You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
From the beginning, Checkly has bet on [Monitoring as Code](/concepts/monitoring-as-code) which lets you create and control your monitoring infrastructure entirely using code. [Checkly constructs](/constructs/overview) can reflect all your monitoring properties.
10
+
From the beginning, Checkly has bet on [Monitoring as Code](/concepts/monitoring-as-code) which lets you create and control your monitoring infrastructure entirely using code.
11
+
12
+
By default, [Checkly constructs](/constructs/overview) reflect all your monitoring properties.
**The Monitoring as Code workflow is by default AI-native** because LLMs are excellent at writing and editing Checkly constructs code and modern AI agents can execute CLI commands easily.
38
40
39
-
You only need to provide the necessary context about Checkly and your monitoring setup to your AI agent of choice.
40
-
41
-
## Add custom Checkly rules to your AI conversation
41
+
Provide the necessary Checkly context and let your AI agent of choice do the rest.
42
42
43
-
The [`checkly.rules.md` file](https://www.checklyhq.com/docs/ai/checkly.rules.md) includes best practices, example code and required CLI commands to give your AI workflow enough context to perform Checkly-related tasks.
43
+
<AgentExamples />
44
44
45
-
Once the Checkly rules are included in your AI context window, your agent can effectively assist you in managing your monitoring setup.
45
+
## Add Checkly context to your AI agent conversation
46
46
47
-
It will be able to:
48
-
49
-
<Cardtitle="Create new checks, alert channels or other constructs"horizontal>
50
-
"Can you create a new `BrowserCheck` monitoring `example.com`"
51
-
</Card>
47
+
Install [Checkly Skills](/integrations/ai/skills) or add the [Checkly Rules](/integrations/ai/rules) to your AI conversation to give your AI agent enough context to perform Checkly-related tasks.
52
48
53
-
<Cardtitle="Gather information about the current monitoring setup"horizontal>
54
-
"What are the currently used monitoring locations?"
Include the entire Checkly context in commands or documentation.
59
56
</Card>
57
+
</Columns>
60
58
61
-
With enough application context you can even create checks for your specific use cases.
59
+
### Skills vs Rules
62
60
63
-
<Cardtitle="Analyze application code and create the monitoring setup"horizontal>
64
-
"Can you create new API Checks for the application API endpoints?"
65
-
</Card>
66
-
67
-
Find a live session explaining how to automate Checkly monitoring with AI below and [read the "Agentic Workflows" guide](/guides/agentic-workflows) for more details.
61
+
**Use Skills** when your AI agent supports the [Agent Skills](https://agentskills.io) standard. Skills load context on demand, keeping your agent's context window lean until Checkly-related tasks arise. This is the recommended approach for compatible agents.
68
62
69
-
<YoutubeEmbedid="WqTXa7GCk-k"title="No Coding! Just Prompting! Getting the most out of AI for Application Reliability." />
63
+
**Use Rules** when your agent doesn't support skills or when you want the Checkly context always available. Rules files are loaded at session start and provide consistent context throughout your conversation.
70
64
71
65
72
-
## Why is there no Checkly MCP server?
66
+
## Why is there no Checkly MCP server (yet)?
73
67
74
68
The MCP concept is often used to enable LLMs to interact with external systems. It acts as a bridge between the AI model and the target system, translating natural language commands into actionable API calls or code snippets.
75
69
76
70
**With Monitoring as Code, Checkly already provides a native way to control your monitoring infrastructure via code and the command line.**
77
71
78
72
Whether you need to create new resources or update existing ones, AI can write and update the necessary construct files and execute the Checkly CLI commands autonomously.
79
73
80
-
## Additional Resources
81
-
82
-
Follow these guides if you use one of the popular AI coding tools:
83
-
84
-
-[Claude Code](/integrations/ai/claude)
85
-
-[Cursor](/integrations/ai/cursor)
86
-
-[GitHub Copilot](/integrations/ai/copilot)
74
+
<Tip>
75
+
We are researching additional AI-native workflows. [Let us know in the public roadmap](https://feedback.checklyhq.com/p/checkly-mcp) if you are interested in more agent-friendly integrations.
The [`checkly.rules.md` file](https://www.checklyhq.com/docs/ai/checkly.rules.md) includes best practices, example code and required CLI commands to give your AI workflow enough context to perform Checkly-related tasks.
11
+
12
+
Once the Checkly rules are included in your AI context window, your agent can effectively assist you in managing your monitoring setup.
13
+
14
+
It will be able to:
15
+
16
+
<AgentExamples />
17
+
18
+
With enough application context, you can even create checks for your specific use cases.
19
+
20
+
<Cardtitle="Analyze application code and create the monitoring setup"horizontal>
21
+
"Can you create new API Checks for the application API endpoints?"
22
+
</Card>
23
+
24
+
Find a live session explaining how to automate Checkly monitoring with AI below and [read the "Agentic Workflows" guide](/guides/agentic-workflows) for more details.
25
+
26
+
<YoutubeEmbedid="WqTXa7GCk-k"title="No Coding! Just Prompting! Getting the most out of AI for Application Reliability." />
27
+
28
+
## Claude Code
29
+
30
+
Claude Code reads instructions from `CLAUDE.md` files. You can place these files globally (in your home directory) or locally (in your project root). Claude Code automatically includes these files in its context.
31
+
32
+
To use Checkly rules with Claude Code, download the rules file and reference it in your `CLAUDE.md`:
Restart your Claude Code session to load the instructions.
56
+
57
+
## GitHub Copilot
58
+
59
+
GitHub Copilot reads project-level instructions from `.github/copilot-instructions.md`. This file is automatically included in Copilot's context for all chat interactions.
Cursor uses `.mdc` (Markdown Cursor) files stored in `.cursor/rules/` for project-specific instructions. These rules are automatically included in Cursor's context.
0 commit comments