Skip to content
Merged
Show file tree
Hide file tree
Changes from 2 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion .vscode/settings.json
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,8 @@
"**/src/wizard/**": true
},
"cSpell.words": [
"laravel"
"laravel",
"subprocessor",
"subprocessors"
]
}
2 changes: 1 addition & 1 deletion develop-docs/self-hosted/index.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ The difference only resides on a few things that are impossible to be hosted by
- Pricing tiers & Billing system.
- [Spike protection](https://docs.sentry.io/pricing/quotas/spike-protection/), as it is tightly coupled with Billing Quotas.
- [Spend Allocation](https://docs.sentry.io/pricing/quotas/spend-allocation/), as it is tightly coupled with Billing Quotas.
- AI & ML features (such as autofix), although the code is open at [getsentry/seer](https://github.com/getsentry/seer).
- Seer and other AI & ML features, although the code is open at [getsentry/seer](https://github.com/getsentry/seer).
- [Data Storage Location](https://docs.sentry.io/organization/data-storage-location/), because you own your data.
- [iOS Symbolication](https://docs.sentry.io/platforms/apple/data-management/debug-files/symbol-servers#built-in-repositories), because Apple does not provide a public symbol server, nor do they allow us to distribute the Debug Information Files (DIFs) ourselves.

Expand Down
2 changes: 1 addition & 1 deletion docs/contributing/environment.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ You will now be able to access docs via http://localhost:3000.

A few linters are available. Run `yarn lint` to apply them all.

Some lints can be autofixed with eslint
Some lints can be auto-fixed with eslint

```bash
yarn lint:eslint:fix
Expand Down
17 changes: 17 additions & 0 deletions docs/product/ai-in-sentry/index.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
---
title: AI in Sentry
sidebar_order: 25
description: "Learn about Sentry's AI-powered features that help you analyze and debug your code faster."
---

Sentry leverages artificial intelligence and machine learning to enhance your debugging and monitoring experience. Our AI-powered features help you understand issues faster, get automated fixes, and gain deeper insights into your application's behavior.

## AI-Powered Features

### [Seer](/product/ai-in-sentry/seer/)

Seer is Sentry's AI agent that provides intelligent analysis and automated solutions for your code issues. Seer combines issue detection, analysis, and automated fixing capabilities to streamline your debugging workflow.

- **[Issue Scan](/product/ai-in-sentry/seer/issue-scan/)**: Intelligent scanning and analysis of issues with actionability scoring
- **[Issue Fix](/product/ai-in-sentry/seer/issue-fix/)**: Automated root cause analysis and code fixes powered by AI
- **[Privacy & Security](/product/ai-in-sentry/seer/seer-privacy-security/)**: Understanding how Seer handles your data securely
73 changes: 73 additions & 0 deletions docs/product/ai-in-sentry/seer/index.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,73 @@
---
title: Seer
description: "Learn about Seer, Sentry's AI agent, and managing generative AI features."
sidebar_order: 21
---

Seer is Sentry's AI agent that powers a set of features built on generative AI and ML that uses Sentry's rich context (issue details, tracing data, and profiles) to help you understand and resolve issues faster.

## Seer Capabilities

Seer provides two main capabilities to enhance your debugging:

- [**Issue Fix**](#issue-fix): A collaborative workflow to find the root cause and solution of issues
- [**Issue Scan**](#issue-summary): Intelligently analyzes your issues and provides actionability scores to help you prioritize what to work on.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
- [**Issue Fix**](#issue-fix): A collaborative workflow to find the root cause and solution of issues
- [**Issue Scan**](#issue-summary): Intelligently analyzes your issues and provides actionability scores to help you prioritize what to work on.
- [**Issue Scan**](#issue-summary): Scans issues as they are ingested in Sentry to determine an actionability scoring and run Seer's issue fix on them automatically.
- [**Issue Fix**](#issue-fix): Automated root cause analysis and suggested code fixes.



### Issue Fix

Issue Fix uses AI to find the root cause of your issues and suggest solutions. WIth Issue Fix, you can:

- Get automated root cause analysis using Sentry's context and your codebase
- Receive AI-generated code fixes and unit tests
- Collaborate with Seer throughout the debugging process
- Create pull requests directly from the Seer Interface
- Benefit from Github integration for seamless code changes
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
- Benefit from Github integration for seamless code changes
- Benefit from GitHub integration for seamless code changes


Learn more about [Issue Fix](./issue-fix/).

### Issue Scan

Issue Scan intelligently analyzes your issues and helps you prioritize what to work on. With Issue Scan, you can:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
Issue Scan intelligently analyzes your issues and helps you prioritize what to work on. With Issue Scan, you can:
Issue Scan intelligently analyzes your issues and helps you prioritize what to work on, and enables running Issue Fix automatically on an issue. With Issue Scan, you can:


- Filter issues by their latest scan results
- View actionability scores that indicate how likely an issue is to be resolvable
- Se Seer labels in the issue stream for quick identification
- Get insights into which issues need immediate attention

## How Seer Works

Seer leverages multiple data sources to provide accurate analysis and solutions:

- **Issue Context**: Error messages, stack traces, and event metadata from your [Issues]()
- **Tracing Data**: Distributed [traces]() and span information
- **Your Codebase**: Relevant code from linked GitHub repositories
- **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](https://sentry.io/orgredirect/organizations/:orgslug/settings/#hideAiFeatures)
2. **Set up GitHub Integration**: For Issue Fix capabilities, [connect your GitHub repositories](/organization/integrations/source-code-mgmt/github/)
3. **Configure Settings**: Customize Seer's behavior in your project settings
4. **Start Using**: Look for Seer options in your issue details pages

## 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 generative AI models without your express consent and AI-generated output from your data is shown only to you, not other customers. Our generative AI features are powered by generative AI models hosted by subprocessors identified on our [subprocessor list](https://sentry.io/legal/subprocessors/). 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](/security-legal-pii/security/ai-ml-policy/#use-of-identifying-data-for-generative-ai-features).

## Disabling Generative AI Features

If you don't find Seer useful and want to disable it for all users, you can do so in your organization's settings with the ["Show Generative AI Features" toggle](https://sentry.io/orgredirect/organizations/:orgslug/settings/#hideAiFeatures).
46 changes: 46 additions & 0 deletions docs/product/ai-in-sentry/seer/issue-fix/index.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,46 @@
---
title: Issue Fix
description: "Use Seer's Issue Fix to automatically find the root cause of issues and generate code fixes."
sidebar_order: 20
---

**Issue Fix** is Seer's collaborative workflow to find the root cause of and solution to issues. It uses Sentry's context (issue details, tracing data, logs, and profiles), your codebases (integrated through GitHub), and its interactions with you to identify and reason through problems in your code.

<Alert>
Issue Fix replace Suggested Fix (an earlier feature that has been sunset) and builds upon the capabilities previously known as Autofix.
</Alert>

## How Issue Fix Works

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

{/* IMG */}

Issue Fix will then analyze the issue and relevant code to help identify the root cause and a solution. You'll see a live stream of Seer's thought process in real time as it works through the problem. Seer 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 Seer's conclusions, building a clear chain of reasoning back to the root cause.

While Issue Fix is reasoning through your problem, you can step in to add context or feedback; collaboration tends to lead to the best results. If Issue Fix 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:

{/* IMG */}

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. From there you'll have three options:

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

{/* IMG */}

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

## Prerequisites

To use Issue Fix, you'll need to have the following:

1. A Sentry project with issues that have sufficient context (issue details, tracing data, logs, and profiles).

2. GitHub integration set up in your Sentry project. This allows Seer to access your codebase and generate code fixes. See the [Sentry GitHub integration](/organization/integrations/source-code-mgmt/github/) to learn more.

3. Working knowledge of the issue you want to fix. Seer will help you identify the root cause and suggest a solution, but you should have a general understanding of the problem you're trying to solve.

27 changes: 27 additions & 0 deletions docs/product/ai-in-sentry/seer/seer-privacy-and-security/index.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
---
title: Seer Privacy and Security
sidebar_order: 30
description: "Learn about how Seer handles your data securely and protects your privacy."
---

Seer is designed with your privacy and security in mind. We take the following measures to ensure that your data is handled securely:

## Data Processing for Seer

We use the data listed below to provide insights, analysis, and solutions for your review. Your data will not be used to train any generative AI models without your express consent and AI-generated output from your data is shown only to you, not other customers. Our generative AI features are powered by generative AI models hosted by subprocessors identified on our [subprocessor list](https://sentry.io/legal/subprocessors/). 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](/security-legal-pii/security/ai-ml-policy/#use-of-identifying-data-for-generative-ai-features).

## Privacy Guarantees

### No Training on Your Data

Your data will **not** be used to train any generative AI models without your express consent and AI-generated output from your data is shown only to you, not other customers.
18 changes: 6 additions & 12 deletions docs/product/issues/issue-details/sentry-seer/index.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -15,23 +15,17 @@ Autofix and Issue Summary are currently in Beta, free of charge, for paid Sentry

</Alert>

### Autofix
### Issue Fix

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

<Alert>

Autofix replaces Suggested Fix (an earlier feature that has been sunset).

</Alert>

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

![Autofix Start Screen](./img/autofix-start-screen.png)

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.
Seer will then analyze the issue and relevant code to help identify the root cause and a solution. You'll see a live stream of Seer's thought process in real time as it works through the problem. Seer 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 Seer's 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.
While Seer 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 Seer 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:

Expand All @@ -45,7 +39,7 @@ You are free to edit or adjust this solution based on your own requirements and

![Autofix Results](./img/autofix-results.png)

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

### Issue Summary

Expand Down
6 changes: 4 additions & 2 deletions docs/product/sentry-mcp/index.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ The [Sentry MCP Server](https://mcp.sentry.dev) provides a secure way of bringin
- Search for errors in specific files
- Query projects and organizations
- List and create Sentry DSN's for projects
- Execute autofix runs and retrieve autofix status and details
- Invoke Seer to automatically fix issues and retrieve the status and details of an issue fix

<VimeoEmbed id="1080588938?h=1e437d4874" />

Expand Down Expand Up @@ -53,10 +53,12 @@ Once configured via one of these methods, you'll be able to view the available t
- Check Sentry for errors in `file.tsx` and propose solutions.
- Diagnose issue `issue id` and propose solutions.
- Create a new project in Sentry for `service-name` and setup local instrumentation using it.
- Use Sentry's autofix feature, and help me analyze and propose a solution for `issue id`.
- Use Sentry's Seer and help me analyze and propose a solution for `issue id`.

![Sentry MCP using Autofix](./img/mcp-autofix1.png)

TODO: Image needs to be updated

## Verified Clients

The Sentry MCP Server has been verified to work in:
Expand Down