Seer

Seer is Sentry's AI debugging agent. It uses Sentry's rich context (issue details, tracing data, logs, and profiles) to help you troubleshoot and fix errors and performance issues faster.

Seer Capabilities

Seer provides three main capabilities to enhance your debugging:

• Issue fix: A collaborative agent skilled at root cause analysis and solving issues
• Issue scan: Automatically scans issues as they come in, feeding additional context to your alerts and automating triage
• Automation: Combines issue fix and scan into a powerful workflow: identifying actionable issues in real time and generating high quality fixes, automatically

Issue Fix

Seer combines all of the relevant context from your code with Sentry's telemetry data to provide a best-in-class issue debugging experience. The workflow consists of three steps:

1. Root cause the issue using Sentry's context and your codebase
2. Identify a solution based on the analysis
3. Generate a code patch that implements the solution and open a PR

For a full product walk-through, see issue fix.

Issue Scan

Seer is able to automatically analyze issues as they are ingested by Sentry. This initial review is used to:

• Generate an "actionability" score, which indicates how likely it is that a particular issue can be fixed with a code change
• Augment issue alerts with a helpful analysis about the problem
• Add an initial guess for what the potential problem is to the issue details page

The actionability score is represented in the issue feed by a Seer icon, which indicate issues that are likely straightforward fixes.

Automation

You can use automation to trigger issue scans and fixes. There are three automation settings you can configure:

1. Automate Issue Scans: This enables Seer's issue scan functionality
2. Automate Issue Fixes: This allows you to customize the degree of automation employed by Seer. For example, setting it to "Highly Actionable and Above" will automatically trigger issue fixes for all of your highly actionable Issues.
3. Stopping Point for Automatic Fixes: Seer allows you to customize how far to go with automation. By default, it stops at the solution step, but you can choose to have it go all the way to code changes or even generate PRs automatically.

What Seer Uses

Seer is a powerful debugging agent, with access to a wide variety of data sources and tools. While debugging issues, it may examine:

• Issue Context: Error messages, stack traces, and event metadata from your Issues
• Tracing Data: Distributed traces and span information
• Logs: Structured Logs from your application (beta)
• Your Codebase: Relevant code from linked GitHub repositories, with support for multiple repos for distributed services
• Performance Data: Profiles and performance metrics
• Interactive Feedback: Your input and guidance during the process

Getting Started with Seer

To start using Seer's capabilities:

1. Enable Seer: Make sure AI features are enabled in your organization settings
2. Set up GitHub Integration: For Seer to be able to create patches and open pull requests, connect your GitHub repositories
3. Configure Settings: Customize Seer's behavior in your project settings
4. Start Using: Look for Seer options in your issue details pages

Privacy and security

Sentry includes strong guarantees for privacy and security of your data. At a glance:

• Sentry does not train generative AI models using your data by default and without your permission.
• AI-generated output is shown only to you and other authorized users in your account.

You can learn more about our data privacy practices in the security and legal docs.