Write the prompt as a monitoring objective, not as implementation instructions. Include the target URL, the user journey, and the observable success criteria.For broader guidance, see Prompt best practices.
Prompt
Go to https://app.example.com/login.Sign in with the test account.Verify that the dashboard loads, the account name is visible, and there are no blocking console errors.
Good prompts include:
The exact page or flow to start from
The expected end state
Important assertions
Known constraints, such as test account behavior
What should count as a failure
Avoid prompts that ask the agent to test too many unrelated paths in one check. Create separate Agentic Checks for separate critical flows.
Agentic Checks do not automatically expose account environment variables to the agent. Add only the variables the agent needs with agentRuntime.exposeEnvironmentVariables.
checkout.agentic.check.ts
import { AgenticCheck, Frequency } from 'checkly/constructs'new AgenticCheck('checkout-flow', { name: 'Checkout Flow', prompt: 'Sign in to the test account and verify that a user can reach the checkout review step.', frequency: Frequency.EVERY_1H, activated: true, agentRuntime: { exposeEnvironmentVariables: [ { name: 'TEST_USER_EMAIL', description: 'Email address for the checkout test account' }, { name: 'TEST_USER_PASSWORD', description: 'Password for the checkout test account' }, ], },})
Do not paste secrets directly into the prompt. Store secrets as Checkly environment variables and expose only the variables the agent needs for this check.
Some applications block automated monitoring unless requests include required headers, test bypass tokens, or feature flags. If your flow depends on a header value, expose that value as an environment variable and say in the prompt which header the agent should send. Do not paste the header value directly into the prompt.
Agentic Checks include a default browser automation skill. You can add extra skills when the agent needs domain-specific capabilities.
agentic-runtime.check.ts
import { AgenticCheck } from 'checkly/constructs'new AgenticCheck('web-quality-check', { name: 'Web Quality Agentic Check', prompt: 'Review the homepage and verify that the main navigation and primary call to action are usable.', agentRuntime: { skills: ['addyosmani/web-quality-skills'], },})
Keep the skill list short. Every added skill expands what the agent can do during execution.
Agentic Checks can run from up to three public locations by default. Enterprise accounts can contact sales to enable unlimited locations.The CLI construct supports these frequencies:
Only active Agentic Checks consume Agentic Check capacity.Use activated: false when you want to deploy an Agentic Check draft without consuming active capacity:
draft.agentic.check.ts
import { AgenticCheck } from 'checkly/constructs'new AgenticCheck('draft-agentic-check', { name: 'Draft Agentic Check', prompt: 'Verify the account settings page loads for a signed-in user.', activated: false,})
You can keep inactive checks in code and activate them later when your account has enough capacity.
If deployment fails because of active capacity, deactivate an existing Agentic Check or purchase enough Agentic Check capacity before deploying the new active check.
