master
md 77 lines 2.93 KB
Rendered Raw
1 # AI-Powered Alert Troubleshooting
2
3 ## Overview
4
5 When an alert fires, you can use AI to generate a detailed troubleshooting report that analyzes whether the alert requires immediate action or is just noise. The AI examines your alert's history, correlates it with thousands of other metrics across your infrastructure, and provides actionable insights—all within minutes.
6
7 ![Ask AI from Alerts](https://raw.githubusercontent.com/netdata/docs-images/refs/heads/master/netdata-cloud/netdata-ai/alert-troubleshoot-1.png)
8
9 ### Key Benefits
10
11 - **Save hours of manual investigation** - Skip the initial data collection and correlation work
12 - **Reduce alert fatigue** - Quickly identify false positives versus legitimate issues
13 - **Get actionable guidance** - Receive specific next steps based on the analysis
14 - **Start from insight, not zero** - Begin troubleshooting with a comprehensive baseline analysis
15
16 ### How It Works
17
18 The AI troubleshooting engine performs three key analyses when you trigger an investigation:
19
20 1. **Alert Analysis** - Examines the alert's history and underlying metric behavior to determine if it's a transient false positive or legitimate issue
21 2. **Correlation Discovery** - Scans thousands of metrics and log patterns across your infrastructure to identify what else was behaving abnormally at the same time
22 3. **Root Cause Hypothesis** - Provides a summary of findings and suggests likely root causes, pointing you to the most relevant metrics or dimensions
23
24 ### Starting an Alert Investigation
25
26 You can trigger AI troubleshooting in three ways:
27
28 #### From the Alerts Tab
29
30 Click the **"Ask AI"** button next to any active or recent alert.
31
32 <!--
33
34 ![Alert tab with Ask AI button highlighted](screenshot-alerts-tab-ask-ai.png)
35
36 -->
37
38 #### From the Insights Tab
39
40 1. Navigate to the **Insights** tab
41 2. Select **"Alert Troubleshooting"** from the investigations section
42 3. Choose any recent alert from the dropdown menu
43
44 <!--
45
46 ![Insights tab showing Alert Troubleshooting option](screenshot-insights-alert-troubleshooting.png)
47
48 -->
49
50 #### From Alert Notifications
51
52 When you receive an alert email, click the **"Troubleshoot with AI"** link to automatically start the investigation.
53
54 <!--
55
56 ![Email notification with Troubleshoot with AI link](screenshot-email-troubleshoot-link.png)
57
58 -->
59
60 ### Understanding Your Report
61
62 Reports typically generate in 1-2 minutes. Once complete:
63
64 - The report appears in your **Alerts** tab
65 - A copy is saved in the **Insights** tab under "Investigations"
66 - You receive an email notification with the analysis summary
67
68 ![Alert Troubleshooting report example](https://raw.githubusercontent.com/netdata/docs-images/refs/heads/master/netdata-cloud/netdata-ai/alert-troubleshoot-report.png)
69
70 ### Access and Availability
71
72 - Generally available in Netdata Cloud (Business and Free Trial)
73 - Eligible Spaces receive 10 free AI runs per month; additional usage via AI Credits
74
75 :::note
76 Track AI credit usage from `Settings → Usage & Billing → AI Credits`.
77 :::