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
title: Sumo Logic Copilot - Unstructured Logs Support (Beta)
4
-
description: Streamline your log analysis with Sumo Logic Copilot, our AI-based assistant designed to simplify log analysis by allowing you to ask questions in plain English and providing search suggestions without the need to write log queries.
4
+
description: Streamline your log analysis with Sumo Logic Copilot, our AI-based assistant that simplifies log analysis by letting you ask questions in plain English, even for logs without a well-defined structure.
5
5
keywords:
6
6
- copilot
7
7
- artificial intelligence
@@ -19,29 +19,63 @@ import useBaseUrl from '@docusaurus/useBaseUrl';
This feature is in Beta. To participate, contact your Sumo Logic account executive.
22
+
This feature is in Beta. To participate, contact your Sumo Logic account executive or [enroll here](https://forms.gle/LozrrAppM9FM94tS9).
23
23
24
-
Copilot’s Unstructured Logs Support broadens Copilot’s query translation and suggestion capabilities to raw, non-JSON text logs. By removing the need for defined fields, organizations can gain deeper insights from logs that don’t conform to a standard structure. Here are some key highlights:
24
+
Unstructured Logs Support for [Sumo Logic Copilot](/docs/search/copilot), our AI assistant, enables it to understand and provide insights from raw, text-based logs—even if they don't follow a structured format like JSON. This means you can ask questions in plain English and get meaningful results from nearly any log data, without requiring Field Extraction Rules (FERs).
25
25
26
-
***Broader coverage**
27
-
- Copilot now works with any text-based logs, making it ideal for heterogeneous environments or custom log formats.
28
-
***Improved usability**
29
-
- Receive suggestions and sample searches you can adapt or refine as needed.
30
-
***Performance and reliability**
31
-
- Thorough testing shows that query execution and response times remain consistent with Copilot’s structured log functionality.
32
-
- Our ongoing QA focuses on delivering accurate results, even in large and diverse log sets.
33
-
***Security and compliance**
34
-
- We follow the same strict security standards used across all Sumo Logic services.
35
-
- Unstructured Logs Support leverages Copilot’s existing safe-handling mechanisms for user data.
36
-
***Common use cases**
37
-
-**Broad keyword searches**. Find relevant entries in raw text (for example, by IP address or error keyword) without needing to define fields.
38
-
-**Error analysis & triage**. Quickly locate top errors in logs that lack a clear structure.
39
-
-**Security & threat hunting**. Identify suspicious patterns, attacker IOCs, or critical authentication failures in free-form logs.
40
-
***Future enhancements**
41
-
-**Refined language parsing**. We plan to further improve how Copilot detects common terms like "login," "IP," and "authentication."
42
-
-**Advanced filtering**. Additional options (for example, time range, user ID, IP, and location) are planned for the final release.
26
+
## What's new
43
27
28
+
Previously, Copilot worked best on structured (JSON) logs. Now, it automatically applies parsing logic to unstructured logs, even if no FERs are configured. This allows Copilot to interpret logs from many popular data sources out-of-the-box.
44
29
45
-
## Feedback
30
+
Copilot learns from usage patterns—if a log source is already used in dashboards or commonly queried, it’s more likely to produce strong results.
46
31
47
-
Organizations interested in participating in the Beta can coordinate with their Sumo Logic account teams. Any anomalies or performance concerns should be raised via normal Sumo Logic support channels.
32
+
***Broader coverage**. Copilot now parses and generates insights from unstructured log formats, even without FERs, making it useful for environments that include custom or inconsistent log types.
33
+
***Improved usability**. Ask questions in natural language. Copilot interprets your intent and suggests relevant searches—even for raw, non-JSON logs.
34
+
***Performance and reliability**. Response times and suggestion accuracy are consistent with Copilot’s structured log experience.
35
+
***Security and compliance**. The same strict data handling and privacy standards apply. Unstructured Logs Support builds on Copilot’s secure foundation.
36
+
***Common use cases**.
37
+
***Keyword-based search**. Search for IP addresses, error codes, or other patterns without needing a predefined schema.
38
+
***Error triage**. Quickly identify the most common error messages in raw logs to speed up troubleshooting.
39
+
***Threat hunting**. Detect suspicious activity, failed logins, or unusual patterns in plain-text logs.
40
+
***Smarter prioritization**. Frequently used data sources (such as those in dashboards or frequent queries) are prioritized for deeper insights.
41
+
42
+
## Tips and best practices
43
+
44
+
* Start with common natural language queries, like:
45
+
- “Show failed login attempts for the past 24 hours”
46
+
- “Find logs with IP 192.0.2.0”
47
+
- “What are the top 5 errors from nginx logs today?”
48
+
* Use dashboards to monitor your log sources. Copilot performs better when logs are part of existing queries and visualizations.
49
+
* Logs with clear timestamps, separators (like commas or tabs), and consistent patterns tend to yield better results.
50
+
51
+
## Related updates
52
+
53
+
These recent Copilot enhancements make it even easier to work with unstructured logs:
54
+
55
+
***Dynamic conversation titles**. Your queries are automatically named for easy organization and retrieval.
56
+
***"Open in Copilot" for alerts**. Investigate alerts directly in Copilot without losing context.
57
+
***Suggestion pinning**. Pin suggestions inside a conversation to revisit them during your investigation.
58
+
59
+
## FAQ
60
+
61
+
**Does this replace Field Extraction Rules (FERs)?**<br/>
62
+
No. Copilot works with or without FERs. While FERs are useful for structured analysis, they're no longer required for Copilot to interpret unstructured logs.
63
+
64
+
**Will Copilot interpret all my logs?**<br/>
65
+
Copilot prioritizes data sources that are already used in dashboards or frequent queries. This improves the relevance of insights and helps focus on high-value logs.
66
+
67
+
**How is this different from structured log support?**<br/>
68
+
Structured logs have predefined fields, allowing Copilot to map queries directly. For unstructured logs, Copilot uses AI and parsing techniques to infer structure on the fly.
69
+
70
+
71
+
## Feedback and support
72
+
73
+
We’re actively looking for customers to participate in the beta and provide feedback. Ideal participants:
74
+
75
+
* Use dashboards for monitoring across most of their data sources
76
+
* Have some hands-on experience with Copilot
77
+
* Are willing to provide detailed feedback during the beta
78
+
79
+
👉 [Click here to enroll](https://forms.gle/LozrrAppM9FM94tS9)
80
+
81
+
To report issues or share feedback, reach out through your Sumo Logic account team.
0 commit comments