Seer
Learn about Seer, Sentry's AI agent, and managing generative AI features.
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 provides end-to-end debugging tools to help you troubleshoot and fix errors and performance issues faster, often before they are even merged:
- Autofix: Automatically scan issues as they come into Sentry, finding root causes, and automating triage.
- PR Creation: Use Autofix to generate a code fix and create a PR.
- External Coding Agents: Delegate Seer's analysis to an external coding agent for debugging and fixes.
- Seer Agent: Investigate errors and performance issues, and take action in Sentry. Ask Seer to find relevant telemetry related to issues, orcreate dashboards, monitors, and alerts.
- Code Review: Have Seer review your code changes in GitHub or GitLab, catching bugs before merging.
To start using Seer's capabilities follow these steps:
Connect to GitHub through the Sentry GitHub integration or Gitlab through the Sentry GitLab integration. Note: Seer supports GitHub.com and GitLab.com (cloud versions only).
Turn on Seer features for your projects and repos - Enable Issue Autofix, delegate to Coding Agents, and enable Code Review.
Seer is an add-on to your Sentry subscription. By enabling it, you are signing up for active contributor pricing for this feature. Any person who creates 2 or more PRs/MRs in a month in a Seer-Enabled repo/project will be billed. A repo/project is considered Seer-Enabled when it is connected to Sentry and has one or more Seer features turned on. You can learn more about Seer pricing here.
Seer is able to automatically analyze issues as they are ingested by Sentry by combining all of the relevant context from your code with Sentry's telemetry data to provide a best-in-class issue debugging experience. Autofix includes:
A Root Cause Analysis step used to:
- Determine if the issue can be automatically analyzed and fixed using Seer's Autofix
- Add an initial guess for what the potential problem is to the issue details page
Once Autofix has run, Seer will provide remediation recommendations.
PR Creation
You can prompt Seer to generate PRs, or merge requests on GitLab, to fix your issue and push the changes to your repository. You can add more context in natural language, or any external supporting information, to help Seer generate a better fix. Note: You must install the Seer Github or GitLab app to use this feature.
External Coding Agents
Seer always performs root cause analysis and solution planning using its own internal tools and Sentry context. At the final code generation step of Autofix, instead of having Seer generate the code fix directly, you can hand off to an external coding agent for implementation.
Supported coding agents for handoff are: Claude Code, Cursor Cloud Agents, and GitHub Copilot. Learn more about how to set up each coding agent here. Read more about using them with Autofix.
This feature is currently in open beta. Please reach out on GitHub if you have feedback or questions. Features in beta are still in-progress and may have bugs. We recognize the irony.
Use natural language to ask Seer to investigate your application and customize Sentry. Seer brings together relevant errors, traces, spans, logs, and connected code and telemetry integrations to help you understand what happened and decide what to do next.
Ask Seer to act on what you find. Archive issues you no longer need to track, build a dashboard, or create a monitor or alert directly through the Seer conversation. Use Ask Seer in Sentry or talk to Seer through the Slack integration.
Share your conversations with team members, copy your conversation to share with other agents, or revisit previous conversations to continue your investigation.
Example requests
- "What has performance been like in my application for the last 7 days?"
- "I want to archive all recurring issues in this project with no events in the last 30 days. Share the list with me before archiving."
- “Create a dashboard showing checkout errors and latency on the checkout page over the last seven days.”
- “Create an alert for checkout errors in production. Add a different action for each threshold for number of events. 50 in a week - email. 100 in a day - Slack.”
To get started, click Ask Seer on any page in Sentry.
If your organization has Open Team Membership disabled, Seer Agent will not be available. Seer Agent makes org-wide queries on your data, and does not have finer-grained access controls yet.
Seer Agent in Slack
You can also use Seer Agent in Slack as a part of the Slack integration.
AI Code Review reviews your code changes, predicting errors and offering suggestions for improvement before merging pull requests or merge requests. Code Review is available on GitHub and GitLab.com.
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 or GitLab repositories, with support for multiple repos for distributed services
- Performance Data: Profiles and performance metrics
- Interactive Feedback: Your input and guidance during the process
- Sentry Docs: Sentry's documentation site
The Datadog for Seer integration gives Seer Agent access to Datadog data like metrics, spans, traces, logs, notebooks, monitors, dashboards, and more. Seer can then use Datadog data to enhance or supplement Sentry telemetry in issue analysis or investigations.
The Google Cloud Platform for Seer integration gives Seer Agent access to Cloud Logging, Cloud Monitoring, and Cloud Trace data. Seer can then use Google Cloud data to enhance or supplement Sentry telemetry in issue analysis or investigations.
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.
If you would not like to show generative AI Features at all in your Sentry account, go to organization settings and turn off the
Show Generative AI Featurestoggle.If you want to use some generative AI features, while disabling others, you can bulk manage these settings by going to Seer settings and selecting from the dropdown at the top of the table in each tab.
For organizations that need to prevent Seer from creating PRs, you can manage this in Advanced Settings in Seer settings.
Note: Disabling the setting removes the Create PR button from the Autofix flow and prevents anyone from enabling Allow Root Cause Analysis to create PRs by Default. Sentry will not create PRs or push code to your codebase. This setting does not impact AI chat sessions, where you can potentially prompt our AI chat to emit code snippets and examples, and does not affect workflows involving your own coding agent.
Our documentation is open source and available on GitHub. Your contributions are welcome, whether fixing a typo (drat!) or suggesting an update ("yeah, this would be better").