Sentry Seer

Seer is Sentry's AI agent that powers a set of features built on generative AI and ML. You can find it in the Solutions Hub section of the issue details page after clicking on any error from the Issues page.

Once you've set up Seer, you'll be able to use the following features:

• Issue Summary: A quick summary of issue context to help you see what's going on
• Autofix: A collaborative workflow to find the root cause and solution of issues

Issue Summary

The Issue Summary provides a quick overview of an issue by highlighting key insights taken from event and issue-level metadata. You'll see a quick overview of what's going wrong, a potential cause, and if relevant, insights from trace-connected issues, all in the Solutions Hub in the sidebar:

Autofix

Autofix uses Sentry's context (issue details, tracing data, and profiles), your codebase (integrated through GitHub), and its interactions with you to identify and reason through problems in your code. Autofix can identify the root cause and suggest a code change for fixing the issue and/or add unit tests for it.

When you start an Autofix run, you'll see the following screen, with an option to share any additional context:

Autofix will then analyze the issue and relevant code to help identify the root cause and a solution. You'll see a live stream of Autofix's thought process in real time as it works through the problem. Autofix will share key insights as they come up and you'll have the option to expand each. You'll see the event data and code that support Autofix conclusions, building a clear chain of reasoning back to the root cause.

While Autofix is reasoning through your problem, you can step in at any time to add context or feedback; collaboration tends to lead to the best results. If Autofix encounters gaps in its understanding, it will ask for your input.

The output will be a clearly defined root cause of the Sentry issue, and a detailed solution for how to resolve it:

You are free to edit or adjust this solution based on your own requirements and preferences. Once you are ready to proceed, you can select "Code It Up" to generate code resolving the bug. You have three options:

• Write a fix
• Write a unit test reproducing the issue
• Write both

Once the coding step is complete, you can either create a Pull Request (PR) in GitHub directly from Autofix, or create a branch and checkout the code locally if you would like to iterate further.

Data Processing for Generative AI

We use the data listed below to provide insights, analysis, and solutions for your review. Your data will not be used to train any Seer models without your express consent and AI-generated output from your data is shown only to you, not other customers. Seer is powered by generative AI models hosted by subprocessors identified on our subprocessor list. Our subprocessors are only permitted to use the data as directed by us.

The data used for these features includes:

• Error messages
• Stack traces
• Sentry spans
• DOM interactions
• Profiles
• Relevant code from linked repositories

You can learn more about our data privacy practices here.

Disabling Seer Features

If you don't find the Seer features useful and want to disable it for all users, you can do so in your organization's settings with the "Enable Seer Features" toggle [link]