Meeting Title: Brainforge x 8x8 Cancellation Analysis Sync Date: 2026-04-29 Meeting participants: read.ai meeting notes, Pranav, YvetteRuiz
WEBVTT
1 00:01:57.370 ⇒ 00:01:58.480 Pranav: I don’t think that’s
2 00:02:02.160 ⇒ 00:02:03.100 Pranav: How do you think?
3 00:02:14.100 ⇒ 00:02:15.210 Pranav: Dr. May God.
4 00:02:16.210 ⇒ 00:02:23.750 Pranav: Let’s not wait for the road to get better and close it, and… 35 moment.
5 00:02:37.230 ⇒ 00:02:38.370 YvetteRuiz: Hey, Pranav!
6 00:02:39.140 ⇒ 00:02:40.350 Pranav: Hey, Yvette!
7 00:02:40.540 ⇒ 00:02:41.119 YvetteRuiz: How are you?
8 00:02:41.120 ⇒ 00:02:43.649 Pranav: How are you? I’m good, I’m good. How are you doing?
9 00:02:43.650 ⇒ 00:02:47.929 YvetteRuiz: I’m doing alright, thank you for asking. Hang on just a sec.
10 00:02:48.350 ⇒ 00:02:48.970 Pranav: Totally.
11 00:02:58.110 ⇒ 00:02:59.590 YvetteRuiz: Hmm, alrighty.
12 00:02:59.890 ⇒ 00:03:02.290 Pranav: I’m gonna be wearing my hat today. My hair is not.
13 00:03:02.290 ⇒ 00:03:06.010 YvetteRuiz: No worries, no worries.
14 00:03:06.010 ⇒ 00:03:07.990 Pranav: How’s your week been?
15 00:03:08.660 ⇒ 00:03:14.620 YvetteRuiz: Oh, man, it’s been a week, really working to get myself caught up.
16 00:03:15.440 ⇒ 00:03:18.030 Pranav: Because you were out mid-last week, right?
17 00:03:18.030 ⇒ 00:03:21.440 YvetteRuiz: Yeah, I was out Wednesday, Thursday, and Friday, yes,
18 00:03:21.440 ⇒ 00:03:22.070 Pranav: Yeah.
19 00:03:22.340 ⇒ 00:03:22.690 YvetteRuiz: Yep.
20 00:03:22.690 ⇒ 00:03:39.019 Pranav: Okay, yeah, so I… yeah, we haven’t talked in probably, like, a week and a half or something, so I just wanted to put this on the calendar, especially since we just started talking about transcripts, and then… I thought we had a really good call on Tuesday of last week that had me thinking a lot about
21 00:03:39.020 ⇒ 00:03:46.139 Pranav: what are some cool ways to help you with just, like, getting more real-time data and getting all these systems connected?
22 00:03:46.740 ⇒ 00:04:04.439 Pranav: But yeah, first, I kind of wanted to talk about transcripts, you know, like, what we’re already working on. And so, we initially talked about, you know, department-based insights, which is still super valuable, but then you brought up cancellation transcripts specifically, and how can we get insights on those.
23 00:04:04.520 ⇒ 00:04:13.520 Pranav: I have such a good picture now, after talking to Janiece about just, like, the scale of things, like, I think yesterday she mentioned how you guys had 3,200 calls.
24 00:04:14.310 ⇒ 00:04:19.220 Pranav: And so, yeah, that’s not surprising to you, it sounds like, but to me, I was like, okay, wow.
25 00:04:19.410 ⇒ 00:04:21.009 Pranav: I knew the number of seats.
26 00:04:21.010 ⇒ 00:04:23.170 YvetteRuiz: It’s layered.
27 00:04:23.170 ⇒ 00:04:23.730 Pranav: Yeah.
28 00:04:23.730 ⇒ 00:04:39.020 YvetteRuiz: And we use it as a total because that is what’s handled, but it’s… it’s that cut in half because our calls are layered, so when the call comes in, it goes to reception, and then from reception, it’s distributed to the queue. So…
29 00:04:39.020 ⇒ 00:04:39.649 Pranav: That makes sense.
30 00:04:40.800 ⇒ 00:04:41.729 Pranav: I mean, it’s still a lot.
31 00:04:41.730 ⇒ 00:04:46.660 YvetteRuiz: Still, but it’s still… it’s, it’s, it’s big. I just wanted to… Break it down.
32 00:04:46.660 ⇒ 00:04:47.639 Pranav: Totally, no, I appreciate it.
33 00:04:48.200 ⇒ 00:04:55.050 Pranav: Yeah, that is super helpful. So… with that, right, I think…
34 00:04:55.250 ⇒ 00:05:04.320 Pranav: looking at data is super valuable, because you can make one decision, create one additional procedure for CSRs to follow, and that could…
35 00:05:04.430 ⇒ 00:05:21.260 Pranav: end up being dozens, if not hundreds, of, like, cancellations that don’t get canceled. One thing Janiece talked to me about yesterday was, like, there right now, there isn’t, like, a procedure, for example, when people are moving. We kind of just end the call there, and it just ends up being a canceled account.
36 00:05:21.300 ⇒ 00:05:26.239 Pranav: Whereas we can probably ask them, hey, are you moving into this area where we are also servicing?
37 00:05:26.610 ⇒ 00:05:31.019 Pranav: Just asking that additional question, and then maybe giving a little bit more of, like, a…
38 00:05:31.300 ⇒ 00:05:40.310 Pranav: a script or direction for CSRs would be super valuable, but the first step is knowing why are they canceling, so we can then…
39 00:05:40.370 ⇒ 00:05:56.150 Pranav: analyze that… I mean, that’s gonna be the analysis for basically why are they canceling, and then kind of give direction for, okay, how do we mitigate canceling? Like, then we can think strategically. You and Janiece are probably going to have the best kind of understanding of how to… the strategy behind that.
40 00:05:56.150 ⇒ 00:06:00.450 Pranav: But I think, kind of, what BrainForge can help so much with is…
41 00:06:00.520 ⇒ 00:06:04.489 Pranav: how can we first get that analysis to you? How can we
42 00:06:04.970 ⇒ 00:06:22.579 Pranav: let you look through the door and see all of these things that are happening across these 1,600 calls, per day. So, yeah, basically what I’m saying is, with department-based insights, I’m wondering, do you want to switch gear a little bit and have us focus initially right now on cancellations?
43 00:06:22.760 ⇒ 00:06:30.889 YvetteRuiz: Yeah, that is actually good, because I actually… I have a meeting next week with all… with Bobby.
44 00:06:30.890 ⇒ 00:06:45.529 YvetteRuiz: With Matt, and Bo, and Steven, and all the division managers, because cancellations are a hot topic right now. I mean, pretty much everything that I’m working on, Pranav, and I’m trying to get myself centered.
45 00:06:45.620 ⇒ 00:07:00.330 YvetteRuiz: because I do… in my bucket, I have a lot of things going on, but my focus, I want it to be strictly on how do we better the customer experience, right? Because, again, listening to phone calls, looking at our cancellations, I mean, those are all things, like.
46 00:07:00.490 ⇒ 00:07:16.370 YvetteRuiz: I need to get a good grip on, right? And so, just to give you just kind of what I share… I share on a monthly basis, but I shared this with everybody because I needed everybody to… to… to get a good look of what I’m talking about.
47 00:07:16.670 ⇒ 00:07:22.810 YvetteRuiz: I get my reports every month, so my March cancellations, I had…
48 00:07:23.430 ⇒ 00:07:36.110 YvetteRuiz: I don’t have my data here, but, in residential pests only, I had… in the month of March, I had 881 cancellations.
49 00:07:36.150 ⇒ 00:07:51.940 YvetteRuiz: Okay? 881 cancellations. My top reasons were moved, which is always the theme, okay? Contract fulfilled as needed, change service type, financial hardship, and then bad debt. In my HVAC department, I had 330 cancellations.
50 00:07:51.940 ⇒ 00:08:16.029 YvetteRuiz: Again, top one is contract fulfilled as needed, moved, competitor, unable to schedule, and then I had rodent… my rodent department, 299, lawn care, 244, lawn mowing, 214, mosquito, 184, commercial passed, 162. Washing and cleaning, 137. Termite, 103. Terry Mesh, 90.
51 00:08:16.150 ⇒ 00:08:23.779 YvetteRuiz: Water quality, 61. Pool and spa, 35 cancellations. You know, again, We’re just… we’re losing.
52 00:08:23.780 ⇒ 00:08:26.439 Pranav: know the reason, too. Like, with.
53 00:08:26.440 ⇒ 00:08:38.329 YvetteRuiz: Well, here’s where… I don’t trust… I’m gonna walk you through, but this is why I… I really need… I really want the transcripts to really help us, because I… that’s where we’re really gonna… because…
54 00:08:38.580 ⇒ 00:08:51.429 YvetteRuiz: right now, what happens, Pranav, is a call comes in, and that’s one channel, okay? That’s a call, that’s in my team’s handling it, right? Because then you got email, then you got other ways that come… that there’s cancellations coming through.
55 00:08:52.230 ⇒ 00:09:00.830 YvetteRuiz: We get the phone call, we take the reason, we attempt to save, that’s if, you know, the CSR is attempting to save, right?
56 00:09:00.940 ⇒ 00:09:15.659 YvetteRuiz: we attempt to save, and then we don’t handle the cancellation. We have to… we take care of it on the phone, but we gotta go in there, we gotta put a request in to our billing department, who processes the actual cancellation. From there to there.
57 00:09:15.740 ⇒ 00:09:22.970 YvetteRuiz: And it’s been known, human error, the reason that we initially put may not be what they use as the category, okay?
58 00:09:22.970 ⇒ 00:09:23.440 Pranav: I see.
59 00:09:23.440 ⇒ 00:09:30.679 YvetteRuiz: So, that could be… some false information right here. Then you have the ones that are just…
60 00:09:30.700 ⇒ 00:09:45.989 YvetteRuiz: cleanup stuff, you know what I mean? So, if I could really rely on my transcripts to give me that true data, then I really have some good insights, like, okay, what is… what are the true reasons? Because right now, I can tell you I have…
61 00:09:46.200 ⇒ 00:09:50.670 YvetteRuiz: I don’t know, probably over 20, 25 cancellation reasons?
62 00:09:50.810 ⇒ 00:10:09.670 YvetteRuiz: I can tell you, I probably don’t need that many reason categories. If I could really do a deep dive and tell me, okay, what are the true things that are being said on the phone? I could really narrow that bucket down, and we can really start honing in on, okay, what are our customers telling us, and what are we doing to attempt the save, and then how can we
63 00:10:09.670 ⇒ 00:10:13.679 YvetteRuiz: make that better. I mean, what opportunities are we missing?
64 00:10:14.190 ⇒ 00:10:26.450 Pranav: Gotcha. So, there’s a few things here, and I kind of want to figure out, okay, what data do we want to fact-check based on the transcripts, and what things are we confident are true based on the tag? So…
65 00:10:26.450 ⇒ 00:10:34.370 Pranav: We’re confident that there’s something within the 8x8 system that tags transcripts if they’ve… they’re cancellations, right?
66 00:10:34.850 ⇒ 00:10:35.350 Pranav: Okay.
67 00:10:35.350 ⇒ 00:10:36.460 YvetteRuiz: Correct, so we…
68 00:10:37.370 ⇒ 00:10:48.779 YvetteRuiz: the transcripts… well, let me back up, because we’ve not officially set up, and this is my data team, just because we don’t, you know, we don’t have a whole… we don’t have a big data team, right? We’ve never been able to set up
69 00:10:49.310 ⇒ 00:11:09.000 YvetteRuiz: our speech analytics piece of it, because the speech analytics piece in 8x8 has, tagging, so you can go… you can insert your key phrasing, so if they use the word move, you can… you can categorize. We haven’t officially did that. We’re not truly using deposition codes anymore, so somehow, someway, we would have to probably start
70 00:11:09.000 ⇒ 00:11:16.100 YvetteRuiz: Utilizing our phrases, our speech, speech, our speech analytic piece of it.
71 00:11:16.110 ⇒ 00:11:21.870 YvetteRuiz: to tag phrases, or use depositions, or… I don’t know how we would just scrub through the…
72 00:11:22.500 ⇒ 00:11:29.510 YvetteRuiz: do the transcripts themselves, and just pick up keywords. This is where I need your help, and kind of just devoting more time to.
73 00:11:29.700 ⇒ 00:11:33.849 Pranav: I just, I remember you saying at one point that we have certain IDs.
74 00:11:33.960 ⇒ 00:11:42.520 Pranav: for transcripts that were about cancellations for… so, but that isn’t… we don’t have the IDs for all of them, right?
75 00:11:42.520 ⇒ 00:11:43.039 YvetteRuiz: No, we shouldn’.
76 00:11:43.040 ⇒ 00:11:44.639 Pranav: That we picked. Yeah.
77 00:11:44.640 ⇒ 00:12:02.190 YvetteRuiz: Okay. Yeah, so we don’t have the whole… and I mean, we can start from ground zero, so, like, if you and I could spend some… some really… some good time, and I’m willing to do the investment, this is where I was talking about. I have a whole lot of things going on right now, but I want to peel off a lot of that stuff and simply focus on
78 00:12:02.210 ⇒ 00:12:08.479 YvetteRuiz: where it’s gonna make the most impact. And I already know everything on this is gonna make a big impact on, so…
79 00:12:08.590 ⇒ 00:12:24.400 YvetteRuiz: we could take some time and look at the 8x8 system, we could look at the speech analytics piece, I can bring David in, my data analyst, and we can start talking about, hey, let’s go ahead and use these key phrases. You know, let’s just tag those, right? And then we’ll just give it a trial run.
80 00:12:24.740 ⇒ 00:12:26.039 YvetteRuiz: Right. Okay, let’s…
81 00:12:26.700 ⇒ 00:12:35.399 YvetteRuiz: Whether it be through deposition, right? I’m just spit… I’m just spitballing things right now. This is where I just… I want to be able to collaborate on what is the best way to get this set up.
82 00:12:35.400 ⇒ 00:12:54.869 Pranav: Yeah, totally, yeah. So, I think what I’m hearing here is that we still don’t have a system in place where we can effectively filter transcripts from cancellations versus others, right? So that’s the first step. So, filtering all these transcripts from, hey, what are just, like, regular calls, maybe for new customers, existing customers, and
83 00:12:55.370 ⇒ 00:13:10.210 Pranav: let’s first take out the cancellation transcripts, right? Yep. So, there’s a few ways we can do it. We can do it the way that you were talking about within 8x8. There’s certain, features within there for keywords, depositions, things of that nature. There’s also things on…
84 00:13:10.790 ⇒ 00:13:27.080 Pranav: outside of 8x8 that we could do, which is kind of analyzing, like, a first pass per transcript to assess, okay, is this a cancellation based on the semantic phrasing of all the different… the conversation, basically? And then we can give a… a likelihood.
85 00:13:27.190 ⇒ 00:13:35.520 Pranav: Of is this cancellation or not? And so, yeah, from there, that sounds good to me, and, like, I definitely want to work with you on that.
86 00:13:35.780 ⇒ 00:13:44.749 YvetteRuiz: And thank you for saying that, because that was going to be… that was my question, and this is, again, where my ignorance comes in, right? Like, I don’t know, because I know what 8x8 has to offer.
87 00:13:44.980 ⇒ 00:13:56.049 YvetteRuiz: I’m… and of course, you know, I… I want to know what Brainforge can do now that you guys are in our 8x8 system and can pull our transcripts. So, to your point, to what you said.
88 00:13:56.440 ⇒ 00:14:07.540 YvetteRuiz: let’s just say I gave you a queue, and I’ll just use the home improvement queue, because that’s the smallest. Could you go through those calls
89 00:14:07.540 ⇒ 00:14:23.040 YvetteRuiz: I don’t know how that’s done, now that you have access to that. Could you go through those calls, get the transcripts on them, and run a utility, a tool, anything that picks up keywords on your end? Is that what you’re saying? Could be… is possible?
90 00:14:23.360 ⇒ 00:14:41.739 Pranav: Oh yeah, that’s totally possible. So whether it’s, like, you know, we do it… we just pull the transcript, we do it on our end, or 8x8 already has that built-in functionality, we’ll assess what is kind of the fastest and most effective way of doing this. So… yeah, I mean, these are all definitely options,
91 00:14:41.950 ⇒ 00:14:51.929 Pranav: Even if we wanna… the problem with, like, specific words, if maybe they said, like, a version of that word, or they said the same thing that is similar to that,
92 00:14:52.290 ⇒ 00:15:01.599 Pranav: you know, I think it’s pretty… like, this, if I’m to kind of think out loud with you, I think they’re probably going to be saying the word cancel in the…
93 00:15:02.140 ⇒ 00:15:05.009 Pranav: In the transcript, if it’s a cancellation.
94 00:15:05.010 ⇒ 00:15:21.979 YvetteRuiz: Let me share some… I actually have a class… not a class, I have a training tomorrow. I’m gonna be in Austin, I have a training, I’m gonna meet with all my leaders, because we’re gonna simply focus on moved, right? So I had a meeting with Steven and Beau, and we’re like, okay, here is all the percentage of the customers that are
95 00:15:22.260 ⇒ 00:15:47.219 YvetteRuiz: in our reasoning, have moved, right? It’s a lot of dollars that are going out the door, so I finally got them to commit and say, okay, if somebody calls in and says they moved today, that what’s the process, right? And I walked them through what should be the process, right? I’m sorry to hear that you’re moving, you know, I’m not sorry to hear, but thank you for letting me know that you’re moving. Are you moving within the Austin area, Corpus area, those things, right? And so, if the customer tells me, yes, they are.
96 00:15:47.220 ⇒ 00:15:48.700 YvetteRuiz: then, great!
97 00:15:48.820 ⇒ 00:16:08.159 YvetteRuiz: I could go ahead and get your services transferred. You have reward points on your… so I walked through those things, so we just kind of talked about, like, what are some of those safe tactics, or what are the things that we want to say? So I already have that script, all the offers, everything. So tomorrow, what I’m going to do is I have it all in a PowerPoint presentation. I’m putting it all together right now.
98 00:16:08.460 ⇒ 00:16:20.059 YvetteRuiz: I’m gonna go meet with my people, and I need to make sure that everybody knows, and then how are we gonna train the agents to start doing that? So, we could start with that. I don’t know, I’m just throwing that out there, but…
99 00:16:20.500 ⇒ 00:16:24.530 YvetteRuiz: I was gonna show you… transcripts.
100 00:16:25.830 ⇒ 00:16:28.680 YvetteRuiz: So what I did is I went ahead and I pulled
101 00:16:30.570 ⇒ 00:16:34.360 YvetteRuiz: I had my QA manager go in there and pull
102 00:16:35.410 ⇒ 00:16:46.780 YvetteRuiz: a handful of phone calls that I went through the report with that were categorized moved. I had her pull the phone call, and I had her pull the transcripts for me, and then I ran them through ChatGPT.
103 00:16:47.250 ⇒ 00:16:47.880 Pranav: Yep.
104 00:16:48.470 ⇒ 00:16:51.709 YvetteRuiz: And so, I just want to show you really quick, Vernav.
105 00:16:52.370 ⇒ 00:16:56.839 YvetteRuiz: Because I don’t even know, I mean, please feel free to stop me if I’m rambling.
106 00:16:56.840 ⇒ 00:16:57.480 Pranav: No, no, no.
107 00:16:57.480 ⇒ 00:17:01.000 YvetteRuiz: what I’m saying. Yeah. I’m happy to, like…
108 00:17:01.000 ⇒ 00:17:08.249 Pranav: There’s one other thing that I want to talk to you about that’s kind of relevant to this, so we can save some time at the end, but let’s go through this for right now.
109 00:17:08.250 ⇒ 00:17:11.769 YvetteRuiz: So, here’s the transcripts that she sent me, right?
110 00:17:11.770 ⇒ 00:17:12.390 Pranav: Yep.
111 00:17:13.240 ⇒ 00:17:24.529 YvetteRuiz: So, Michelle, I’m calling, hi, Michelle, I was calling because I have an account with you, and we recently moved, okay? And so, they’re talking about moved right here, and…
112 00:17:24.780 ⇒ 00:17:28.889 YvetteRuiz: So I went through that. You know, she handed it pretty okay.
113 00:17:29.200 ⇒ 00:17:31.420 YvetteRuiz: Then the next person…
114 00:17:34.290 ⇒ 00:17:41.550 YvetteRuiz: No, that’s the same person, I’m so sorry. Then you have this one right here, China. I need to cancel my services.
115 00:17:41.770 ⇒ 00:17:55.649 YvetteRuiz: okay, what’s the address? And then they go through it, and she’s talking, I’m actually moving, right? But there’s some things… so anyway, what I did is I took all these transcripts, I threw them into ChatGPT, and ChatGPT pretty much told me everything that I felt was going on.
116 00:17:55.780 ⇒ 00:18:05.140 YvetteRuiz: We’re going through the motions, we do a good job of gathering the information, gathering all that, but we’re not doing anything to attempt the save. There’s keywords in there that said.
117 00:18:05.280 ⇒ 00:18:17.199 YvetteRuiz: I want to cancel right now because I’m building a new house, but I may want to use your services in 6 months. Well, boom, I should have had something alert me saying, oh, okay, well, we can contact you. Something in there, so those are the things that…
118 00:18:17.200 ⇒ 00:18:29.449 YvetteRuiz: again, I don’t know if you guys can pull that and run that through the system and tell me what, because based off of the 10 calls that I sent ChatGPT, they were able to give me just kind of some solid, good information.
119 00:18:29.450 ⇒ 00:18:33.329 Pranav: Gotcha. So, I think what we can do is…
120 00:18:33.700 ⇒ 00:18:41.259 Pranav: Because that’s where the real value comes in, right? You already know that people are canceling, you know that the reason for a lot of it is moving.
121 00:18:41.290 ⇒ 00:18:58.870 Pranav: your… what you kind of want to know is, like, which one of these are… can we potentially save? Because they’ve expressed interest, like, yeah, 3 months from now, 6 months from now, or they’ve just kind of said… they just aren’t aware that you guys are servicing, like, in that other area. So you basically want to have, like.
122 00:18:59.020 ⇒ 00:19:04.100 Pranav: Groupings of all these individuals that canceled that are, hey, these ones, you know, they canceled.
123 00:19:04.220 ⇒ 00:19:06.739 Pranav: Their reasoning for canceling is…
124 00:19:06.940 ⇒ 00:19:15.990 Pranav: you know, it’s not kind of something that we can help with, you know? Or it’s not… for right now, it’s not, like, worth an effort. But then there’s a lot…
125 00:19:15.990 ⇒ 00:19:29.999 YvetteRuiz: buckets because you have, like, inefficient service. I was upset, you never took care of my problem. I have your moves, I have, I just… I can’t afford it anymore. You know, you have your buckets, so that’s what it’ll be able to tell me, but within those buckets.
126 00:19:30.210 ⇒ 00:19:47.009 YvetteRuiz: can it also tell me where are we missing the opportunities, right? Like, what can we do? Because that’s where the coach feature comes in, and that’s where the, okay, these are your reasons why the people are leaving, but what are we doing to attempt to make the saves? And then, if we don’t have those things in place today, then
127 00:19:47.270 ⇒ 00:19:56.119 YvetteRuiz: I need to go work with my leader, my higher-ups, and tell them, hey, I need more tools to be able to equip my team, to be able to give them something.
128 00:19:56.450 ⇒ 00:20:15.770 Pranav: Yes, definitely. And I think probably what we do is we do the same thing that we were thinking with department-based insights, except just for cancellations. And so let’s first do, like, a one-time analysis. Let’s see, like, what are the things that we’re noticing for just when we ingest, maybe, let’s say, the last couple weeks, or the last… you can give me a time frame.
129 00:20:16.120 ⇒ 00:20:24.259 Pranav: And with that, you know, yeah, there’s gonna be one additional step, which is, like, okay, first assessing which of these transcripts are cancellations, which are not.
130 00:20:24.300 ⇒ 00:20:29.299 Pranav: Or what we can also do is, if you have a whole host of
131 00:20:29.320 ⇒ 00:20:46.270 Pranav: of transcripts that you already have the IDs for, you know, you’ve already kind of done the manual check to say, okay, these are cancellations, but you haven’t run an analysis of, like, the reasons for why they canceled, then we can do that. And that can be our first pass.
132 00:20:46.280 ⇒ 00:20:53.440 Pranav: You know, we could do that very quickly. Does that sound like what we should do first, or do you think you’ve kind of already got those insights?
133 00:20:53.440 ⇒ 00:21:05.949 YvetteRuiz: No, I really… well, see, the thing is, is that I just… that’s what I’m trying to figure out, is, like, what would be the quickest way? Because, like, even if I run the report, I know all my cancellations, let’s… let’s just say I use the last 2 weeks, right? I already know.
134 00:21:06.120 ⇒ 00:21:14.500 YvetteRuiz: I can go in there and I could pull each call. I have to go in there and pull each call to get the trans… the transaction ID and get the transcripts for it.
135 00:21:15.290 ⇒ 00:21:25.899 YvetteRuiz: Is that the best way to go in there and do it? Just to confirm that that was the reason that they moved, and what opportunity did we miss? Or is there an easier way? And that’s why I’m thinking, if we set up
136 00:21:26.260 ⇒ 00:21:27.670 YvetteRuiz: 8x8.
137 00:21:28.600 ⇒ 00:21:34.860 YvetteRuiz: you know, to have those phrases, that’s gonna be the best way. I just didn’t know if there was…
138 00:21:35.010 ⇒ 00:21:52.240 YvetteRuiz: aside from me giving you the transaction IDs, is there an easier way? Like, if I just told you, hey, go through this queue, go through the home improvement queue, Pranog, pull those phone calls, because… and you could… we could use a small trade, we can use… because within the home improvement department, we have…
139 00:21:52.420 ⇒ 00:21:53.480 YvetteRuiz: Pool…
140 00:21:53.960 ⇒ 00:22:02.049 YvetteRuiz: And I forgot which pool, oh my gosh, I’m throwing a blank. Washing, cleaning, but you can go to those, and can you scrub through all those phone calls?
141 00:22:02.280 ⇒ 00:22:02.670 Pranav: Or just…
142 00:22:02.670 ⇒ 00:22:08.709 YvetteRuiz: today’s fault? I don’t know. I mean, what… I’m just trying to find something where I don’t have to put a lot of work in investing, too.
143 00:22:08.710 ⇒ 00:22:09.070 Pranav: Yes.
144 00:22:09.070 ⇒ 00:22:09.530 YvetteRuiz: I could just.
145 00:22:09.530 ⇒ 00:22:10.180 Pranav: Totally makes sense.
146 00:22:10.180 ⇒ 00:22:11.430 YvetteRuiz: Yeah.
147 00:22:11.430 ⇒ 00:22:19.329 Pranav: I think this worked too, like, once we get it done for, you know, within home improvement, just for pool cleaning, we’ll see how we can…
148 00:22:19.700 ⇒ 00:22:35.220 Pranav: expand that to all these other departments. So, I think that’s a way to think about it. Let’s start with home improve… or you let me know if home improvement’s the one to start with, what specific sub-service within that department, like, we should focus on. And then, yeah, let’s,
149 00:22:35.910 ⇒ 00:22:45.849 Pranav: let’s… let’s just start with those. We’ll be the ones to assess, okay, what was the reason for… or… was it a cancellation, was it not a cancellation? And then within that, we can…
150 00:22:46.470 ⇒ 00:22:48.589 Pranav: We’ll work on a system of…
151 00:22:48.870 ⇒ 00:22:52.759 Pranav: First, just doing the historical, right? It’s not gonna be, like, a week…
152 00:22:53.420 ⇒ 00:23:02.970 YvetteRuiz: So if you… well, let me ask this, I’m sorry, because it would be interesting, just based off… and I was… I just… I’m trying to start with what’s simple, right? And the first thing that comes to me is just…
153 00:23:03.310 ⇒ 00:23:10.800 YvetteRuiz: home improvement with one trade, right, versus a pest that has, like, thousands of calls. But if you do start, can you…
154 00:23:11.120 ⇒ 00:23:18.239 YvetteRuiz: if you go through that one department, that one trade, I’m sorry, and you pull all those phone calls.
155 00:23:18.320 ⇒ 00:23:37.450 YvetteRuiz: Can you tag all those phone calls? You know, then can you go in there and say, oh, all these are tagged, cancel somewhere, somehow, these are all billing? I don’t know, is that something that you could do? Because it would be interesting analysis, just data, to go in there and see, okay, these are all the type of phone calls that came in for that specific trade, that.
156 00:23:37.980 ⇒ 00:23:42.780 Pranav: So, in 8x8 right now, there’s already certain tags there, right?
157 00:23:43.490 ⇒ 00:24:03.440 Pranav: So, yeah, for us to just create another tag, we could do that. I’ll see if we have to use, based on, like, a predefined tags that 8x8 has already created, or if we’re allowed to create our own tags, because then we can say, like, yeah, AI analysis says canceled, versus just, you know, billing said canceled.
158 00:24:03.500 ⇒ 00:24:11.629 Pranav: So, yeah, we can… I think we can do that for you as well. That wouldn’t not… that wouldn’t be difficult for us,
159 00:24:12.120 ⇒ 00:24:33.379 Pranav: So, okay, let me bring this back to the team, and then tell them a little bit of, like, the change in direction that we’re doing from department-based to canceled. I do think this is, like, a better… better approach, because it’s a… it’s a lot less to focus on, and we’ll be able to drive change more directly, instead of, you know, over time and, you know, broad strokes.
160 00:24:33.930 ⇒ 00:24:37.680 YvetteRuiz: Yeah, no, for sure. I, I, I really,
161 00:24:38.540 ⇒ 00:24:47.469 YvetteRuiz: like to get moving in this direction, or change gears, because it is something that Evoca…
162 00:24:47.810 ⇒ 00:25:02.169 YvetteRuiz: they do something similar. Again, I haven’t tapped into that service or anything. This is, again, going back to the conversation, is how do we kind of just connect everything that we have today? But Evoca has,
163 00:25:03.020 ⇒ 00:25:05.110 YvetteRuiz: As a service, it’s called Coach.
164 00:25:05.260 ⇒ 00:25:21.899 YvetteRuiz: And what that does… but that’s… that’s based off their AI, though. That’s the thing, is that the calls come in through their system, they can pull all the transcripts on it, and then they can go in there and they can put together a coaching thing saying, hey, here, you missed all these opportunities right here.
165 00:25:22.320 ⇒ 00:25:26.810 Pranav: Yeah, okay. I mean, that makes sense to me.
166 00:25:27.550 ⇒ 00:25:40.730 Pranav: Okay, cool. Yeah, let’s, we’ll talk again on Friday, right? We have our… already… we have our call for end of week, and then, you know, since we’re kind of closing up here, I think it’s a good… good point to kind of wrap up. Okay.
167 00:25:40.730 ⇒ 00:25:50.660 Pranav: But there is, like, also the discussion about, like, integrating all these tools together. You talk about how, you know, 8x8 has certain information, and you’re kind of going to the data team to kind of
168 00:25:50.820 ⇒ 00:25:58.150 Pranav: analyze post-everything happening, and, like, post-fire what is going on. So I think, you know, maybe just…
169 00:25:58.450 ⇒ 00:26:16.140 Pranav: having a system in place where you can see all the… all of this information in one platform would be super interesting as well. That’s kind of, like, the… the idea that came to mind when you were talking about, kind of, some of the problems that you were having last week on our call with, like, Utam. So, yeah, let’s discuss more of that on Friday.
170 00:26:16.540 ⇒ 00:26:36.430 YvetteRuiz: Okay, that sounds like a plan. I know I have a lot of things right now, and that’s why I’m really trying to dial myself back, saying, okay, look, Yvette, you’ve got to go in there and just really focus on the one thing, or the one, or couple of things, because if not, I’m going to drive myself absolutely nuts, and that’s… that’s just because there’s a lot of things coming.
171 00:26:36.430 ⇒ 00:26:54.890 Pranav: I think it’s bad, honestly. I think because you’re… the way you’re phrasing them, too, it’s like, it’s… I see the urgency for, like, or I see why it’s urgent. It’s just about, okay, look, working on the right thing right now, and, you know, making sure it’s, like, we’d love to work on, like, three things at the same time, too, right? So…
172 00:26:55.960 ⇒ 00:27:02.699 Pranav: We can talk about that as well, going forward. Okay. But okay, this, I mean, this is super helpful, Yvette, thank you.
173 00:27:02.940 ⇒ 00:27:11.089 YvetteRuiz: Okay, yeah. I’m also… I sent out a survey today, to all my CSRs, on Andy.
174 00:27:11.370 ⇒ 00:27:19.610 YvetteRuiz: So, I want to invite that to you, because I want to know… From them, themselves, on…
175 00:27:19.680 ⇒ 00:27:36.499 YvetteRuiz: what is working? Just so you know, it’s the questions, I think I asked, like, 10 questions, I know it’s a lot, but still. How often do you use Andy? You know, what tasks, or areas do you mainly use ANDI for? Has Andy made your job easier, harder?
176 00:27:36.500 ⇒ 00:27:43.870 YvetteRuiz: resulted in no change. If Andy has changed your workflow, easy or harder, please explain.
177 00:27:44.330 ⇒ 00:27:57.479 YvetteRuiz: And then I have, on average, how much time does Andy save you? How helpful do you find Andy overall? What do you like most about Andy? What frustrates you or slows you down when using Andy?
178 00:27:58.610 ⇒ 00:28:13.309 YvetteRuiz: Are there specific tasks you wish Andy could help you, but currently doesn’t? And then the last one is, do you have any suggestions on how we can improve Andy? So, I already started getting a lot of responses.
179 00:28:14.060 ⇒ 00:28:14.820 Pranav: Perfect.
180 00:28:15.640 ⇒ 00:28:17.779 Pranav: Cool. Well, excited to see those.
181 00:28:17.780 ⇒ 00:28:19.140 YvetteRuiz: Yeah.
182 00:28:20.610 ⇒ 00:28:21.520 YvetteRuiz: Okay. Alright.
183 00:28:21.690 ⇒ 00:28:22.300 Pranav: Yeah.
184 00:28:22.530 ⇒ 00:28:24.780 YvetteRuiz: Alright, well then we’ll connect on Friday, then?
185 00:28:25.000 ⇒ 00:28:27.360 Pranav: Perfect. Yeah, yeah, yeah. Talk to you later.
186 00:28:27.360 ⇒ 00:28:29.340 YvetteRuiz: Okay, thanks, Pranav, have a good one.
187 00:28:29.520 ⇒ 00:28:31.169 Pranav: You too. See you soon. Okay, bye.