The IT Nerd

Teleport today announced that it has expanded its Identity Security platform with three new capabilities designed to ensure that agent behavior 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. 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 authorized 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. 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 summarizes 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 behaviors.
  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.
  

Availability

Teleport will preview these capabilities at Black Hat USA 2026 (August 4–6, Mandalay Bay, Las Vegas) at booth #5114. The capabilities will be available for hands-on customer experience this fall. Customers can request to join the technology preview here.

For a deeper discussion on the new Identity Security capabilities, read the blog.

Teleport today announced Beams, a trusted runtime designed to solve the security and IAM challenges blocking teams from designing and running AI agents in production infrastructure. Beams runs each agent in an isolated Firecracker VM with built-in identity. Each Beam is connected to infrastructure and inference services without secrets, with audit and access control.

Beams addresses a key challenge engineers face when designing agentic workflows for infrastructure. Engineers want to develop, test and deploy agents, but they need to do this in a secure environment. Today, launching agents means stitching together IAM, infrastructure, and secrets by hand — with no consistent identity, no visibility into agent actions, and every team building its own container or VM workflows from scratch. Beams eliminates that operational drag by providing ephemeral, isolated environments that are fast to start, locked down, and wired into Teleport’s identity and audit trails.

Each Beam runs in a Firecracker VM with full file system and networking isolation. Beams inherit delegated identity so they can authenticate to registered services and inference endpoints without using secrets, with fine-grained networking control over external and internal services. Every action is audited, giving teams full visibility into what agents access and when.

Beams are built for a range of agentic use cases — from internal agents that need access to production services, to agentic ephemeral workflows where developers build against staging without exposing secrets, to multi-agent production pipelines requiring hardened, reproducible isolation.Beams will launch as an MVP on April 30, 2026. Engineers interested in early access can register at https://www.beams.run.

Teleport will demonstrate Beams at both RSAC (Booth S-3111) and KubeCon (Booth 840) during the week of March 23.