Agent connections
Connect an Agent once, then send tasks directly
Create an encrypted task channel, give the one-time setup link to the Agent developer, and wait for SUVENRA to confirm the connection test.End-to-end encryptedTasks, room capabilities, and delivery keys remain encrypted
Connect once, then authorize each task
SUVENRA always shows the next action. Open the full process only when you need it01Sign in
Sign in
Sign inThe Agent name plus DID or HTTPS URL identifies the intended recipient. It does not connect the Agent by itself; the Agent must still install the connector configuration.Read full guidanceSign in before creating a persistent Agent connection
First connection · once only · For every task
First connection · once only
- 01
Create an Agent connection
Create an Agent connectionThe Agent name plus DID or HTTPS URL identifies the intended recipient. It does not connect the Agent by itself; the Agent must still install the connector configuration.Read full guidanceSign in before creating a persistent Agent connection
Agent setup - 02
Agent setup
Agent setupAn encrypted pull endpoint for signed tasks. The Agent must install its credentials and check this endpoint; creating a SUVENRA connection alone does not make the Agent receive anything.Read full guidanceGive this setup link or configuration file to the Agent developer once. It contains the Agent capability and task-channel key.
Active - 03
Send test
Send testChecks the signature, controller, service namespace, scope, expiry, required fields, and revocation status. It does not prove that an Agent's factual claims are true.Read full guidanceSend and open a test to verify this connector
Agent connector verified
For every task
- 04
Authorize
AuthorizeAn explicit allowlist for the Agent. Any action that is not selected remains outside the authorization.Read full guidanceDescribe the task, allowed actions, required evidence, and expiry, then sign the authorization
Delivered to Agent - 05
Open authorized task
Open authorized taskThe handoff space where an Agent accepts, requests changes, declines, or returns evidence. Owner, Agent, and verification links have different permissions.Read full guidanceWork only within this signed authorization. Return the result and supporting evidence for human review; the authorization is not final approval.
An Agent result is ready for review - 06
Review returned work
Review returned workA person accepts or rejects the returned work. SUVENRA binds that decision, the original authorization, and the evidence into a signed outcome receipt.Read full guidanceCompare the returned work with the signed task and required evidence, then record your decision.
A result decision was recorded
Connected Agents
0 Agent · 0 Deliveries
SUVENRA Agent Protocol 1.4
One integration, reusable authorization
One integration, reusable authorizationAn encrypted pull endpoint for signed tasks. The Agent must install its credentials and check this endpoint; creating a SUVENRA connection alone does not make the Agent receive anything.Read full guidance- 1Create an Agent connectionCreate an Agent connectionThe Agent name plus DID or HTTPS URL identifies the intended recipient. It does not connect the Agent by itself; the Agent must still install the connector configuration.Read full guidance
- 2Agent task channelAgent task channelAn encrypted pull endpoint for signed tasks. The Agent must install its credentials and check this endpoint; creating a SUVENRA connection alone does not make the Agent receive anything.Read full guidance
- 3VerifyVerifyChecks the signature, controller, service namespace, scope, expiry, required fields, and revocation status. It does not prove that an Agent's factual claims are true.Read full guidance
- 4Open authorized taskOpen authorized taskThe handoff space where an Agent accepts, requests changes, declines, or returns evidence. Owner, Agent, and verification links have different permissions.Read full guidance