Originating in Tel Aviv-Yafo, Israel, and now headquartered in the US, Tenet aims to detect and stop dangerous AI agentic behavior in real time.
TenetSecurity.ai was founded by Barak Sternberg (CEO) and Nevo Poran (CTO). The two have an aligned history: working together they previously built Cisco’s AI Defense research team; and both are Unit 8200 alumni. The funding for the seed round is led by the Westly Group (whose previous investments include Tesla, SentinelOne, and Lumina).
The firm operates a patent-pending technology designed to prevent dangerous actions by wanton AI agents, whether they be simple runaway agents or maliciously hijacked agents. Once introduced into a network, agentic behavior becomes largely invisible to the security team, and activity is only visible after the event.
“AI agents may be the biggest productivity unlock enterprises have seen in decades, which is why organizations are moving so quickly to deploy them,” explains Sternberg. “But we’re also entering a world where autonomous agents are interacting with systems, data, and other agents in ways most security tools were never designed to understand. That creates an entirely new security layer that requires a fundamentally different approach to protection.”
Tenet’s goal is to allow companies to reap the benefits of using AI agents without suffering harm from their unknown and uncontrolled (runaway) extracurricular autonomous tendencies occurring during runtime. Malicious activity can also be provoked by external bad actors poisoning the data used by the agent — a process defined by Tenet as ‘agentjacking’.
The danger is aggravated by the speed at which agents operate; by the time security teams see the problem it is too late to prevent it. Tenet uses its own agentic solution to match the speed of other agents. It use a lightweight runtime sensor that simultaneously sees the operating system behavior, the network and API calls, and the agents’ LLM reasoning. Tenet believes that organizations may have up to five times the number of agents running than security teams realize. Defense may not know about the size of their threat, but the Tenet platform sees all agents’ behavior.
If Tenet’s sensor flags a suspicious action, it simulates and predicts the agent’s next move before it can execute. If harmful, it can be stopped before it happens. This is not a rule based activity, but environment provoked reaction founded in the knowledge that preventing a dangerous action is far better than curing its effect.
The threat of agentjacking by malicious adversaries, which can be more harmful than simple agent misbehavior, is validated by research from Tenet’s own Threat Labs. “The research team validated the technique across more than 100 enterprise environments and found thousands of organizations potentially exposed through publicly accessible attack paths,” says Tenet. This attack technique operates without triggering traditional security controls because the agents were acting within their authorized permissions, but they will be stopped by the Tenet platform.
“We’re increasingly seeing AI agents become part of the attack path itself,” says Poran. “Attackers can manipulate agents to access sensitive data, abuse privileges, or take actions on their behalf in ways traditional security tools were never designed to detect. The challenge isn’t simply monitoring prompts or API traffic but understanding and controlling agent behavior in real time. The only place left to catch these threats is at runtime, in the moment an agent decides to act” he adds.
The firm claims success in its early deployments. “One $1 billion ARR legal-sector enterprise increased its use of AI agents from two deployments to more than twenty over a six-month period while using Tenet’s platform. According to the company, more than ten attempted attacks, including a critical XSS attack, were detected and blocked during that period. In another Fortune 1000 enterprise deployment, Tenet identified a runaway AI agent generating tens of thousands of dollars in unnecessary token consumption over a single weekend before it could be scaled more broadly.”
The seed funding is targeted at continued product development, expansion of Tenet Threat Labs, expansion of the company’s North American go-to-market operations, and wider coverage across emerging AI agent frameworks and enterprise environments.
Related: Magnitude Emerges From Stealth Mode With $10 Million in Funding
Related: NewCore Emerges From Stealth Mode With $66 Million in Funding
Related: Aryon Security Raises $29 Million in Series A Funding
