Beta
Oso for Agents
Authorization, monitoring, alerting, and access throttling for AI agents.
LLM agents make permissions harder
Permissions are already hard enough: broken access control rose to #1 in the OWASP Top 10 list of AppSec failures. The explosion of agents increases the attack surface.
A human with incorrect permissions is bad enough, but an LLM agent can potentially cause orders of magnitude more damage.
We have the opportunity, however, to rethink permissions and avoid making the same mistakes again.
Agentic AI can do amazing things, but you need to give agents access to your systems for them to work. That’s risky:
Humans are often overprovisioned, and replicating that for agents can be disastrous
Humans work on the scale of wall clock time and waking hours, while agents move faster and don’t stop
Agents may or may not follow controls applied in prompting and are vulnerable to prompt injection
Agents need a new approach
Oso for Agents gives teams hardened runtime guardrails that keep agents from going rogue:
- Monitor agent actions, assess risk continuously, and raise alerts on anomalous behavior.
- Define and enforce what agents can do using deterministic policies.
- Take one-click actions to throttle access, quarantine actions, or apply time-bound privileges.
- Log every decision: full audit trail, full visibility, full accountability for agent interactions.
Oso for Agents
Schedule time with Graham Neray, Oso’s founder, to learn more about automated least privilege enforcement for agents and our private beta program.
.png)