---
title: "AI-Detected Issues"
description: "Learn about AI-detected issues and how Sentry uses AI to find problems in your traces."
url: https://docs.sentry.io/product/issues/issue-details/ai-detected-issues/
---

# AI-Detected Issues

This feature is available only if you're in the [Early Adopter program](https://docs.sentry.io/organization/early-adopter-features.md). Features available to Early Adopters are still in-progress and may have bugs. We recognize the irony.

You can join the early adopter discussion on [GitHub](https://github.com/getsentry/sentry/discussions/109234).

Sentry analyzes your traces and logs using AI to detect issues that traditional pattern-matching detectors can't catch. Instead of relying on hardcoded rules, AI Issue Detection identifies problems across broader trace context, using a trained model to create issues that closely match [designated categories](https://docs.sentry.io/product/issues/issue-details/ai-detected-issues.md#issue-categories).

## [Issue Categories](https://docs.sentry.io/product/issues/issue-details/ai-detected-issues.md#issue-categories)

AI Issue Detection classifies detected issues into the following categories:

| Issue Category      | Description                                       | Possible Issue Title                                                      |
| ------------------- | ------------------------------------------------- | ------------------------------------------------------------------------- |
| HTTP                | Issues related to HTTP requests and responses     | Inefficient HTTP Requests, Degraded HTTP Operation, Failed HTTP Operation |
| Database            | Issues related to database queries and operations | Inefficient Database Queries, Degraded Database Operation                 |
| Runtime Performance | General runtime performance problems              | Blocking Operation, Degraded UI Performance                               |
| Security            | Potential security concerns detected at runtime   | Potential Security Leak, Potential Security Risk                          |
| Code Health         | Misconfigurations or usage of deprecated features | Configuration Warning, Deprecation Warning                                |

## [Configuration](https://docs.sentry.io/product/issues/issue-details/ai-detected-issues.md#configuration)

### [Enabling AI Issue Detection](https://docs.sentry.io/product/issues/issue-details/ai-detected-issues.md#enabling-ai-issue-detection)

AI Issue Detection is available to organizations with the Early Access feature enabled on a paid account.

You must also have the "Show Generative AI Features" toggle enabled in **Organization Settings > General**.

### [Project-Level Toggles](https://docs.sentry.io/product/issues/issue-details/ai-detected-issues.md#project-level-toggles)

Under **Project Settings > Performance**, the **AI Issue Detection** toggle controls whether Sentry runs AI issue detection at all. If toggled on, you can enable or disable each category individually.

All toggles are enabled by default.

## [Issue Details Page: Span Evidence](https://docs.sentry.io/product/issues/issue-details/ai-detected-issues.md#issue-details-page-span-evidence)

When viewing an AI-detected issue, the span evidence section shows:

* **Transaction** — The transaction where the issue was detected (links to the transaction summary).
* **Explanation** — A description of what the problem is.
* **Impact** — The potential impact of the issue.
* **Evidence** — Supporting detail from the trace.
* **Trace** — A preview of the trace, and a link to the full trace view.