. A CI/CD automation agent can be restricted to named pipeline tools and a single notification channel.
The release also introduces Agent Access Keys, which Cequence describes as a composite credential built for headless agents running in automated workflows. Each key binds agent identity, user identity, and persona-level privileges into one attributable credential. The platform also adds per-tool policy enforcement, including rate limits, data masking, approval workflows, and a full audit trail showing which agent acted, on whose behalf, at what time, and under which permissions.
Cequence cited Gartner research arguing that the main risk in securing agents lies in what AI does, rather than what it says. The company also said more than 80% of Fortune 500 companies now deploy active AI agents, while only 47% have AI-specific safeguards in place. Many enterprises have already invested in AI platforms, but remain cautious about connecting autonomous systems to live applications and data.
“Enterprises have made massive investments in AI, and the race to put agents into production across customer experiences, employee workflows, and business operations is accelerating fast,” said Ameya Talwalkar, CEO and Co-Founder at Cequence. “However, security, governance, and scale requirements can’t be ignored. Cequence closes the gap that has been holding organisations back by automatically limiting agent tool access which lowers costs, enhances performance, and improves security.”
Cequence said early deployments are already being used in complex environments. One major US telecommunications provider used the technology to stop agents crossing boundaries in tools including GitLab, Confluence, Jira, and Slack, using scoped virtual endpoints to restrict each agent to the systems it needed without adding extra infrastructure.
The company added that AI Gateway now supports more than 140 verified enterprise application integrations. Cequence said its broader platform protects more than 10 billion daily API interactions and four billion user accounts.
“AI agents have quickly become a channel as significant as the web or mobile, powering customer commerce, employee productivity, and autonomous operations all at once,” said Shreyans Mehta, CTO and Co-Founder at Cequence. “Agent Personas is how you govern infrastructure access at the agent level, enforcing exactly what each agent can do down to the specific API endpoint, across any model or platform. It is the control plane enterprises need to confidently and securely enable agentic AI access to applications and data.”
You must be logged in to post a comment.