Tool permissions
Give each agent a defined scope.
Evaluate the agent’s identity, delegated authority, target resource and arguments before the tool runs.
Agent tool authorisation
Give AI agents access to production tools with scoped permissions, human approvals and traceable decisions.
01 / Product
Remus places an authorisation check between an agent’s proposed action and the system that can carry it out.
Tool permissions
Evaluate the agent’s identity, delegated authority, target resource and arguments before the tool runs.
Human approvals
Bind a reviewer’s approval to the specific request so a change in amount, resource or parameters calls for a new decision.
Audit evidence
Connect the requesting identity, matched policy, approval and execution outcome in one record.
Product walkthrough
Follow a proposed refund from the agent’s request to the recorded outcome.
Request timeline
Run the refund demoCharge CH-0821 / USD
$49.00Requested refundThe tool waits while a reviewer examines the original charge and proposed amount.
02 / Use cases
Customer record
Policy outcomes
01 / Customer operations
Give a support agent access to the record linked to its assigned ticket. Compare that request with a cross-tenant lookup or a deletion to see what the delegated grant covers.
Explore customer operationsRefund review
Policy outcomes
02 / Financial actions
Let a billing agent prepare a refund while the executor checks the amount and the request’s approval. Compare a small refund, a reviewable refund and one outside the agent’s limit.
Explore financial actionsService incident
Policy outcomes
03 / Internal tools
Give an incident-response agent temporary access to the affected service. Compare the permitted log query with access to another service or a credential change.
Explore internal toolsDeployment model
Map how an agent reaches an action, where its identity comes from, and who holds the credentials. Enforce the decision at a boundary the tool actually honours.
Read the implementation notesEstablish who is acting and the authority they bring.
Verify the request before using a privileged credential.
Reject direct calls that lack the required authority.
03 / Architecture
The trusted executor checks the request and holds the credentials used to call the protected tool.
Direct agent-to-tool path blocked when the endpoint rejects the agent’s credentials. Equivalent credentials or another accessible endpoint need the same enforcement.
04 / Resources
Start from deny by default. Grant a named agent access to a specific action and resource for the duration of a task. For example, let a support agent read customer records in its tenant while withholding deletion privileges.
Carry the agent identity and the user or service it represents separately. Enforce the intersection of the caller’s authority, the agent’s permitted actions and the task scope. Store both identities with the decision.
Record the exact action, arguments and resource under review. Verify the reviewer’s authority, enforce an expiry and check the approved request again before execution. Use a request identifier to prevent a replay.
Try calling the tool directly from the agent environment. Inspect alternate endpoints, available tokens and shared service accounts. If any route grants equivalent authority, remove that access or enforce the same policy there.
Developer sandbox
Try an allowed read, a blocked deletion and a refund that requires approval.