Agent Management

Register, profile, and govern every AI agent in your organization. Track ownership, dependencies, costs, and behavioral health across your entire agent estate.

Overview

Every AI agent that sends traffic through Rivaro gets an agent identity — a persistent record with ownership metadata, behavioral metrics, trust score, and lifecycle status. Agents can be registered explicitly or discovered automatically via the proxy.

Agent Identity

Each agent has the following fields:

Core identity

Field	Description
agentId	Unique identifier in the format ag_<16chars>
agentName	Internal name (e.g. customer-support-bot)
displayName	Human-readable name shown in the dashboard
description	What this agent does
adapterType	Provider the agent uses: gpt-4, claude-3, azure-openai, etc.
appContextId	Linked AppContext (optional — links to provider routing config)

Ownership & accountability

Field	Description
ownerEmail	Email of the person responsible for this agent
ownerName	Owner's full name
businessUnit	Department: Finance, Sales, Engineering, Legal, HR, etc.
environment	DEVELOPMENT, STAGING, or PRODUCTION
agentType	BROWSER, INTERNAL_CUSTOMER_FACING, INTERNAL_EMPLOYEE_FACING, or THIRD_PARTY
modelName	The LLM model used (GPT-4, Claude-3, etc.)

Identity strength

Identity strength reflects how well-verified an agent is. It determines the maximum trust score the agent can earn and serves as a zero-trust signal.

Strength	Criteria	Max trust score
BASIC	Unknown or unresolvable — seen in traffic but not registered	25
STANDARD	Registered agent with no approved assets	50
VERIFIED	Registered and has at least one approved asset	80
STRONG	Approved asset + bound to a verified user identity	95

Status & metrics

Field	Description
status	PENDING_APPROVAL, ACTIVE, QUARANTINED, or TERMINATED
trustScore	0–100. Starts at 0 (zero trust). See Actor Governance
totalSessions	Lifetime session count
totalViolations	Lifetime policy violation count
totalIncidents	Lifetime incident count
firstSeenAt	When this agent first sent traffic
lastSeenAt	Most recent activity timestamp
lastViolationAt	Most recent violation timestamp

Dependency Tracking

Rivaro tracks which assets each agent uses — both declared (code references, IAM policies) and runtime (live traffic observed through the proxy). This gives you a complete picture of what each agent actually depends on versus what it's supposed to depend on.

Observation types

Type	Confidence	How detected
RUNTIME_USAGE	CONFIRMED	Agent sent live traffic to this asset through the Rivaro proxy
CODE_REFERENCE	INFERRED	Found as an import or API call in source code scan
IAM_POLICY	INFERRED	Service account has an IAM permission to access this asset
DISCOVERED	SUSPECTED	Found by a discovery scan in the same environment

Dependency metrics

For each dependency, Rivaro tracks:

• usageCount — number of times the agent has called this asset
• totalCostUsd — cost attribution for calls to this asset
• lastRuntimeUsage — most recent live call timestamp
• firstSeen / lastSeen — observation window

Shadow dependencies

A shadow dependency is an asset the agent calls at runtime but that isn't declared in code or IAM. Rivaro surfaces these automatically. Example: an agent that starts calling a new API endpoint not referenced in its codebase — the dependency shows up in runtime observations but has no code reference.

Blast Radius Analysis

For any asset in your inventory, Rivaro can answer: if this asset goes down or is revoked, which agents break? The blast radius calculation returns:

• Affected agent count
• List of affected agents — with their environment, owner, and last usage
• Impact score — a composite severity score

Use this before decommissioning an asset, rotating credentials, or blocking a discovered endpoint.

Orphaned Agents

An agent is orphaned when it has no assigned owner (ownerId is null). Orphaned agents are a governance gap — violations have no responsible party and incidents have no escalation path.

View orphaned agents at Agents > Orphaned in the dashboard, or via GET /api/agents/orphaned. Assign owners directly in the dashboard or via PUT /api/agents/{agentId}.

Agent Lifecycle

Agents follow this lifecycle:

1. Discovered — first seen in proxy traffic or via discovery scan, status: PENDING_APPROVAL
2. Approved — administrator approves the agent, status: ACTIVE, initial trust granted
3. Active — agent sends traffic, trust score builds or degrades based on behavior
4. Quarantined — risk threshold exceeded, all requests blocked pending review
5. Terminated — permanently blocked; requires admin reactivation to restore

See Actor Governance for the full trust score and escalation mechanics.

Managing Agents

Dashboard

The Agents section of the dashboard provides:

• Full agent inventory with search and filtering by environment, status, business unit
• Per-agent detail: profile, dependency graph, session history, violation timeline
• Access surface summary — what each agent can reach, by asset category
• Production vs. non-production filtering
• Orphaned agent list

Key API endpoints

Endpoint	Description
GET /api/agents	List all agents in the organization
GET /api/agents/{agentId}	Get full agent profile
PUT /api/agents/{agentId}	Update agent metadata (owner, description, etc.)
GET /api/agents/orphaned	List agents with no owner assigned
GET /api/agent-dependencies/{agentId}	Get full dependency graph for an agent
GET /api/agent-dependencies/blast-radius/{assetId}	Get blast radius for a given asset
GET /api/agent-dependencies/shadow/{agentId}	Get undeclared (shadow) dependencies

Next steps

• Actor Governance — Trust scores, quarantine, and termination mechanics
• Sessions — What gets recorded per agent session
• Discovery & Shadow AI — How agents are discovered automatically
• Asset Management — The assets agents depend on