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
{{ message }}
This repository was archived by the owner on Sep 2, 2025. It is now read-only.
Not providing entity names and types in your prompt makes the prompt unhelpful. The prompt, “What’s wrong with the api-gateway?” does not provide entity names or types. The level of specificity is low and returns an overwhelming set of responses that might or might not be useful in your troubleshooting.
83
+
Not providing entity names and types in your prompt makes the prompt unhelpful. The prompt “What’s wrong with the api-gateway?” does not provide entity names or types. The level of specificity is low and returns an overwhelming set of responses that might or might not be useful in your troubleshooting.
:guilabel:`Paymentservice in online boutique env is having issues in past 15 mins. Look for any relevant error exemplar traces. Once you've identified the exemplar traces, analyze each full trace by its trace ID`
192
+
:guilabel:`Paymentservice in online boutique env is having issues in past 15 mins. Look for any relevant error exemplar traces. After identifying the exemplar traces, analyze each full trace by its trace ID`
193
193
194
194
The third example prompt expands on the second example prompt. The second example prompt was good, but the third is excellent. One way to improve a prompt when you don’t know more specific information is to instruct the Assistant to extract certain details, then you can further prompt the Assistant using the extracted details. In this excellent example prompt, the Assistant extracts traces. Then it examines the traces and provides you with its analysis. From there, you can ask more and more specific questions based on information in the Assistant’s analysis. You might want to tell the Assistant how many exemplar traces to analyze so that the Assistant does not overwhelm you with a very large response and exceed context limitations of the conversation.
195
195
@@ -209,8 +209,8 @@ When you want to create a chart in Splunk Observability Cloud, you might prompt
209
209
210
210
The preceding prompt is excellent because it gives the Assistant a fair amount of detail on what you want to know. The Assistant can make a functional chart based on the information you provide. You can follow up to adjust your chart after you see it. For example, you can then tell the Assistant to adjust the chart to a particular 30-minute window.
For specific instructions on how access and use the AI Assistant, see :guilabel:`o11y-ai:`.
212
215
213
-
214
-
215
-
216
-
216
+
To learn about Splunk's commitment to responsible AI, see :new-page:`Responsible AI for AI Assistant in Observability Cloud <http://splunk.com/en_us/about-splunk/splunk-data-security-and-privacy/responsible-ai-for-ai-assistant-in-observability-cloud.html>`.
You can give feedback to the AI Assistant in development team by selecting the thumbs up or thumbs down icon that appears after each AI Assistant response.
55
55
@@ -91,7 +91,20 @@ When you interact with AI Assistant in Observability Cloud, Splunk collects and
91
91
* - Usage data
92
92
- Usage data is more fully described in the Splunk Privacy Statement. Examples include “thumbs up”, “thumbs down”, “chat id”, “copy”, “tokens used”, and “response length”.
93
93
94
+
You can activate and deactivate data sharing by going to :guilabel:`Settings`. On the General Organization Settings page, go to the AI Assistant Management section. Select :guilabel:`AI Assistant in Observability` to activate the AI Assistant for your organization.
95
+
96
+
If you do not want to share your data, deselect :guilabel:`Allow my AI service data to be used for research and development purposes`.
Learn how to prompt the AI Assistant effectively by reading :ref:`o11y-ai-promptlibrary`. You can find general guidance on how to prompt the Assistant to achieve the best results, as well as see sample prompts and learn what makes a prompt excellent, good, or poor.
109
+
110
+
To learn about Splunk's commitment to responsible AI, see :new-page:`Responsible AI for AI Assistant in Observability Cloud <http://splunk.com/en_us/about-splunk/splunk-data-security-and-privacy/responsible-ai-for-ai-assistant-in-observability-cloud.html>`.
0 commit comments