Troubleshooting LinkedIn Enrichment and AI Personalization Issues

Caroline B. · 2025-11-09 02:49:30.473172+00

Hi! Quick question regarding LinkedIn enrichment + AI personalization not pulling profile content. I’m trying to generate a personalized opening sentence for cold emails using information from a contact's Linkedin profile. I used a waterfall to find the LinkedIn URL, and the correct LinkedIn profile appears in the column (I validated it manually). The issue: Even though the person's Linkedin profile has content in the Experience/About section, the AI produces generic output that doesn’t reference anything from their Linkedin. It seems like the Experience/About data isn’t being passed through. What I need help with: • Is there a known issue where LinkedIn profile content (i.e. Experience/About) doesn't populate when the Linkedin URL comes from a waterfall? • Should I be using a different LinkedIn enrichment field to pull this information from a profile? Appreciate any help!

Troubleshooting LinkedIn Enrichment and AI Personalization Issues | Clay

7 comments

· Sorted by Oldest

Clay Support
APP
·
·
To get Experience/About data from profiles, use the "Enrich Person from Profile" integration which retrieves comprehensive details including work experience from profile URLs.
You can then reference specific experience data by drilling down into the experience list - expand the first item (Index 0) to access details like company name, role title, or summary.
Note that our data providers don't use active sessions to scrape live data, so some profile fields may not be visible if they require being logged in. This could explain why Experience/About content isn't populating even with valid profile URLs.
Clay Support
APP
·
·
Is that what you were looking for?
Clay Support
APP
·
·
If you still need help with pulling profile content or using the enrichment fields, I’m here to assist. Would you like to provide more details about what you’re trying to achieve or any specific issues you’re encountering?
Asher
·
·
Hey Caroline B., thought I’d jump in with a couple of pointers. There are generally two inputs people rely on, which it seems like you are using as well:
1.
Their LinkedIn summary
2.
Their current or past experience
For the summary (See first screenshot): If the person doesn’t have a LinkedIn summary, the model won’t have anything meaningful to work with. In your case for example, I found your linkedin profile, and seems like your summary field is blank, so Clay can’t use that as a personalization source. For experience data (See second screenshot): Clay returns the experience section as a JSON array, meaning each role is its own object. Because of that, you can’t just tell the AI to “look at the profile”, it will treat it as unstructured text and give weird results. The right way is to first use formulas to extract and format the relevant data from each experience item, then feed that structured version back into your prompt. That’s what makes the personalization reliable. I also have some thoughts on how to get the most out of AI for personalization overall, but figured these two points would be most useful to you right now. Feel free to DM me if you want to dive deeper or if you want the template to extract all the 'summary' from each experience, happy to help!
Clay Support
APP
·
·
You're absolutely right about the experience data structure. Experience data returns as a JSON array where each role is a separate object.
To use this data effectively, you need to drill down into specific items within the experience list and reference individual endpoints like company name, role title, or summary from each experience object.
Simply telling AI to "look at the profile" won't work because it treats the unstructured JSON as text. Instead, use formulas to extract and format the relevant experience data first, then feed that structured version into your AI prompt for reliable personalization.
Clay Support
APP
·
·
Did that answer your question?
Clay Support
APP
·
·
If you still need help with extracting or formatting experience data for AI personalization, I’m happy to assist further. Would you like to share more about the specific challenges you’re facing or the results you want to achieve?

Clay Support
APP
·
·
To get Experience/About data from profiles, use the "Enrich Person from Profile" integration which retrieves comprehensive details including work experience from profile URLs.
You can then reference specific experience data by drilling down into the experience list - expand the first item (Index 0) to access details like company name, role title, or summary.
Note that our data providers don't use active sessions to scrape live data, so some profile fields may not be visible if they require being logged in. This could explain why Experience/About content isn't populating even with valid profile URLs.
Clay Support
APP
·
·
Is that what you were looking for?
Clay Support
APP
·
·
If you still need help with pulling profile content or using the enrichment fields, I’m here to assist. Would you like to provide more details about what you’re trying to achieve or any specific issues you’re encountering?
Asher
·
·
Hey Caroline B., thought I’d jump in with a couple of pointers. There are generally two inputs people rely on, which it seems like you are using as well:
1.
Their LinkedIn summary
2.
Their current or past experience
For the summary (See first screenshot): If the person doesn’t have a LinkedIn summary, the model won’t have anything meaningful to work with. In your case for example, I found your linkedin profile, and seems like your summary field is blank, so Clay can’t use that as a personalization source. For experience data (See second screenshot): Clay returns the experience section as a JSON array, meaning each role is its own object. Because of that, you can’t just tell the AI to “look at the profile”, it will treat it as unstructured text and give weird results. The right way is to first use formulas to extract and format the relevant data from each experience item, then feed that structured version back into your prompt. That’s what makes the personalization reliable. I also have some thoughts on how to get the most out of AI for personalization overall, but figured these two points would be most useful to you right now. Feel free to DM me if you want to dive deeper or if you want the template to extract all the 'summary' from each experience, happy to help!
Clay Support
APP
·
·
You're absolutely right about the experience data structure. Experience data returns as a JSON array where each role is a separate object.
To use this data effectively, you need to drill down into specific items within the experience list and reference individual endpoints like company name, role title, or summary from each experience object.
Simply telling AI to "look at the profile" won't work because it treats the unstructured JSON as text. Instead, use formulas to extract and format the relevant experience data first, then feed that structured version into your AI prompt for reliable personalization.
Clay Support
APP
·
·
Did that answer your question?
Clay Support
APP
·
·
If you still need help with extracting or formatting experience data for AI personalization, I’m happy to assist further. Would you like to share more about the specific challenges you’re facing or the results you want to achieve?