---
title: Common workflows
description: >-
  Learn the standard tool sequences for running tests, creating monitors,
  querying metrics, and investigating incidents on the platform.
sidebarTitle: Workflows
lastUpdated: "2026-09-23"
---

> **For AI agents:** the complete documentation index is at [llms.txt](/llms.txt). Append `.md` to any page URL for its markdown version.

These recipes show the tool order for the tasks agents run most often. Each step names the tool to call.

<Tip>
  Before a multi-step task, call `platform_guide` with the relevant topic (for example `test_creation` or `metrics`). It returns the up-to-date sequence and prerequisites straight from the server.
</Tip>

## Run a test

<Steps>
  <Step title="Find the test">
    `list_tests` with a product slug, or `search_collections` to find it in the folder tree.
  </Step>
  <Step title="Check what it needs">
    `get_test_detail` to see required input variables and owners.
  </Step>
  <Step title="Build and run a campaign">
    `build_campaign` to assemble the run (pass a `variants` array to pick an environment), then `run_campaign`.
  </Step>
  <Step title="Read the result">
    `poll_execution` until it finishes, then `get_execution_detail` for per-test pass/fail data.
  </Step>
</Steps>

## Create a monitor

<Steps>
  <Step title="Pick the test and environment">
    `list_tests` for the test id, and `list_variable_groups` for the variable group that holds your environment.
  </Step>
  <Step title="Create the monitor">
    `create_monitor` with the product, test id, variable group, and schedule.
  </Step>
  <Step title="Activate or pause">
    `toggle_monitors` to turn monitors on or off in bulk.
  </Step>
</Steps>

## Query metrics

<Steps>
  <Step title="Explore the schema">
    `query_metrics` with `SHOW MEASUREMENTS` and `SHOW FIELD KEYS` to discover what is collected.
  </Step>
  <Step title="Query the series">
    `query_metrics` with a `SELECT` to read KPI time series, then `compute_slo` or `correlate_metrics` for deeper analysis.
  </Step>
</Steps>

## Investigate incidents

<Steps>
  <Step title="Check overall health">
    `get_incident_counter` for a quick critical / warning / closed count.
  </Step>
  <Step title="List and inspect">
    `list_incidents` filtered by status, then `get_incident` for detail.
  </Step>
  <Step title="Resolve">
    `close_incident` once the underlying issue is handled.
  </Step>
</Steps>

## What's next?

<Columns cols={2}>
  <Card title="Tools reference" icon="robot" href="/mcp/tools/overview">
    Look up the exact parameters for each tool above.
  </Card>
  <Card title="Core concepts" icon="sitemap" href="/mcp/concepts">
    Variables, variants, edit budgets, and the safety model.
  </Card>
</Columns>