STACK
MENU

How STACK works

Overview

Most agent deployments today are assembled from several separate systems: an identity provider, a secrets manager, an API gateway, policy checks and logging. Those products can all perform their own function correctly without sharing a common view of the work the agent was authorised to do. A request may therefore be valid at the gateway, and a credential may be valid at the secrets manager, even though the action itself has moved beyond the original job.

STACK gives each agent a Passport that provides that shared view. It carries references to the approved work, the authority behind it and the identity records involved, along with the services, actions and limits available to the agent. Credential use, runtime decisions and the resulting record stay connected to it while the agent is working. The same state can be used to stop the agent or reconstruct what happened.

Separate identity, credential, gateway, policy and logging systems reorganise around one Passport. The agent presents the Passport before runtime checks allow a request to reach an external system. Secrets feed credential access, policy feeds the runtime check, and Drop-offs, Skills and evidence remain connected to the same record.
AGENT
EXTERNAL
SYSTEM
IdentityAgent known
SecretsCredential valid
GatewayRequest valid
Approved job: unknown
PolicyRule passed
LogsEvents collected

Run your agent through STACK.

stack | Product