How Checkly uses AI

Checkly uses AI to enhance our monitoring and testing capabilities. Checkly’s AI features are always opt-in. You can opt in on the AI settings screen.

We focus the use of AI on three following areas:

1. Check creation: use AI to quickly generate checks based making it quicker and easier to set up monitoring for new applications or features.
2. Check failure triage: use AI to analyze check failures and provide insights into impacted users and features, helping teams quickly identify and resolve issues.
3. Check failure remediation: use AI to propose remediation steps for check failures, reducing the time spent on troubleshooting and improving overall system reliability.

All AI features are designed to operate on the data you provide or the data generated by your checks. This data is already stored in Checkly, and we do not send any additional data to third-party AI providers.

Any provided environment secrets are scrubbed before being sent to the AI provider.

We do not train any custom models on your data. Any data used by the AI features is processed in real-time and not stored for future use. To address further privacy concerns, you can bring your own AI model and provider to Checkly. For more information, see the section below on built-in and custom models.

By default, Checkly uses OpenAI’s GPT-4.1 model for AI features. However, you can also bring your own model (BYOM) and provider to Checkly. To do this, you need to set up a custom AI provider in the AI settings screen.

Last updated on June 6, 2025. You can contribute to this documentation by editing this page on Github