Enforce organizational control on every agent.

Policy, authorization, audit and traceability for the teams responsible for keeping agent adoption within the organization's boundaries.

Security can't be reimplemented by every team.

When each department secures its own agents, the organization ends up with as many security models as there are frameworks in use. A requirement approved once shouldn't need a separate implementation for every technology.

Policy enforced at the boundary, before the call, instead of explained afterwards.

Define once. Enforce everywhere.

The controls security teams expect to have.

Policy enforcement

Enforce security requirements centrally, not team by team.

Authorization

Define which agents can reach which models, tools, data and systems.

Audit trails

Maintain traceability over configuration changes and runs.

Traceability

Understand how an agent evolved and who changed it.

Isolation and encryption

Role-based access, tenant isolation and data encrypted per data subject.

Know Your Agent: the risk questions, the kernel's answers.

Who is it and what is it for?

Identity per version, artifact digest, declared purpose and approval.

What does it access?

Declared tools and data; credentials from the vault, scoped and just in time.

What does it do alone and what does it ask a human?

Pause and approval are language effects, ask and approve, written in the code.

What limits does it have?

Guardrails, budget, token cap and policy, enforced at run time.

How does it record every decision?

A hash-chained append-only trail, with a decision id and every external effect.

How does it detect drift?

Fail-closed tool contracts, limits and continuous evaluation.

How does it stop?

Pause, step-through, breakpoint and a kill switch that cancels in-flight runs.

Agent passport: one record per agent and environment, each answer marked declared, enforced or not covered. Deployment to production is blocked if the passport does not allow it.

Inside the institution's own cloud.

Three ways to deploy: shared cloud, tenant isolation, or dedicated in the institution's own account, with its keys and a role it can revoke.

Security is the operating layer's job.

The AgentOS for regulated operations.

An Agent Kernel that schedules, isolates, persists, protects and accounts for every agent running on it, at massive scale, including in the institution's own cloud.

By submitting, you agree to receive the Tessera newsletter, as described in the Privacy Policy. You can unsubscribe at any time.