القائمة
Retrieves usage analytics for Relevance AI agents and projects. Use when asked about agent usage, most active agents, execution counts, or usage trends over time.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Manage AI agents, tools & multi-agent workforces on Relevance AI. Use when the user wants to create agents, build tool workflows, orchestrate multi-agent systems, or manage knowledge tables via the Relevance AI API.
Manages Relevance AI agents - creating, configuring tools, writing system prompts, setting up triggers, and running conversations. Use when building agents, attaching tools, debugging execution, or viewing agent results.
Manages Relevance AI tools (studios) - creating transformation workflows, configuring OAuth, running tools, and recovering versions. Use when building tools, adding steps, debugging transformations, or restoring previous versions.
Manages Relevance AI workforces (multi-agent systems) - creating workflows, configuring nodes/edges, triggering execution, and debugging runs. Use when building multi-agent pipelines, connecting agents together, or debugging workforce execution.
Manages Relevance AI knowledge tables - creating tables, adding rows, querying data, and bulk updates. Use when working with knowledge tables, CRM data, or agent data storage.
Manages agent evaluations in Relevance AI - creating test cases, running evaluations, and analyzing results. Use when testing agent behavior, setting up automated testing, or reviewing evaluation results.
| name | relevance-analytics |
| description | Retrieves usage analytics for Relevance AI agents and projects. Use when asked about agent usage, most active agents, execution counts, or usage trends over time. |
Skill for retrieving and analyzing usage data for agents and projects.
📚 Full API Documentation:
https://api-{region}.stack.tryrelevance.com/latest/documentation(replace{region}with your project's region)
Analytics uses relevance_api_request since there's no dedicated MCP tool. This skill shows you how to call the endpoints correctly.
POST /agents/analytics
// Get all agent analytics (no filters)
const analytics = await relevance_api_request({
endpoint: '/agents/analytics',
method: 'POST',
body: { filters: {} },
});
// Filter by specific agent
const agentAnalytics = await relevance_api_request({
endpoint: '/agents/analytics',
method: 'POST',
body: {
filters: {
agentId: { eq: 'your-agent-id' },
},
},
});
// Filter by date range
const rangeAnalytics = await relevance_api_request({
endpoint: '/agents/analytics',
method: 'POST',
body: {
filters: {
insert_date_: {
gte: '2025-01-01T00:00:00.000Z',
lte: '2025-01-31T23:59:59.999Z',
},
},
},
});
{
"states_results": {
"timeseries": [
{
"insert_date_": "2025-01-20T00:00:00.000Z",
"source_type": "agent",
"source_id": "<agent_id>",
"event_type": "state-updated",
"event_value": "running",
"frequency": 5,
"total": 5,
"bucket": "weekly"
}
],
"total_change": { ... },
"change_per_event_value": { ... }
},
"labels_results": { ... },
"tasks_created_results": {
"timeseries": [
{
"insert_date_": "2025-01-27T00:00:00.000Z",
"source_type": "agent",
"source_id": "<agent_id>",
"frequency": 10,
"total": 10,
"bucket": "weekly"
}
],
"total_change": { ... }
},
"last_updated_at": "2025-01-23T00:00:00.000Z"
}
| Field | Description |
|---|---|
event_value: "running" | Agent executed a task |
event_value: "idle" | Agent completed/stopped |
event_value: "pending-approval" | Agent waiting for human approval |
frequency | Count of events in that time bucket |
bucket | Time grouping (e.g., "weekly") |
source_id | Agent ID |
relevance_api_request with POST /agents/analytics and { filters: {} }states_results.timeseries for entries where event_value is "running"source_id (agent ID) and sum frequency to get total runs per agentrelevance_list_agents to get agent names{ filters: { insert_date_: { gte: "2025-12-01T00:00:00.000Z" } } }source_id values from entries where event_value is "running" — these are active agentsrelevance_list_agents and find agents whose IDs are NOT in the active setCall analytics with { filters: {} } and sum the frequency of all entries where event_value is "pending-approval".
Call analytics with { filters: { agentId: { eq: "your-agent-id" } } }. The states_results.timeseries entries with event_value: "running" show weekly run counts via insert_date_ (week) and frequency (count).
| Endpoint | Purpose |
|---|---|
GET /agents/list | List all agents (includes metadata.last_run_date) |
GET /agents/{agentId} | Get agent details by ID |
POST /agents/analytics | Get usage analytics (this skill) |
relevance_list_agents