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/issues/issue-details/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
@@ -40,7 +40,7 @@ A few tags are shown as a preview on the page, but to see more, you can either c
40
40
41
41
The first and last time the issue has been seen will be displayed here. These values will depend on your environment selection and will be updated if you change the environments. If you have releases set up, the first and last release where the issue was seen will be shown
42
42
43
-
The solutions hub contains features from [Sentry AI](/product/issues/issue-details/sentry-ai) that help you understand and fix issues.
43
+
The solutions hub contains features from [Sentry AI](/product/issues/issue-details/sentry-seer) that help you understand and fix issues.
44
44
45
45
If you have [issue tracking](/organization/integrations/issue-tracking) set up, integrations or linked issues will appear.
description: "Learn about Seer, Sentry's AI agent, and managing generative AI features."
4
+
sidebar_order: 50
5
+
6
+
---
7
+
8
+
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**](https://sentry.io/orgredirect/organizations/:orgslug/issues/) page.
9
+
10
+
Once you've set up Seer, you'll be able to use the following features:
11
+
12
+
-[**Issue Summary**](#issue-summary): A quick summary of issue context to help you see what's going on
13
+
-[**Autofix**](#autofix): A collaborative workflow to find the root cause and solution of issues
14
+
15
+
<Alert>
16
+
17
+
Issue Summary and Autofix are currently in Beta, free of charge, for paid Sentry customers. Feedback is highly welcomed and can be submitted in-product or via email to [[email protected]](mailto:[email protected]).
18
+
19
+
</Alert>
20
+
21
+
## Issue Summary
22
+
23
+
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:
24
+
25
+
26
+
27
+
## Autofix
28
+
29
+
<Alert>
30
+
31
+
Autofix replaces Suggested Fix (an earlier feature that has been sunset).
32
+
33
+
</Alert>
34
+
35
+
**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.
36
+
37
+
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.
42
+
43
+
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.
44
+
45
+
The output will be a clearly defined root cause of the Sentry issue, and a detailed solution for how to resolve it:
46
+
47
+
48
+
49
+
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:
50
+
51
+
- Write a fix
52
+
- Write a unit test reproducing the issue
53
+
- Write both
54
+
55
+
56
+
57
+
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.
58
+
59
+
## Data Processing for Generative AI
60
+
61
+
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](https://sentry.io/legal/subprocessors/). Our subprocessors are only permitted to use the data as directed by us.
62
+
63
+
The data used for these features includes:
64
+
65
+
- Error messages
66
+
- Stack traces
67
+
- Sentry spans
68
+
- DOM interactions
69
+
- Profiles
70
+
- Relevant code from linked repositories
71
+
72
+
You can learn more about our data privacy practices [here](https://docs.sentry.io/security-legal-pii/security/ai-ml-policy/#use-of-identifying-data-for-generative-ai-features).
73
+
74
+
## Disabling Seer Features
75
+
76
+
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]
Copy file name to clipboardExpand all lines: docs/security-legal-pii/security/ai-ml-policy.mdx
+24-53Lines changed: 24 additions & 53 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,25 +4,19 @@ sidebar_order: 10
4
4
description: "Learn about Sentry's approach to AI/ML"
5
5
---
6
6
7
-
<Alert>
8
-
These settings will be rolling out to users over the next few weeks.
9
-
</Alert>
7
+
## Delivering a better user experience
10
8
11
-
Throughout Sentry’s history, we’ve operated under a policy of [privacy by default](https://sentry.io/lp/privacy-by-default/). This same principle applies to our work in the Artificial Intelligence (AI) and Machine Learning (ML) space, where we want to be just as [transparent](https://blog.sentry.io/terms-of-service-update/)about what data we’re using and why.
9
+
Sentry processes your service data, the data you configure to be collected and reported to your Sentry instance, to provide our service to you. As Sentry's service has evolved, however, prior heuristics-based approaches cannot deliver the product value we've come to expect. To train and validate models for grouping, notifications, and workflow improvements, Sentry will need access to additional [service data](https://blog.sentry.io/terms-of-service-update/)to deliver a better user experience.
12
10
13
-
Sentry is at a juncture where prior heuristics-based approaches cannot sustain the demands of the product. For example, fingerprinting error events as part of creating groups, has gotten a lot more complicated with the rise of JavaScript and the use of extensions and third-party services.
11
+
You can update these settings within the "Service Data Usage" section of the Legal & Compliance page in [Sentry](https://sentry.io/orgredirect/organizations/:orgslug/settings/legal/), which is located within the "Usage & Billing" Settings.
14
12
15
-
To train and validate models for grouping, notifications, and workflow improvements, Sentry will need access to additional service data to deliver a better user experience.
13
+
### Use of non-identifying data
16
14
17
-
You can update these settings within the new “Service Data Usage” section of the Legal & Compliance page in [Sentry](https://sentry.io/orgredirect/organizations/:orgslug/settings/legal/), which is located within the “Usage & Billing” Settings.
15
+
In accordance with our Terms of Service, Sentry may use non-identifying elements of your service data for product improvement. For example, we may aggregate web vitals data to show your site's performance against a Sentry-built benchmark. The data accessed for the benchmark cannot be linked back to any particular project or customer, making it non-identifying.
18
16
19
-
## Use of Non-Identifying Data
17
+
###Use of aggregated identifying data
20
18
21
-
In accordance with our Terms of Service, Sentry may use non-identifying elements of your service data for product improvement. For example, we may aggregate web vitals data to show your site’s performance against a Sentry-built benchmark. The data accessed for the benchmark cannot be linked back to any particular project or customer, making it non-identifying.
22
-
23
-
## Use of Aggregated Identifying Data
24
-
25
-
For upcoming features like priority alerts or ML-based grouping, Sentry is asking for access to the following forms of service data:
19
+
For upcoming features like priority alerts or ML-based grouping, if authorized by you, Sentry may access the following forms of service data for product improvement:
26
20
27
21
- Error messages
28
22
- Stack traces
@@ -31,52 +25,29 @@ For upcoming features like priority alerts or ML-based grouping, Sentry is askin
31
25
32
26
## Use of Identifying Data for Generative AI Features
33
27
34
-
For upcoming features like Autofix that use Generative AI, Sentry is asking for access to the following forms of service data:
28
+
Sentry Seer powers our generative AI features like Autofix. To learn more about Seer features, including how you can manage Seer features, [see here](/product/issues/issue-details/sentry-seer/).
29
+
30
+
For Seer features, Sentry is asking for access to the following forms of service data 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.
35
31
36
32
- Error messages
37
33
- Stack traces
38
-
-Spans
34
+
-Sentry spans
39
35
- DOM interactions
40
-
- Relevant code to linked repositories
36
+
- Profiles
37
+
- Relevant code from linked repositories
41
38
42
-
All functionality leveraging RAG will require user opt-in. By opting in, you agree to our use of relevant stack trace and code from your linked repositories with generative AI models hosted by the feature-specific subprocessors identified on our [subprocessor list](https://sentry.io/legal/subprocessors/).
43
-
44
-
To ensure our BAA customers can remain HIPAA compliant and that data stays in your selected region, we will disable generative AI features in Sentry for all BAA customers and EU region customers by default where we are unable to flow-down necessary BAA terms or where data storage in the EU region is not available, as applicable.
39
+
To ensure that data is stored in your selected region, we will disable Seer features in Sentry for EU region customers by default where data storage in the EU region is not available.
45
40
46
41
## Data Access Summary
47
42
48
-
<table>
49
-
<tbody>
50
-
<tr>
51
-
<th>Access Type</th>
52
-
<th>Is the underlying data identifiable?</th>
53
-
<th>Will this data (or any output) be shared with others?</th>
54
-
<th>Will this data be used for training Sentry models?</th>
55
-
<th>Will this data be used to train 3rd party models?</th>
56
-
</tr>
57
-
<tr>
58
-
<th>Non-identifying data</th>
59
-
<td>No</td>
60
-
<td>Other Sentry customers</td>
61
-
<td>Yes</td>
62
-
<td>No</td>
63
-
</tr>
64
-
<tr>
65
-
<th>Aggregated identifying data</th>
66
-
<td>Yes</td>
67
-
<td>Sentry only</td>
68
-
<td>Yes</td>
69
-
<td>No</td>
70
-
</tr>
71
-
<tr>
72
-
<th>Identifying data for generative AI features</th>
73
-
<td>Yes</td>
74
-
<td>Approved feature-specific subprocessors</td>
75
-
<td>No</td>
76
-
<td>No</td>
77
-
</tr>
78
-
</tbody>
79
-
</table>
43
+
|**Access Type**|**Is the underlying data identifiable?**|**Who will this data (or any output) be shared with?**|**Will this data be used for training Sentry models?**|**Will this data be used to train 3rd party models?**|
|**Identifying data for generative AI features**| Yes | Approved subprocessors | No | No |
48
+
49
+
50
+
**In these cases we don't share the underlying data, only aggregations or output generated from the data.*
80
51
81
52
## Data Handling
82
53
@@ -86,6 +57,6 @@ In addition to the consent mechanisms mentioned above:
86
57
2. We'll apply the same deletion and retention rules to our training data as we do to the underlying service data. This means that if you delete service data, it will also be removed from our machine learning models automatically.
87
58
3. We'll scrub data for PII before it goes into any training set.
88
59
4. We'll ensure that the only service data presented in the output of any generative AI feature belongs to the customer using the feature.
89
-
5. We'll only use AI models built in-house, deployed in our production cloud, or provided by our existing trusted [third-party subprocessors](https://sentry.io/legal/subprocessors/) who have made contractual commitments that are consistent with the above.
60
+
5. We'll only use generative AI models built in-house, deployed in our production cloud, or provided by our existing trusted [third-party subprocessors](https://sentry.io/legal/subprocessors/) who have made contractual commitments that are consistent with the above.
90
61
91
-
We're confident that with these controls in place, we'll be able to use service data to improve our products through AI while at the same time protecting that data.
62
+
We're confident that with these controls in place, we'll be able to use service data to improve and provide our products through AI while at the same time protecting that data.
0 commit comments