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: docs/product/ai-in-sentry/index.mdx
+6-3Lines changed: 6 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -14,20 +14,23 @@ Seer is Sentry's AI debugging agent that helps resolve errors and performance is
14
14
15
15
-**[Issue Fix](/product/ai-in-sentry/seer/issue-fix/)**: Automated root cause analysis and suggested code fixes, for errors and performance issues.
16
16
-**Issue Scan**: Scans issues as they are ingested in Sentry to determine an actionability score and run Seer's issue fix on them automatically.
17
-
-**[Privacy & Security](/product/ai-in-sentry/ai-privacy-and-security/)**: Understanding how Seer handles your data securely.
18
17
19
-
## Issue Summary
18
+
###Issue Summary
20
19
21
20
**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.
Sentry Prevent AI is a generative AI assistant developed by Sentry, available in GitHub. It helps you generate new tests for uncovered code and reviews your code changes, offering suggestions for improvement before merging pull requests.
25
+
23
26
## Privacy and security
24
27
25
28
Sentry includes strong guarantees for privacy and security of your data. At a glance:
26
29
27
30
- Sentry does not train generative AI models using your data by default and without your permission.
28
31
- AI-generated output is shown only to you and other authorized users in your account.
29
32
30
-
You can learn more about our data privacy practices[in the security and legal docs](/security-legal-pii/security/ai-ml-policy/#use-of-identifying-data-for-generative-ai-features).
33
+
You can get more details at [AI Privacy and Security](/product/ai-in-sentry/ai-privacy-and-security/). To learn more about all our data privacy practices go to [the security and legal docs](/security-legal-pii/security/ai-ml-policy/#use-of-identifying-data-for-generative-ai-features).
description: "Learn about Seer, Sentry's AI agent, and managing generative AI features."
4
-
sidebar_order: 21
4
+
sidebar_order: 20
5
5
---
6
6
7
-
Seer is Sentry's AI debugging agent. It includes a set of features, built on generative AI, that use Sentry's rich context (issue details, tracing data, logs, and profiles) to help you troubleshoot and fix errors and performance issues faster.
7
+
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.
8
8
9
9
## Seer Capabilities
10
10
11
-
Seer provides two main capabilities to enhance your debugging:
11
+
Seer provides three main capabilities to enhance your debugging:
12
12
13
-
-[**Issue fix**](#issue-fix): A collaborative workflow to find the root cause and solution of errors and performance issues.
14
-
-**Issue scan**: Intelligently analyzes your issues and provides actionability scores to help you prioritize what to work on.
13
+
-[**Issue fix**](#issue-fix): A collaborative agent skilled at root cause analysis and solving issues
14
+
-[**Issue scan**](#issue-scan): Automatically scans issues as they come in, feeding additional context to your alerts and automating triage
15
+
-[**Automation**](#automation): Combines issue fix and scan into a powerful workflow: identifying actionable issues in real time and generating high quality fixes, automatically
15
16
16
17
### Issue Fix
17
18
18
-
Issue fix uses AI to find the root cause of your apps' issues and suggest solutions. With issue fix, you can:
19
+
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:
19
20
20
-
- Get an accurate root cause analysis, using Sentry's context and your codebases
21
-
- Receive suggested code fixes and unit tests
22
-
- Collaborate with Seer throughout the debugging process
23
-
- Create pull requests directly from the Seer interface
21
+
1. Root cause the issue using Sentry's context and your codebase
22
+
2. Identify a solution based on the analysis
23
+
3. Generate a code patch that implements the solution and open a PR
24
24
25
-
Learn more about [issue fix](./issue-fix/).
25
+
For a full product walk-through, see [issue fix](./issue-fix/).
26
+
27
+
<VimeoEmbedid="1091964967?h=4f24769ccd" />
26
28
27
29
### Issue Scan
28
30
29
-
Issue scan intelligently analyzes your issues and helps you prioritize what to work on. With issue scan, you can:
31
+
Seer is able to automatically analyze issues as they are ingested by Sentry. This initial review is used to:
32
+
33
+
- Generate an "actionability" score, which indicates how likely it is that a particular issue can be fixed with a code change
34
+
- Augment issue alerts with a helpful analysis about the problem
35
+
- Add an initial guess for what the potential problem is to the issue details page
36
+
37
+
The actionability score is represented in the issue feed by a Seer icon, which indicate issues that are likely straightforward fixes.
30
38
31
-
- View actionability scores that indicate how likely an issue is to be fixable with a code change, manually or with Seer's issue fix
32
-
- Enable Seer's issue fix to be started automatically once an issue is ingested in Sentry
33
-
- Filter issues by their latest scan results
34
-
- See Seer labels in the issue stream for quick identification
35
-
- Get insights into which issues need immediate attention
39
+
### Automation
36
40
37
-
## How Seer Works
41
+
You can use automation to trigger issue scans and fixes. There are three automation settings you can configure:
38
42
39
-
Seer leverages multiple data sources to provide accurate analysis and solutions:
43
+
1.**Automate Issue Scans**: This enables Seer's issue scan functionality
44
+
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.
45
+
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.
46
+
47
+
## What Seer Uses
48
+
49
+
Seer is a powerful debugging agent, with access to a wide variety of data sources and tools. While debugging issues, it may examine:
40
50
41
51
-**Issue Context**: Error messages, stack traces, and event metadata from your [Issues](/product/issues/)
42
52
-**Tracing Data**: Distributed [traces](/concepts/key-terms/tracing/#whats-a-trace) and span information
@@ -49,9 +59,13 @@ Seer leverages multiple data sources to provide accurate analysis and solutions:
49
59
50
60
To start using Seer's capabilities:
51
61
52
-
1.**Enable Seer**: Make sure AI features are enabled in your [organization settings](https://sentry.io/orgredirect/organizations/:orgslug/settings/#hideAiFeatures)
62
+
1.**Enable generative AI features**: Make sure AI features are enabled in your [organization settings](https://sentry.io/orgredirect/organizations/:orgslug/settings/#hideAiFeatures)
53
63
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
64
+
3.**Configure Settings**: Customize Seer's behavior in your project settings under `Seer Automation`. Seer is enabled by default using these settings:
65
+
-**Automatic issue scans**: Enabled
66
+
-**Automatic issue fixes**: Enabled for highly actionable issues and above
67
+
68
+
> **Note**: You can monitor your Seer usage in the [Stats & Usage tab](https://sentry.io/settings/stats/) and can learn more about managing your Seer budget [here](/pricing/quotas/manage-seer-budget/).
55
69
4.**Start Using**: Look for Seer options in your issue details pages
56
70
57
71
## Privacy and security
@@ -61,4 +75,4 @@ Sentry includes strong guarantees for privacy and security of your data. At a gl
61
75
- Sentry does not train generative AI models using your data by default and without your permission.
62
76
- AI-generated output is shown only to you and other authorized users in your account.
63
77
64
-
You can learn more about our data privacy practices[in the security and legal docs](/security-legal-pii/security/ai-ml-policy/#use-of-identifying-data-for-generative-ai-features).
78
+
You can learn more about our data privacy practices[in the security and legal docs](/security-legal-pii/security/ai-ml-policy/#use-of-identifying-data-for-generative-ai-features).
0 commit comments