The LeanData AI Assistant is a natural-language chat experience that helps admins investigate audit logs directly from the Audit Logs page. Instead of opening individual log entries and cross-referencing graph configuration to figure out why a record was processed a certain way, you can ask the assistant questions in plain language and receive answers that combine the record’s audit log with the relevant graph topology, match logic, and routing context.
The assistant is built on top of LeanData’s routing engine, so it has access to your deployments, your match logic, and the full journey of a record across Orchestration and BookIt audit logs. It can explain single log entries, summarize multi-log journeys, and execute searches on your behalf.
The LeanData AI Assistant helps admins quickly understand and explain LeanData routing behavior. Common scenarios include:
- Explaining a single audit log in plain language to share with a non-technical stakeholder, such as a sales rep asking why a lead was assigned to them.
- Understanding match decisions on Lead-to-Account, Contact-to-Account, or similar match nodes, including which candidate records were considered and why one was selected over the others.
- Exploring the route not taken by asking what would have needed to be different for the record to take a different edge or land on a different owner.
- Summarizing a multi-log journey across Orchestration and BookIt as one narrative, for example a lead that routes through Orchestration and then books a meeting through BookIt for Forms.
- Searching audit logs with natural language when you do not remember the exact filter or field name, for example “show me all logs for leads from Acme that ended in the catch-all queue this week.”
- Onboarding newer admins or sales support staff who do not yet have deep familiarity with your routing graphs.
Want more? Catch the full conversation here.
Video Transcript
Cool . Thanks , Kevin . Hey , everyone . I’m excited to talk about our new LeanData AI assistant . So this is a new , jump forward in some of our AI capabilities where we are gonna be bringing a new AI assistant into our audit logs . So with this assistant in this release , you will be able to kind of talk with this assistant , within audit logs to ask more about this details of specific logs and how routing , assignments were made . So before you’d have to kind of go in if , for example , a rep would ask you a question like , hey . Why did I actually get this lead ? Why did this route to me ? You as an admin would likely have to go into the LeanData , open up audit logs for that specific object , the lead object , for example , and then trace back to find the specific log that that rep was asking about . After doing so , what you do is you’d probably read through that path , try to understand exactly what happened , what are the characteristics of the lead that made it route a certain way , and finally end up at that rep . From there , what you do is you’d probably try to translate that into something that the rep can understand and then send that information back to the rep . Overall , pretty long process , but we know it’s kind of a question that , a lot of you admins do get day to day from your reps . So the purpose of this assistant is really to help make that process easier . So rather than going through that manual process , what you might do is actually just ask directing the assistant . Hey . Why did this lead named x person route to x user ? What it’s gonna do is now it’s gonna actually pull up that log for you on its own . No need to actually search that yourself . And then return that answer in natural language . That way you can kinda read over it . It’s already prepped for you to just send that back to your rep . Overall , really wanting to make that process a lot easier for you all . But besides that , there are also other questions you might be able to ask , like , hey . Why did this why did this record error , for example ? And that can , kind of , help you , kind of resolve any of the errors that might be coming out in your routing flows . We do have some additional just , like , AI assistant features that’ll help here . We do have additional conversation based threads so that you can actually have different conversations based off of and take up of pick up on certain conversations based off of , like , what you’ve asked it before . And that’ll really help you organize your work efficiently there as well . Yeah . It sounds like a no . It’s definitely now a model that folks are used to interacting with the chat assistant in various capacities . So I think this will be a very easy thing to pick up for folks . But , you know , as for the time savings aspect , do you have any metrics around how much you would expect a typical admin to save on a weekly basis by using something like this versus the old method that you described ? Yeah . Absolutely . I mean , I just kinda went through that process itself on , like , how an admin how you all might be doing this today . Yeah . So I think , like , per time , like , a rep asks , like , I think that saves you ten minutes or so depending on , you know , how quickly it actually takes you to look at that path . So just think about that , how that expands into weekly . I think there is just a large number of time savings that can be done answering those questions so that you can actually better focus on , you know , your actual day job , which is not answering those questions . Yeah . Yeah . Absolutely . Also , another question about so this will give you information about how something was routed . Right ? But does it have the ability to then go a step further and then make recommendations for , let’s say , if it is a graph error or something that was set up in a certain way to how would you want to set it up so that you get the result that you want ? Yeah . So that’s actually gonna be answered with our next iteration of the AI assistant , which is gonna be bringing it into the float builder itself . You’d be able to ask it questions like , hey . I see this error . How do I fix my graph so that , that error doesn’t happen again ? So that’s gonna be coming up next quarter . So kind of giving you a little preview about that . So , yeah , this first iteration is gonna be mostly on logs , and then you’re gonna see this come up in other parts of our product , in the future as well
