I'd like to hear suggestions on using AI activities when there's a publishing schedule that's shorter than the learning may take to build the model. 

I'm curious about expected usage, and perhaps some examples of successful examples. I have seen cases where we felt after reviewing the results it was best to exclude the thousands of Audience Manager audiences, and test that against leaving them in. 

I'd like to hear Drew's thoughts on leveraging the Models API to "subtractively" influence the AI inputs to Automated Personalization and Auto-Target? I could see wanting to put more influence on carefully planned profile values by removing some of the other inputs. 

Not related, but I have one of their die-cast cement trucks and one of their baseball hats. 

I'd also recommend investigating User Based Recs and Cart Based Recs, which leverage our AI capabilities. They work as a "multi-input" recommendation so we're basing it on multiple items instead of a single item. They allow you to do very personalized recommendations in any part of the site based on...

Recs is definitely something that requires a fair amount of planning in the implementation process. I would suggest starting with a list of placements that you want to use, and make a list of what types of things you need to know to do what you want to accomplish as far as the business rules/logic. ...

Yes, you have John, Justin and Bill standing by. You may want to refresh the page. 

Hi, welcome. You can create a separate collection to sort out the different types of content, so you could have a Collection that holds products, and another that contains articles, and then you apply whichever one you need to a specific Recommendation. Make sure you have a good plan on how to separ...

Welcome everyone. I'm Bill Ozinga, and am looking forward to answering your Recommendations questions this morning. 

Yes, it is AP only.