Observed arrival · 2026-09-01
Agent Mandate API: Signed Authority for Agent Actions
An API for defining, verifying, and auditing what consequential actions an AI agent is allowed to take.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
Field notes
The visible example represents authority as structured data: a principal, named agent, action, resource, expiry, currency, aggregate cap, per-action limit, and approval threshold. Its sample transfer requests 30,000 minor units against a 25,000 approval boundary, making the policy decision concrete rather than hypothetical. The homepage says the response includes the governing clause and an audit digest, while also stating that the no-key demo stores nothing.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
$PaidCommerce or pricing visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue