You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: develop-docs/self-hosted/index.mdx
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -17,7 +17,7 @@ The difference only resides on a few things that are impossible to be hosted by
17
17
- Pricing tiers & Billing system.
18
18
-[Spike protection](https://docs.sentry.io/pricing/quotas/spike-protection/), as it is tightly coupled with Billing Quotas.
19
19
-[Spend Allocation](https://docs.sentry.io/pricing/quotas/spend-allocation/), as it is tightly coupled with Billing Quotas.
20
-
- AI & ML features (such as autofix), although the code is open at [getsentry/seer](https://github.com/getsentry/seer).
20
+
-Seer and other AI & ML features, although the code is open at [getsentry/seer](https://github.com/getsentry/seer).
21
21
-[Data Storage Location](https://docs.sentry.io/organization/data-storage-location/), because you own your data.
22
22
-[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.
description: "Learn about Seer, Sentry's AI agent, and managing generative AI features."
4
+
sidebar_order: 21
5
+
---
6
+
7
+
Seer is Sentry's AI debugging agent that powers a set of features built on generative AI and ML that uses Sentry's rich context (issue details, tracing data, logs, and profiles) to help you troubleshoot and fix errors and performance issues faster.
8
+
9
+
## Seer Capabilities
10
+
11
+
Seer provides two main capabilities to enhance your debugging:
12
+
13
+
-[**Issue Fix**](#issue-fix): A collaborative workflow to find the root cause and solution of issues
14
+
-**Issue Scan**: Intelligently analyzes your issues and provides actionability scores to help you prioritize what to work on.
15
+
16
+
### Issue Fix
17
+
18
+
Issue Fix uses AI to find the root cause of your issues and suggest solutions. WIth Issue Fix, you can:
19
+
20
+
- Get automated root cause analysis using Sentry's context and your codebase
21
+
- Receive AI-generated code fixes and unit tests
22
+
- Collaborate with Seer throughout the debugging process
23
+
- Create pull requests directly from the Seer Interface
24
+
- Benefit from Github integration for seamless code changes
25
+
26
+
Learn more about [Issue Fix](./issue-fix/).
27
+
28
+
### Issue Scan
29
+
30
+
Issue Scan intelligently analyzes your issues and helps you prioritize what to work on. With Issue Scan, you can:
31
+
32
+
- Filter issues by their latest scan results
33
+
- View actionability scores that indicate how likely an issue is to be resolvable
34
+
- Se Seer labels in the issue stream for quick identification
35
+
- Get insights into which issues need immediate attention
36
+
- Enable Seer's Issue Fix to be started automatically once an issue is ingested in Sentry
37
+
38
+
## How Seer Works
39
+
40
+
Seer leverages multiple data sources to provide accurate analysis and solutions:
41
+
42
+
-**Issue Context**: Error messages, stack traces, and event metadata from your [Issues](/product/issues/)
43
+
-**Tracing Data**: Distributed [traces](/concepts/key-terms/tracing/#whats-a-trace) and span information
44
+
-**Your Codebase**: Relevant code from linked GitHub repositories and [logs](/product/explore/logs/)
45
+
-**Performance Data**: Profiles and performance metrics
46
+
-**Interactive Feedback**: Your input and guidance during the process
47
+
48
+
## Getting Started with Seer
49
+
50
+
To start using Seer's capabilities:
51
+
52
+
1.**Enable Seer**: Make sure AI features are enabled in your [organization settings](https://sentry.io/orgredirect/organizations/:orgslug/settings/#hideAiFeatures)
53
+
2.**Set up GitHub Integration**: For Issue Fix capabilities, [connect your GitHub repositories](/organization/integrations/source-code-mgmt/github/)
54
+
3.**Configure Settings**: Customize Seer's behavior in your project settings
55
+
4.**Start Using**: Look for Seer options in your issue details pages
56
+
57
+
## Data Processing for Generative AI
58
+
59
+
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.
60
+
61
+
The data used for these features includes:
62
+
63
+
- Error messages
64
+
- Stack traces
65
+
- Sentry spans
66
+
- DOM interactions
67
+
- Logs
68
+
- Profiles
69
+
- Relevant code from linked repositories
70
+
71
+
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).
72
+
73
+
## Disabling Generative AI Features
74
+
75
+
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).
description: "Use Seer's Issue Fix to automatically find the root cause of issues and generate code fixes."
4
+
sidebar_order: 20
5
+
---
6
+
7
+
**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.
8
+
9
+
<Alert>
10
+
Issue Fix replace Suggested Fix (an earlier feature that has been sunset) and builds upon the capabilities previously known as Autofix.
11
+
</Alert>
12
+
13
+
## How Issue Fix Works
14
+
15
+
When you start an Issue Fix run, you'll see the following screen, with an option to share any additional context:
16
+
17
+
{/* IMG */}
18
+
19
+
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.
20
+
21
+
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.
22
+
23
+
The output will be a clearly defined root cause of the Sentry issue, and a detailed solution for how to resolve it:
24
+
25
+
{/* IMG */}
26
+
27
+
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:
28
+
29
+
- Write a fix
30
+
- Write a unit test reproducing the issue
31
+
- Write both
32
+
33
+
{/* IMG */}
34
+
35
+
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.
36
+
37
+
## Prerequisites
38
+
39
+
To use Issue Fix, you'll need to have the following:
40
+
41
+
1. A Sentry project with issues that have sufficient context (issue details, tracing data, logs, and profiles).
42
+
43
+
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.
44
+
45
+
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.
description: "Learn about how Seer handles your data securely and protects your privacy."
5
+
---
6
+
7
+
Seer is designed with your privacy and security in mind. We take the following measures to ensure that your data is handled securely:
8
+
9
+
## Data Processing for Seer
10
+
11
+
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.
12
+
13
+
The data used for these features includes:
14
+
- Error messages
15
+
- Stack traces
16
+
- Sentry spans
17
+
- DOM interactions
18
+
- Profiles
19
+
- Relevant code from linked repositories
20
+
21
+
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).
22
+
23
+
## Privacy Guarantees
24
+
25
+
### No Training on Your Data
26
+
27
+
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.
We'll be adding AI integrations continuously. You can also instrument AI manually with the Sentry Python SDK.
31
152
32
153
</Alert>
33
154
34
-
35
155
## Pipelines and LLMs
36
156
37
157
The Sentry LLM Monitoring feature relies on the fact that you have an orchestrator (like LangChain) creating pipelines of one or more LLMs (such as gpt-4). In the LLM Monitoring dashboard, we show you a table of the AI pipelines and pull the token usage from your LLMs.
0 commit comments