Teleport has introduced enhancements to its Identity Security platform, integrating three new capabilities: Beams Session Summaries, Agentic Classifiers, and Risk Scoring. These advancements aim to maintain agent activities within preset limitations, especially as autonomous agents gain more responsibilities in production infrastructure.
The introduction of these features follows Teleport's recent white paper, "From Zero Trust to Agent Trust," which discusses the insufficiency of zero trust principles in managing agents at scale. The paper expands on zero trust's core tenets by proposing three corresponding principles of agent trust:
- Verify explicitly → Enforce continuously: Agents necessitate a unique, attestable identity, operating within a trusted runtime that enforces operating, execution, and communication boundaries.
- Use least privileged access → Bound collective autonomy: Actions safe on an individual level may require escalation when executed collectively by multiple agents.
- Assume breach → Assume misalignment: Continuous monitoring of agent actions is essential, allowing real-time intervention when agents deviate from their intended goals.
Enhancing identity security platform
Teleport's capabilities are integrated with Beams, its trusted runtime for agents, supporting an augmented Identity Security platform:
- Beams Session Summaries: Summarises an AI agent's actions, documenting its identity, privileges, and activities such as API calls and prompts, to establish a behavioural baseline.
- Agentic Classifiers: Enables the evaluation of behaviour against company-specific criteria, highlighting discrepancies with agents' stated objectives.
- Risk Scoring: Automatically assesses SSH, Kubernetes, and database sessions for risk levels, allowing for the identification of specific commands or actions through the MITRE ATT&CK framework.
Ensuring continuous monitoring
Combined with Beams, these features help establish the principles of agent trust, offering agents a continuously monitored cryptographic identity. They reveal both collective and individual risks, equipping enterprises to address any misalignment in real-time.
Ben Arent, Director of Product at Teleport, notes, "The capabilities we're announcing today are the operational harness for agent trust: they let enterprises see what an agent actually did, classify whether that behaviour is expected, and score the risk of what it might do next."
Teleport, the AI Infrastructure Identity company, announces that it has expanded its Identity Security platform with three new capabilities designed to ensure that agent behaviour remains within defined boundaries: Beams Session Summaries, Agentic Classifiers, and Risk Scoring. Together, these capabilities give enterprises a foundational harness for identifying and preventing agent misalignment as autonomous agents take on greater responsibility inside production infrastructure.
The announcement follows Teleport's recent white paper, From Zero Trust to Agent Trust, which argues that zero trust is necessary but insufficient to govern agents operating at scale.
Corresponding principles of agent
The paper extends the three core principles of zero trust into three corresponding principles of agent trust:
- Verify explicitly → Enforce continuously. Agents need a unique, attestable identity and must operate inside a trusted runtime that architecturally enforces their operational, execution, and communication boundaries.
- Use least privileged access → Bound collective autonomy. Individually authorised actions can still be collectively destructive when taken by a swarm of agents acting in parallel. Bounding collective autonomy means actions that are safe individually but risky in aggregate require escalation before they execute.
- Assume breach → Assume misalignment. Agents can drift from their original objective through adversarial manipulation or through unintentional causes, like context shift over time. Enterprises must continuously monitor for that drift and be able to intervene in real time.
Identity security platform
Teleport's new capabilities are delivered through Beams, Teleport's trusted runtime for agents, working in concert with its Identity Security platform, now extended to address agentic behavior:
- Beams Session Summaries are a summary of an AI agent's actions: its identity, privileges, tool and API calls, LLM prompts, responses, and reasoning digested into a short human readable summary of what it was doing and what it was thinking. This establishes a behavioral baseline for evaluating agent activity against its declared objective.
- Agentic Classifiers provide policy for humans, agents or groups of agents to be evaluated against company specific criteria, enabling agent behavior to be flagged that is inconsistent with an agent's declared objective.
- Risk Scoring automatically summarises SSH, Kubernetes, and database sessions, classifies them by risk level and maps actions to the MITRE ATT&CK framework. Infrastructure and Security teams can now automate or manually search across sessions for specific commands, resources, or behaviours.
Continuously monitored identity
Together, these three capabilities in concert with Beams lay the foundation for the agent trust principles: they give agents a cryptographic, continuously monitored identity; they make collective and individual risk visible before action is taken; and they give enterprises the tooling to detect and respond to misalignment as it happens, turning "assume misalignment" from a design principle into a running practice.
"The capabilities we're announcing today are the operational harness for agent trust: they let enterprises see what an agent actually did, classify whether that behavior is expected, and score the risk of what it might do next," said Ben Arent, Director of Product at Teleport. "Zero trust assumes the actors inside the architecture are human, bounded, and verifiable at the point of access. Agents break that assumption. They're not predictable, and a swarm of individually authorised actions can add up to an outcome no one sanctioned."
