Predictive Intelligence and a Flow
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
‎02-13-2024 02:38 AM
I'm using a classification definition to predict the Supporting Service of all incidents newly opened via email or self-service. I'm also using a Flow to get this prediction and assign the Supporting Service for the incident accordingly. When I test the Flow within Flow Designer, everything seems to work perfectly fine. However when I create a new incident, for instance via self-service, it appears that my model returns an error. I'm also using the exact same incident to do the test inside Flow Designer, so I'm really baffled. Here's what I see in the test results / flow context when I look at the outcome of the classification prediction action:
Test result:
Flow execusion context:
Can anyone tell me how it is that I get these two different outcomes, even though it's the exact same incident? I'd really appreciate any tips!

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
‎02-14-2024 03:51 AM
ERR014: ML Object with name null is not found indicates that it is unable to find your solution that you have defined in the flow configuration when invoking the prediction. Can you take a screenshot of this flow config where you are calling the prediction on your solution.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
‎02-14-2024 06:20 AM
Hi Brian, I've updated the description of the problem a litte, I'm no longer getting the "not found" error after changing the flow context, but the error I've shown in the post above.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
‎02-14-2024 06:18 AM
I'm updating the description of the problem a little here based on new observations. The "not found" issue may have had something to do with the flow context. However the issue remains in a slightly different form. When I create a new incident via for instance self-service, I get this error:
Which apparently indicates that no prediction was made, which is also what I see when I test the model directly with this newly created incident. "unable to predict". However, when I test the model or the flow with one of the already existing incidents, everything works, as shown in the original post.
So, any ideas anyone?

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
‎02-14-2024 09:04 PM
So what is the behavior when you Open Incident Table and Submit the Incident ?
what is the Flow Trigger Condition?
Regards
RP