Troubleshooting AI Enrichment with Select List Outputs

Andrew Thomas · 2025-03-18 20:23:25.227456+00

Hi team -- I'm working on an AI enrichment, and I'm using field outputs with select lists. I've done this in the past, but for some reason the output is not respecting my select list options. Do you have any advice here?

Troubleshooting AI Enrichment with Select List Outputs | Clay

Andrew Thomas
·
·
Andrew Thomas
·
·
Table: https://app.clay.com/workspaces/10648/workbooks/wb_RejaUaU5NegY/tables/t_HvEKQhPgxZ3e/views/gv_NiSEXhk5GHgW
Channeled
APP
·
·
It seems like you're having an issue with your AI enrichment output not respecting your select list options. To address this, let's first check a few things: 1. Make sure you've correctly defined your column outputs as "Select" data type in the AI integration setup. 2. Verify that your prompt is instructing the AI to use the specific options you've defined for the select list. 3. Double-check that the AI's response is being correctly mapped to the intended field. If you've confirmed these and are still experiencing issues, it would be helpful to see the exact JSON output. Could you please copy and paste the JSON into the chat so we can troubleshoot further?
Source: Use AI integration overview | Documentation | Clay University
Channeled
APP
·
·
To resolve the issue with your AI enrichment output not respecting select list options, let's check a few things: 1. Ensure you've defined your column outputs as "Select" data type in the AI integration setup. 2. Verify that your prompt is instructing the AI to use the specific options you've defined for the select list. 3. Double-check that the AI's response is being correctly mapped to the intended field. If you've confirmed these and are still experiencing issues, it would be helpful to see the exact JSON output. Could you please copy and paste the JSON into the chat so we can troubleshoot further?
Source: Use AI integration overview | Documentation | Clay University
David Gabriel (ViewIn Advisory)
·
·
Hey Andrew, I'm not working for Clay, but can help out. Can you share an example of the prompt that you're using for the output?
Andrew Thomas
·
·
Hey -- Part of the prompt includes this: "**Location_Rating:** This determines whether or not a product is safe to operate in humid, moist, or wet locations. These types are “Dry Location”, “Damp Location”, “Wet Location” and the output can only be one of these three options." I have other "select" type outputs, and it's working fine. I'm just getting an error with this one...
LuisArturo (Clay)
·
·
Hey there Andrew thanks for reaching out and appreciate you jumping in David! Taking a look at your table I see that it the column is now outputting the correct result here, did you still need any help with this.
Andrew Thomas
·
·
Thanks LuisArturo (Clay) -- I ended up adjusting the prompt, and I am getting more reliable output. I've just never seen an instance where an AI action in Clay didn't respect the select list options (regardless of the prompt). Is this something you've seen before?
Andrew Thomas
·
·
Interestingly, I'm seeing this with another attribute as well.
Bo (Clay)
·
·
Hey Andrew, Could you show us where you're seeing this issue as well, please?
Andrew Thomas
·
·
Sure thing. I'll run some more tests and try it again.
Andrew Thomas
·
·
Okay... Here's the table: https://app.clay.com/workspaces/10648/workbooks/wb_RejaUaU5NegY/tables/t_HvEKQhPgxZ3e/views/gv_NiSEXhk5GHgW
Andrew Thomas
·
·
Rows 22, 24, and 25 are good examples of the error.
Andrew Thomas
·
·
Row 22 has a Location_Rating of "Wet", but in the output settings for the AI column, I have that output restricted to 3 values. It is also addressed in the prompt.
LuisArturo (Clay)
·
·
Hey there Andrew thanks for sharing this, I have seen this occur before, but that is when there is a large number for the number outputs expected, as this puts a lot of strain on the AI to perform. Granted it usually only happens for a handful of rows just like you have experienced. Sometimes reworking the prompt can help it get the right answers, other times just rerunning the rows can get the correct response. This is essentially coming down to the AI model being pushed to its limits here.

21 comments