Meeting Title: Brainforge x ABC Home and Commercial: Weekly Project Check Date: 2026-02-26 Meeting participants: read.ai meeting notes, Matt’s Notetaker (Otter.ai), Yvette’s Notetaker (Otter.ai), Uttam Kumaran, David’s Fathom Notetaker, DavidLopez, Amber Lin, Steven, Janiece, YvetteRuiz
WEBVTT
1 00:02:01.630 ⇒ 00:02:02.690 Uttam Kumaran: Hello.
2 00:02:07.530 ⇒ 00:02:08.919 DavidLopez: Hey, Udom, how are ya?
3 00:02:09.690 ⇒ 00:02:10.850 Uttam Kumaran: Hey, good, how are you?
4 00:02:11.080 ⇒ 00:02:12.980 DavidLopez: I’m well, thank you.
5 00:02:24.240 ⇒ 00:02:25.320 Amber Lin: Hello!
6 00:02:27.210 ⇒ 00:02:28.420 DavidLopez: Hey, Amber.
7 00:02:29.620 ⇒ 00:02:30.579 Steven: How’s it going?
8 00:02:31.210 ⇒ 00:02:32.490 Amber Lin: Pretty good!
9 00:02:32.720 ⇒ 00:02:37.939 Amber Lin: I’m waiting… we’re waiting for Janice and Yvette, right?
10 00:02:40.150 ⇒ 00:02:42.360 Steven: I think so. Are they gonna be there, David?
11 00:02:42.550 ⇒ 00:02:49.499 DavidLopez: I know they’re in Austin, so they may be running a little bit behind, but as I understand it, they should be here. I’ll reach out to them now, though.
12 00:02:55.500 ⇒ 00:03:00.830 Amber Lin: Awesome. We have some exciting stuff to share this week, so I want to make sure they can hear that, too.
13 00:03:45.460 ⇒ 00:03:47.549 Uttam Kumaran: How’s, how’s the week going overall?
14 00:03:49.600 ⇒ 00:03:56.409 Steven: It’s good, we’re, getting ready to hit busy season. March starts to increase in lawn mowing schedules, and…
15 00:03:56.950 ⇒ 00:03:59.840 Steven: increase of our busy season, so I think we’re ready to go.
16 00:04:00.210 ⇒ 00:04:04.780 Uttam Kumaran: Yeah, I’m just actually driving back from San Antonio. It’s hot there today.
17 00:04:04.780 ⇒ 00:04:06.920 Steven: Golly, yes, it’s really hot.
18 00:04:06.920 ⇒ 00:04:12.000 Uttam Kumaran: It’s… I just… I’m just looking at the temperature, it’s only… it’s… I’m in Austin now, it’s 80.
19 00:04:12.170 ⇒ 00:04:12.979 Uttam Kumaran: But it was, like.
20 00:04:12.980 ⇒ 00:04:13.870 Steven: Really well.
21 00:04:13.870 ⇒ 00:04:15.980 Uttam Kumaran: 92, 93 when I left.
22 00:04:16.470 ⇒ 00:04:23.630 Steven: Yeah, my truck showed 100, I think it was a little exaggerated, but yeah, it’s legit 90 plus degrees here.
23 00:04:25.140 ⇒ 00:04:29.350 Uttam Kumaran: Let’s see if it sticks, I don’t know, it was cold yesterday. Were you guys… did you have cold yesterday?
24 00:04:30.280 ⇒ 00:04:34.999 Steven: It was cooler, it was warm, but not… not… it was, like, low 80s, maybe.
25 00:04:35.310 ⇒ 00:04:36.270 Uttam Kumaran: Okay, okay.
26 00:04:36.860 ⇒ 00:04:43.339 Steven: Yeah, yeah, it’s, 90 plus today, supposed to cool up a little bit tomorrow, but yeah, it’s warm.
27 00:04:45.430 ⇒ 00:04:47.639 Janiece: I just had to go in from my browser.
28 00:04:50.520 ⇒ 00:04:54.469 Janiece: Hello! It’s giving me crazy problems. Hey guys, sorry.
29 00:04:58.110 ⇒ 00:04:59.650 Amber Lin: Janice, is your photo with you?
30 00:05:00.640 ⇒ 00:05:03.029 Janiece: I just heard her shut her door, so…
31 00:05:03.030 ⇒ 00:05:04.310 Amber Lin: Okay, so she won’t be coming.
32 00:05:04.310 ⇒ 00:05:12.200 Janiece: But if her deal was doing the same thing that mine was, it literally was just spinning and spinning and spinning.
33 00:05:12.520 ⇒ 00:05:13.539 Amber Lin: I see.
34 00:05:14.790 ⇒ 00:05:15.770 Amber Lin: Hi, Yvette!
35 00:05:16.100 ⇒ 00:05:18.229 YvetteRuiz: Hi there! Sorry I’m late.
36 00:05:19.050 ⇒ 00:05:19.980 Uttam Kumaran: Oh, good.
37 00:05:20.060 ⇒ 00:05:25.420 Amber Lin: Ready to get started. Let me share screen.
38 00:05:26.160 ⇒ 00:05:31.559 Amber Lin: some exciting stuff this week, so I was looking forward to this meeting to share it.
39 00:05:32.090 ⇒ 00:05:39.190 Amber Lin: So… Quick glance at usage, I think we’re pretty good. We’re a little bit lower than last week.
40 00:05:39.300 ⇒ 00:05:44.099 Amber Lin: So I’ll check in later and see if it improves tomorrow.
41 00:05:44.200 ⇒ 00:05:53.259 Amber Lin: But the main thing I want to talk about today is the transcripts and the analysis and possible reporting we can do about it.
42 00:05:53.260 ⇒ 00:06:06.790 Amber Lin: That’s the… that’s the main topic I want to talk about today, and there are some updates on zip codes, on central dock, on migration, that I’ll quickly touch upon, and we’ll either talk about those more tomorrow, or in an email.
43 00:06:07.220 ⇒ 00:06:08.480 Amber Lin: So…
44 00:06:08.960 ⇒ 00:06:27.639 Amber Lin: We were able to get… we got some sample transcripts to do analysis on, and I believe once we confirm with Tim on how much backfill we can do, then we can run it full scale on new transcripts, on old transcripts.
45 00:06:27.640 ⇒ 00:06:35.969 Amber Lin: to… to do our reporting, but I want to show you what we’ve got, and what is already possible to do.
46 00:06:35.980 ⇒ 00:06:37.640 Amber Lin: Based on that data.
47 00:06:37.920 ⇒ 00:06:44.680 Amber Lin: So, you know, when a transfer comes in, so there’s… let me pull up a sample…
48 00:06:44.980 ⇒ 00:06:53.309 Amber Lin: transcripts. So, for example, This would be a transcript. And then…
49 00:06:53.460 ⇒ 00:07:05.019 Amber Lin: We were able to piece it together so we have the full transcript, and then we also have another table on, who was the customer, who was the person taking the call.
50 00:07:05.020 ⇒ 00:07:17.150 Amber Lin: How long was the duration, what queue it is, so we not only have the transcript itself, we also have qualities of the transcript. So, based on that.
51 00:07:17.830 ⇒ 00:07:27.740 Amber Lin: the first thing I’m able to do is look at, the numbers. So not the text itself, but the numbers such as
52 00:07:27.870 ⇒ 00:07:44.630 Amber Lin: how many calls are there? How long was it? How long did the customer have to wait? And then other metrics that was available in that table, which we have quite a lot available.
53 00:07:45.090 ⇒ 00:07:49.140 Amber Lin: So… Immediately, I’m able to…
54 00:07:49.210 ⇒ 00:07:59.349 Amber Lin: I’m able to help visualize these metrics by different dimensions, right? For example, if we want to look at the number of calls.
55 00:07:59.350 ⇒ 00:08:13.770 Amber Lin: We want to see, are people hitting their targets? Are departments hitting… departments hitting their targets? We can look at that by agent, we can look at it by time of day, hour of day, day of week.
56 00:08:13.780 ⇒ 00:08:32.629 Amber Lin: look at it over the year on when it’s more busy, and we can also look at it by, by queues or by department. So that’s a very basic insight that we… I believe we’re already able to do. And once I run through all these analysis, I want to show you
57 00:08:32.630 ⇒ 00:08:36.690 Amber Lin: The real dashboard that we already started building.
58 00:08:37.460 ⇒ 00:08:38.169 YvetteRuiz: Great.
59 00:08:39.580 ⇒ 00:08:41.850 Amber Lin: So, this is a…
60 00:08:42.400 ⇒ 00:08:56.030 Amber Lin: Another example. So, we looked at how many calls there are, now we can look at how… how long does it take, right? Because it… it matters for our productivity, it matters for the customer’s experience.
61 00:08:56.030 ⇒ 00:08:56.540 YvetteRuiz: somehow.
62 00:08:56.540 ⇒ 00:09:12.199 Amber Lin: long calls take. So, we can look at it by agent, we can look at it, on the… how long it was in, on hold, how long it was on queue, the overall duration.
63 00:09:12.280 ⇒ 00:09:21.369 Amber Lin: Similarly, we can do that for the departments, or by queues, and by time of day, so all these dimensions are possible.
64 00:09:21.740 ⇒ 00:09:29.350 Amber Lin: So… And… let’s see… And we can also do some…
65 00:09:29.420 ⇒ 00:09:43.740 Amber Lin: some deeper analysis of not just the numbers they directly provide with us, but we can look at something like this. So when I did some analysis, I realized, okay, in the same day, so this is one day of calls.
66 00:09:43.810 ⇒ 00:10:02.920 Amber Lin: There’s multiple calls for a single customer. And I looked at it a little bit more, and then I realized it was because, okay, they come in, they go to reception, reception them, sometimes to a different reception, and then it gets transferred to
67 00:10:02.930 ⇒ 00:10:05.599 Amber Lin: The different departments under that.
68 00:10:06.020 ⇒ 00:10:20.909 Amber Lin: And I was wondering, okay, so we can look at individual calls, but what about the overall experience of that customer? Are we transferring them inefficiently? Are they spending time being…
69 00:10:20.920 ⇒ 00:10:28.639 Amber Lin: moved around in the different lines? Or are we ensuring that they have an overall good experience?
70 00:10:29.190 ⇒ 00:10:33.619 Amber Lin: So, this is a sample customer, so I think this is for…
71 00:10:33.780 ⇒ 00:10:37.030 Amber Lin: This is for Susan. So, Susan had…
72 00:10:37.430 ⇒ 00:10:52.399 Amber Lin: overall 6 calls that day. She was in reception, I think 3 reception lines, and then she went to lawn, she went to handyman, and she went to in-house construction. Maybe she has all 3 of those services.
73 00:10:52.970 ⇒ 00:11:01.649 Amber Lin: And so, she had 3 transfers to queue, 2 initial interactions, and I believe 1 actual conversation.
74 00:11:02.120 ⇒ 00:11:08.469 Amber Lin: So… Even just by looking at that, like, she… she was on call for
75 00:11:08.750 ⇒ 00:11:10.799 Amber Lin: More than an hour.
76 00:11:11.000 ⇒ 00:11:17.510 Amber Lin: To maybe just… Solved one problem, but she was transferred so much.
77 00:11:17.650 ⇒ 00:11:26.569 Amber Lin: That she had to be occupied for more than an hour. And not everybody has time to be occupied for more than an hour, they might just give up.
78 00:11:26.860 ⇒ 00:11:35.219 Amber Lin: So… Like, that’s another level of insight we can do, now that we have all the transfer data, so…
79 00:11:35.480 ⇒ 00:11:42.509 Amber Lin: We can… for example, that analysis, let’s look at this section. So, total spam by customer.
80 00:11:43.400 ⇒ 00:11:55.419 Amber Lin: I think the… ignore the top few parts, but for example, Kathleen had… was on the phone for the total span that single day for, like.
81 00:11:56.560 ⇒ 00:12:05.699 Amber Lin: 3? I don’t know how many hours, so she may be called in the morning, and then called later in the day, or say.
82 00:12:06.330 ⇒ 00:12:09.130 Amber Lin: Even with Becky, she was…
83 00:12:09.290 ⇒ 00:12:14.600 Amber Lin: Probably on the phone for about 40 minutes or so.
84 00:12:15.850 ⇒ 00:12:20.389 Amber Lin: And I think that’s also… Another dimension that…
85 00:12:20.570 ⇒ 00:12:34.039 Amber Lin: I want to illustrate that as something we can look at, because just looking at individual calls by agent doesn’t give us the view of the customer experience. So, that’s something that we can also do.
86 00:12:39.330 ⇒ 00:12:42.649 Amber Lin: Alright, so next I want to…
87 00:12:43.440 ⇒ 00:13:01.249 Amber Lin: So that’s the numeric… the numbers, the data that describes the calls. So what about the call itself? When we look at the text, the transcript of the calls, what can we do, and what can we use it for?
88 00:13:01.720 ⇒ 00:13:15.739 Amber Lin: So, from the text of the transcript, there’s a few things immediately that we can look at. So, what is the sentiment of this call? Is the customer angry? Are they happy? Or is it just neutral?
89 00:13:15.860 ⇒ 00:13:27.600 Amber Lin: What are the improvement suggestions, as we talked about? What is the purpose of this call? Is it to cancel? Is it to book a new service? Is it to adjust something?
90 00:13:28.130 ⇒ 00:13:33.850 Amber Lin: And then, I believe for our specific concerns, we wanted to look at cancellations.
91 00:13:33.950 ⇒ 00:13:39.759 Amber Lin: Did they… did the customer call to cancel? And if so, did we use safe tactics?
92 00:13:39.960 ⇒ 00:13:47.599 Amber Lin: Next, if the customer is calling to book, did it book successfully? What is our overall booking success rate?
93 00:13:47.760 ⇒ 00:13:52.409 Amber Lin: And lastly, is the call resolved, or did the customer have to call again?
94 00:13:52.530 ⇒ 00:14:00.500 Amber Lin: Or… for example, like Susan, like, was she transferred multiple times? Like, did she have…
95 00:14:00.840 ⇒ 00:14:03.810 Amber Lin: A lot of barriers in reaching her goal.
96 00:14:04.950 ⇒ 00:14:24.090 Amber Lin: So, and once we… if we have what they’re supposed to comply with, we can also look at compliance, we can look at their script adherence, how they escalate, so those are possible if we have, a standard to compare against. But…
97 00:14:25.050 ⇒ 00:14:34.310 Amber Lin: wanted to show you, for example, this is a… I believe… Stam.
98 00:14:34.650 ⇒ 00:14:39.079 Amber Lin: This is a sample of 30 transcripts, and among those.
99 00:14:39.630 ⇒ 00:14:59.290 Amber Lin: we have people calling for new bookings, calling for rescheduling, some about general inquiries, and then cancellations, billing, etc. So, I believe once we classify this, then we would be able to double-click into those categories and see
100 00:14:59.330 ⇒ 00:15:06.329 Amber Lin: How are we overall handling those calls? What are people asking, and can we provide better answers
101 00:15:06.430 ⇒ 00:15:08.419 Amber Lin: To people’s questions.
102 00:15:09.470 ⇒ 00:15:10.569 YvetteRuiz: Love that.
103 00:15:10.570 ⇒ 00:15:16.459 Amber Lin: Yeah, and this is, wanted to show you, this is 5 transcripts that I did
104 00:15:16.770 ⇒ 00:15:19.170 Amber Lin: More detailed analysis on.
105 00:15:19.470 ⇒ 00:15:20.690 Amber Lin: So…
106 00:15:23.690 ⇒ 00:15:32.789 Amber Lin: For example, this, this customer called, this person took the call on this particular date, and this is their transcript.
107 00:15:32.890 ⇒ 00:15:47.279 Amber Lin: From that, we’ll be able to say, okay, what type of call is this? This looks like a new booking. Was it resolved? Did they book the meet? Did they book? Did they book it? So, it seems like, yes, they did do that.
108 00:15:47.440 ⇒ 00:15:57.359 Amber Lin: And… And then we can also have improvement suggestions of, okay, how should you best sample
109 00:15:57.460 ⇒ 00:16:04.250 Amber Lin: sample that, should you… and in this case, it said, okay, let’s emphasize immediately.
110 00:16:04.350 ⇒ 00:16:10.469 Amber Lin: Let’s try and remove and avoid the fillers, and…
111 00:16:11.430 ⇒ 00:16:13.919 YvetteRuiz: This is a feedback suggestion, I’m so sorry, Amber.
112 00:16:13.920 ⇒ 00:16:15.439 Amber Lin: Yeah, this is the improvement.
113 00:16:15.440 ⇒ 00:16:17.469 YvetteRuiz: suggestions. Okay, got it.
114 00:16:17.470 ⇒ 00:16:24.710 Amber Lin: Yeah, and I would say, I want to point out this one. So, this one is a cancellation.
115 00:16:24.710 ⇒ 00:16:30.980 YvetteRuiz: Amber, I’m so sorry to interrupt. So, on the improvement suggestion, who’s making those suggestions? Is that…
116 00:16:30.980 ⇒ 00:16:39.359 Amber Lin: This is AI. The AI is making the suggestions. Okay. So, if we have guidelines, that will make the suggestions even better.
117 00:16:39.360 ⇒ 00:16:40.789 YvetteRuiz: Perfect, okay, that’s what I was saying.
118 00:16:40.790 ⇒ 00:16:41.330 Amber Lin: Yeah.
119 00:16:41.330 ⇒ 00:16:42.590 YvetteRuiz: I wanted to know.
120 00:16:42.590 ⇒ 00:16:47.780 Amber Lin: Of course. And then this one, for example, this is on cancellations.
121 00:16:47.960 ⇒ 00:16:55.019 Amber Lin: They’re canceling a… I don’t think they’re canceling a service, but they’re canceling a booking.
122 00:16:55.130 ⇒ 00:17:05.119 Amber Lin: This is a very, very short call. We can see that… no, I think this is transferring. Okay, but…
123 00:17:05.290 ⇒ 00:17:21.300 Amber Lin: In other cases, cancellations, we can read the text to see, did the agent use save tactics? Did they make sure that we went through the options with the customer and tried to save them before, letting them cancel? So…
124 00:17:21.550 ⇒ 00:17:33.420 Amber Lin: These are some possibilities that we can do. I want to pause here for questions before we go on to RIL, and we can show you the first steps that we were able to do.
125 00:17:34.320 ⇒ 00:17:42.980 Uttam Kumaran: Yeah, one question, I had, another opportunity here, Amber, is actually to maybe look through some of the calls that either
126 00:17:43.110 ⇒ 00:17:52.509 Uttam Kumaran: Like, had the longest duration, or maybe the sentiment was the lowest, and actually, like, use those transcripts to compare with what’s in the central doc.
127 00:17:52.640 ⇒ 00:18:01.729 Uttam Kumaran: you know, and basically see, like, hey, is there something we could have learned here, you know? Or is there a change we could have made? I think that’s also something
128 00:18:01.940 ⇒ 00:18:04.009 Uttam Kumaran: You know, really interesting, we can try.
129 00:18:05.260 ⇒ 00:18:07.529 YvetteRuiz: Yeah, that’s a really good suggestion, Utem.
130 00:18:09.620 ⇒ 00:18:28.190 YvetteRuiz: I really like that you can tell the amount of times that that caller called, because I know we’ve talked about that in the past, you know, that first call resolution, trying to go through 8 byte and pull that, but I mean, here, it kind of pretty much paints a good picture, of you. It’s easy to see and stuff, so that’s… that’s big.
131 00:18:28.190 ⇒ 00:18:33.560 YvetteRuiz: I really like the purpose piece, I mean, especially, Amber, if you’re saying, like, I can go in there and I can click
132 00:18:33.560 ⇒ 00:18:43.989 YvetteRuiz: you know, on them to kind of dissect the calls even more? Is that what I’m understanding? So, like, if I go to the new call bookings, I can click more. You’re saying we can go in there to get more detailed information?
133 00:18:43.990 ⇒ 00:18:46.159 Amber Lin: Once we set it up, yes.
134 00:18:46.160 ⇒ 00:18:48.110 YvetteRuiz: Yeah, okay.
135 00:18:48.770 ⇒ 00:19:02.380 YvetteRuiz: So it can get really granular. And then, again, I like the improvement side of it as well, especially if we can tie in our, grading scorecard, to that. I think that would be great.
136 00:19:03.580 ⇒ 00:19:11.019 Uttam Kumaran: Yeah, and one last piece also is the, linking to the, like, the Andy actual transcript, if there is one.
137 00:19:11.020 ⇒ 00:19:13.930 YvetteRuiz: The Andy chat log, right? So…
138 00:19:13.930 ⇒ 00:19:28.740 Uttam Kumaran: you know, one thing I’m super interested in is, like, what is the correlation? It’s really to prove, I think, what, you know, we’re gonna hope that’s true, is like, hey, on average, when folks use Andy, like, the calls are shorter, right? And, like, I think we’re…
139 00:19:28.740 ⇒ 00:19:40.540 Uttam Kumaran: I think we’re… we’re really close to that, finally. And then, ultimately, also showing that, like, hey, for the ones where people used Andy, and maybe the scorecard was bad, like, what happened, and what could we learn, you know?
140 00:19:41.090 ⇒ 00:19:52.779 YvetteRuiz: Absolutely, Utam. I know that was one of our earlier conversations, is tracking metric, with Andy, is the difference between using it, quicker answers, and all that. So, yes, agree 100%.
141 00:19:54.720 ⇒ 00:20:07.509 Amber Lin: Awesome. Alright, let me show you the, dashboards we created. This is just a very early, basic version, but for example, here is something that
142 00:20:07.790 ⇒ 00:20:18.839 Amber Lin: Here we’re doing, so let’s look at just agent, and then we can, for example, we can see, the calls by agent.
143 00:20:18.890 ⇒ 00:20:25.219 Amber Lin: And we can, of course, introduce what department they belong to, because we already have that data for Andy.
144 00:20:25.270 ⇒ 00:20:44.490 Amber Lin: We can also look at, for example, by hour of day. When was… when do we have the most calls? And later on, we can also look at, for the hour of day, how long do the calls take? Do people get more tired throughout a day? And then the calls tend to take longer?
145 00:20:44.490 ⇒ 00:20:47.809 Amber Lin: So I think those are interesting things.
146 00:20:48.310 ⇒ 00:20:49.520 Amber Lin: To look at.
147 00:20:50.400 ⇒ 00:20:51.150 Amber Lin: Yeah.
148 00:20:51.260 ⇒ 00:20:52.370 Amber Lin: Mmm…
149 00:20:52.390 ⇒ 00:20:54.990 YvetteRuiz: So, for example, this is by…
150 00:20:55.310 ⇒ 00:21:02.040 Amber Lin: The caller name, this is by who’s calling, and this is, you can see for this
151 00:21:02.620 ⇒ 00:21:05.420 Amber Lin: Let’s save, past…
152 00:21:06.370 ⇒ 00:21:18.669 Amber Lin: And then, so for example, how many calls was this person in? So we can say some of them were transferred around, there were 5 calls, some of them had, 4 calls, and…
153 00:21:19.420 ⇒ 00:21:23.909 Amber Lin: Let’s see… This is by the different queues.
154 00:21:24.770 ⇒ 00:21:28.530 Amber Lin: And… Let’s see…
155 00:21:28.800 ⇒ 00:21:39.730 Amber Lin: Yeah, and then there’s also transfer type. So, what was this call about? Was this a transfer, or was this an actual conversation that people were having?
156 00:21:45.580 ⇒ 00:21:46.270 Amber Lin: Yeah.
157 00:21:47.600 ⇒ 00:21:57.909 Amber Lin: Sounds good. That’s all I have on the transcript side. I believe the next steps for us will be to…
158 00:21:59.900 ⇒ 00:22:19.269 Amber Lin: I think Uten wanted to talk about this as a new scope, or how we will add on to this work, because with our current, current work with Andy, the migration, the zip codes, the triage tickets, our hours are pretty much occupied with that, but this is a very interesting project, and I do think it will have a lot of unlocks.
159 00:22:19.340 ⇒ 00:22:35.260 Amber Lin: For ABC and for the team, and we’ll love to think about, what’s the timeline for this look like? What are we aiming for? And Yvette, I also saw your email on the KPIs and reporting dashboards, so we’d love to talk a bit more about that.
160 00:22:36.590 ⇒ 00:22:51.870 Uttam Kumaran: Yeah, maybe this is something, Steven, we can chat about. It’s just, yeah, I feel like a lot of this work really fits squarely into some of the stuff we pitched as part of the analytics discovery. And so really, that’s just what I wanted to bring up, is like, yeah, I think our…
161 00:22:51.870 ⇒ 00:23:02.740 Uttam Kumaran: we’re still working on a lot of, you know, Andy Development-related work, but there is a lot of depth here that I think is gonna affect a lot, so I think Amber kind of put it nicely. I know we emailed back and forth, so…
162 00:23:02.840 ⇒ 00:23:03.910 Uttam Kumaran: Yeah.
163 00:23:04.920 ⇒ 00:23:15.259 Steven: Yeah, and like I think Matt said, I’ll be in Austin Monday, and then I know, you know, Yvette and I met yesterday, we met with Bo, kind of… we’ve got several projects, and as y’all know, integrating everything, what.
164 00:23:15.260 ⇒ 00:23:21.830 Uttam Kumaran: part does what, how’s it all come together, so we’ve got a couple bigger discussions we want to have over the next week or so that involves all this, so…
165 00:23:21.830 ⇒ 00:23:32.029 Steven: Hopefully, we’ll get some traction and direction. I said, next week, Matt and Bobby will both be back in town, and our marketing director started, so we should be able to kind of get some better direction over the next couple days, hopefully.
166 00:23:32.610 ⇒ 00:23:34.750 Uttam Kumaran: Okay, okay, great. Thank you.
167 00:23:36.240 ⇒ 00:23:44.949 YvetteRuiz: That stuff, that’s really, really good stuff, really interesting things. I really like the, you know, the transcript piece of it. I think that that has a lot, a lot of value.
168 00:23:46.110 ⇒ 00:23:47.250 YvetteRuiz: Oh, for sure. Amazing.
169 00:23:47.700 ⇒ 00:24:06.960 Amber Lin: Totally agree. Awesome. So, now it’s the remaining updates on the other work streams that we’ve been working on. So quickly, on the zip code side, we went through all the spreadsheets, so including all the technicians, the inspector sheet, the service areas.
170 00:24:08.260 ⇒ 00:24:26.889 Amber Lin: So, through all of those, to validate what assignments, if the assignments have been included in our database, we’re currently doing a final QA, plus a validation using the triage tickets. So, I believe by the end of this week or early next week.
171 00:24:26.910 ⇒ 00:24:35.839 Amber Lin: While Jim will have the final results of what’s still missing, or what triage tickets are still unresolved.
172 00:24:36.260 ⇒ 00:24:40.319 Amber Lin: But I’ll be back with more details there.
173 00:24:41.970 ⇒ 00:24:46.960 Amber Lin: Yeah, and… On the migration side.
174 00:24:47.040 ⇒ 00:24:55.440 Amber Lin: I checked with the team yesterday, I think we’re at the last steps. We should be able to have you guys test it by next week.
175 00:24:55.440 ⇒ 00:25:11.180 Amber Lin: We’ve moved everything over. I think the last thing we’re doing is migrating the AI models over. So making… once we make sure that is done, I think we’re working with Tim on that, people should be able to test
176 00:25:11.260 ⇒ 00:25:13.310 Amber Lin: the new Andy version.
177 00:25:14.010 ⇒ 00:25:15.210 YvetteRuiz: Yay!
178 00:25:15.210 ⇒ 00:25:33.990 Amber Lin: Yeah. Last piece, we’ll talk a little… we’ll talk more about this with the trainers tomorrow, but want to give you some context before we go into that meeting. This is the effort we’re doing on the different central docs to standardize them, to improve them.
179 00:25:33.990 ⇒ 00:25:38.390 Amber Lin: And to establish a…
180 00:25:38.920 ⇒ 00:25:52.920 Amber Lin: A more automated process of when we have new information, how does it get put into the docs, and how do we prevent it from becoming overly chaotic throughout time?
181 00:25:53.430 ⇒ 00:25:54.440 Amber Lin: And…
182 00:25:54.500 ⇒ 00:26:04.060 Amber Lin: I wanted to show you… last week, we said we’ll have something to share, this week. We did go through and did a test run.
183 00:26:04.090 ⇒ 00:26:17.640 Amber Lin: on the Pest Central dock, and Mustafa is currently doing a run on the mechanical dock, which hopefully we’ll have by tomorrow for the trainers to review. And so, we had a…
184 00:26:17.640 ⇒ 00:26:36.130 Amber Lin: structure that we wanted it to follow. And then we were able to grab everything from the original Pest Central doc, and we said, okay, this falls under here, that falls under here, here’s how you can word it, or organize it better, so that everything is
185 00:26:36.130 ⇒ 00:26:51.289 Amber Lin: following the same structure for different services. So that will make it really easy in the future if we have something that’s, oh, this is a pricing thing, this is a durations thing. We will know exactly where to put it in.
186 00:26:51.710 ⇒ 00:27:00.939 Amber Lin: So, let’s take a look at one of these… one of these services. So, it follows, let’s look at…
187 00:27:02.040 ⇒ 00:27:04.939 Amber Lin: Alright, let’s look at…
188 00:27:05.770 ⇒ 00:27:12.010 Amber Lin: First one, I think? First one. So, for example, if we look at general pest control.
189 00:27:12.090 ⇒ 00:27:30.399 Amber Lin: We have, first, what is covered, what is not? Because we know this is the third… second or third biggest categories asked of, do we do this? What about… what is this… what is this service? So we have all the covered, non-covered stuff that we gradually added throughout time.
190 00:27:30.830 ⇒ 00:27:36.500 Amber Lin: And we grabbed the times and durations to put them in one place.
191 00:27:36.910 ⇒ 00:27:39.750 Amber Lin: that relates to GPC, so we have…
192 00:27:40.230 ⇒ 00:27:46.800 Amber Lin: A table for that, so if anyone says these things have to change, they know exactly what they’re looking for.
193 00:27:47.160 ⇒ 00:27:50.750 Amber Lin: We have also… let’s see…
194 00:27:51.040 ⇒ 00:27:59.769 Amber Lin: Service… service codes, if there’s any of that, the other notes and features available.
195 00:28:00.300 ⇒ 00:28:08.529 Amber Lin: And then… We’ll have these workflows that applies to everything in one section.
196 00:28:08.770 ⇒ 00:28:13.380 Amber Lin: And lastly, we’ll have these informations that’s…
197 00:28:13.560 ⇒ 00:28:19.740 Amber Lin: shared throughout. Let me pull that up…
198 00:28:21.280 ⇒ 00:28:30.260 Amber Lin: So, for example, the billing… the billing stuff, the cancellation stuff that’s shared will also be put in one section, so…
199 00:28:30.400 ⇒ 00:28:48.060 Amber Lin: I would say the structure for PEST is so pretty much similar, because we did a good job on PEST. I want to see tomorrow how the mechanical doc goes, and want to discuss with trainers of, hey, do you think this is viable? Do you think it did a good job? How can it improve? Etc.
200 00:28:48.370 ⇒ 00:28:50.829 Amber Lin: So, that’s all I have for this week.
201 00:28:52.080 ⇒ 00:29:04.169 YvetteRuiz: Thank you so much, Amber. That was a lot, and a lot of good information, for sure. So, definitely looking forward to the meeting tomorrow with the trainers, on this. I think that’s going to be very easy to follow if we structure it that way, for sure.
202 00:29:04.170 ⇒ 00:29:05.199 Amber Lin: Yeah, awesome.
203 00:29:06.030 ⇒ 00:29:07.030 Amber Lin: Okay.
204 00:29:07.030 ⇒ 00:29:08.070 Janiece: I really like it.
205 00:29:08.820 ⇒ 00:29:09.930 Amber Lin: Exciting!
206 00:29:10.680 ⇒ 00:29:26.550 Amber Lin: Alright, I don’t think there are any particular action items on your side. I know we’ve… we’ve emailed Tim about the AI models, so I know we’ll follow up there. Other than that, if…
207 00:29:26.830 ⇒ 00:29:34.480 Amber Lin: I think… it’s just, the discussion on the discovery side, so Bhutam will follow up there.
208 00:29:36.600 ⇒ 00:29:38.040 YvetteRuiz: Sounds good!
209 00:29:38.040 ⇒ 00:29:38.660 Amber Lin: Alright.
210 00:29:38.960 ⇒ 00:29:40.140 YvetteRuiz: Thanks, everyone!
211 00:29:40.370 ⇒ 00:29:41.359 YvetteRuiz: Thanks, guys!
212 00:29:41.360 ⇒ 00:29:42.939 DavidLopez: Thank y’all. Thank you. Thank you.
213 00:29:42.940 ⇒ 00:29:43.650 YvetteRuiz: Bye.
214 00:29:44.060 ⇒ 00:29:44.510 Uttam Kumaran: bye.
215 00:29:44.510 ⇒ 00:29:45.589 Janiece: Thank you, bye.