Know which AI agent did what, and prove it.
When an agent changes a record, refunds an order or reads customer data, “the AI did it” will not satisfy your security team or your customers. Agent Identity gives every agent a verifiable identity on each call it makes and each action it records, issued by the identity provider you already run.
Start with a name, then upgrade to proof.
Identity is not the model’s API key. It answers a different question — who is acting — so it can be attributed, authorized and audited.
Local identity
A stable id, a display name, an owner and metadata, asserted by the process itself. Free, instant, and enough to answer “which agent did this?” across a fleet — in traces, audit entries, runtime journals and every tool call.
AgentIdentity("billing-bot", owner="payments")Verifiable identity
Backed by your platform’s identity provider, which mints a short-lived signed JWT. The agent presents it to the resources it calls, so they verify the caller instead of trusting a self-asserted id — and one identity can carry a credential per audience.
identity.get_credential("api://billing")Use the identity platform you already trust.
No new directory to run, no secrets to rotate yourself: the credential comes from the identity provider you already have. AgentIdentity.auto() detects which one you are on.
Microsoft Entra ID
Identity source: IMDS, or the federated token file on AKS. The credential is short-lived and refreshed before it expires; nothing long-lived is stored by Promptise, and persistence stays in your IdP.
AgentIdentity.from_entra("billing-bot", resource="api://mcp")Set it once, and it follows the agent everywhere.
Observability
Every LLM turn and tool call in the trace carries the agent id — filter a fleet’s activity by who acted.
MCP calls
A verifiable identity presents its signed credential to the servers it calls, scoped per resource.
Approvals & audit
Approval requests and HMAC-chained audit entries name the agent, not an anonymous process.
Runtime & delegation
Runtime journals, escalations and cross-agent messages all carry it, so a fleet stays attributable.
This page is general technical information, not legal, regulatory or compliance advice. Using Promptise does not by itself make you or your product compliant with any law or standard — consult a qualified professional before relying on anything here.
Give your agents a name your systems can verify.
Start with a local identity today and move to a verifiable one when a resource needs proof.