Meeting Title: AI Service Morning Huddle Date: 2026-04-30 Meeting participants: Mustafa Raja, Casie Aviles, Samuel Roberts, Pranav Narahari
WEBVTT
1 00:00:32.900 ⇒ 00:00:34.020 Samuel Roberts: Hello. Hi.
2 00:00:34.950 ⇒ 00:00:36.100 Mustafa Raja: Hey, how are you?
3 00:00:36.730 ⇒ 00:00:37.970 Samuel Roberts: Good, good.
4 00:00:39.120 ⇒ 00:00:39.520 Mustafa Raja: Yeah.
5 00:00:39.520 ⇒ 00:00:40.110 Samuel Roberts: you guys.
6 00:00:40.110 ⇒ 00:00:40.960 Mustafa Raja: community.
7 00:00:42.860 ⇒ 00:00:43.550 Samuel Roberts: Sorry?
8 00:00:43.750 ⇒ 00:00:45.900 Mustafa Raja: I just increased the memory.
9 00:00:46.720 ⇒ 00:00:52.880 Samuel Roberts: Okay, yeah, I was trying to get the AI to look at ways to reduce what we’re building, but that’s probably the easiest way.
10 00:00:53.550 ⇒ 00:00:54.700 Mustafa Raja: Yeah…
11 00:00:58.960 ⇒ 00:00:59.670 Pranav Narahari: Hey, guys.
12 00:01:00.490 ⇒ 00:01:01.130 Mustafa Raja: Hey.
13 00:01:02.200 ⇒ 00:01:02.580 Samuel Roberts: Howdy.
14 00:01:02.580 ⇒ 00:01:04.450 Pranav Narahari: Casey, are you in today? I didn’t know that.
15 00:01:05.720 ⇒ 00:01:10.460 Casie Aviles: Oh, hey, yeah. May 1st is our holiday.
16 00:01:11.830 ⇒ 00:01:13.270 Pranav Narahari: Oh, for tomorrow.
17 00:01:13.270 ⇒ 00:01:14.500 Samuel Roberts: Tomorrow, yeah.
18 00:01:14.950 ⇒ 00:01:20.770 Samuel Roberts: Yeah, I’ll be on the road tomorrow as well, so I’ll be… Out of office.
19 00:01:21.070 ⇒ 00:01:22.009 Samuel Roberts: But reachable as…
20 00:01:22.010 ⇒ 00:01:24.370 Pranav Narahari: Okay, you’re out of office tomorrow, too. Okay, that’s good to know.
21 00:01:26.160 ⇒ 00:01:27.820 Pranav Narahari: Alright,
22 00:01:29.050 ⇒ 00:01:35.699 Pranav Narahari: So, I didn’t have anything… I think most of the stuff on ABC’s side that was on your plate before, Casey is done.
23 00:01:35.960 ⇒ 00:01:39.180 Pranav Narahari: So… we can work on some stuff.
24 00:01:39.310 ⇒ 00:01:45.439 Pranav Narahari: that… there is quite a bit on ABC’s side now, since we got some more direction. So…
25 00:01:45.640 ⇒ 00:01:46.130 Samuel Roberts: Transcripts?
26 00:01:46.130 ⇒ 00:01:47.590 Pranav Narahari: I signed a few tickets.
27 00:01:47.730 ⇒ 00:01:48.720 Pranav Narahari: Sorry, what was that?
28 00:01:49.360 ⇒ 00:01:50.639 Samuel Roberts: Transcript stuff, or…
29 00:01:50.980 ⇒ 00:01:52.269 Pranav Narahari: Yeah, transcript stuff.
30 00:01:52.630 ⇒ 00:01:53.740 Samuel Roberts: Cool, cool.
31 00:01:54.640 ⇒ 00:01:55.180 Pranav Narahari: Yep.
32 00:01:56.110 ⇒ 00:02:03.849 Pranav Narahari: Yeah, so I signed a few tickets, so let’s maybe just start with Eden, though. So for Eden… I think the…
33 00:02:04.950 ⇒ 00:02:24.859 Pranav Narahari: you know, didn’t get any response in external chat. I think we’re just gonna have to, like, move forward with the direction that we have, and I do think the embeddings pipeline makes the most sense. It does seem, too, from, like, that demo, that we see more tool calls, that’s gonna be our best assessment for, you know, increased con… increased detail, right?
34 00:02:24.990 ⇒ 00:02:26.140 Pranav Narahari: Yeah.
35 00:02:26.490 ⇒ 00:02:34.260 Pranav Narahari: So, yeah, I feel like that’s… it’s a good path that we’re taking, and I think we should just start automating that solution so that…
36 00:02:34.370 ⇒ 00:02:44.719 Pranav Narahari: We’re embed… we’re creating the embeddings on a daily basis, and then… also, I set up another ticket to, like, also backfill for the last 2 weeks for everybody.
37 00:02:44.890 ⇒ 00:02:46.580 Pranav Narahari: Cool.
38 00:02:46.920 ⇒ 00:02:51.049 Pranav Narahari: So, yeah, Mustafa, I think those are on your plate, I think that should be…
39 00:02:51.180 ⇒ 00:02:56.290 Pranav Narahari: you know, just about the same thing that you did, like, a couple days ago.
40 00:02:56.610 ⇒ 00:03:02.440 Pranav Narahari: Just for the rest of the people, and then now just building the automation to run that daily.
41 00:03:02.890 ⇒ 00:03:06.039 Mustafa Raja: Yeah, so we need a proper pipeline now, right?
42 00:03:07.320 ⇒ 00:03:08.120 Pranav Narahari: Yeah.
43 00:03:08.550 ⇒ 00:03:09.540 Mustafa Raja: Okay, yeah.
44 00:03:10.180 ⇒ 00:03:11.270 Mustafa Raja: That makes sense.
45 00:03:11.840 ⇒ 00:03:12.700 Pranav Narahari: Okay, cool.
46 00:03:13.860 ⇒ 00:03:21.120 Pranav Narahari: Alright, and then I also, for ABC’s side, the goal now is just to focus on cancellations,
47 00:03:21.440 ⇒ 00:03:28.350 Pranav Narahari: Okay. So, I think I… did I talk to you guys about, like, just the scale of, like, the amount of calls that they’re getting per day?
48 00:03:29.800 ⇒ 00:03:33.950 Samuel Roberts: I don’t know if you have, but I have a sense of it after seeing, like, what was getting pulled in, but…
49 00:03:33.950 ⇒ 00:03:35.320 Pranav Narahari: Right, yeah, so…
50 00:03:35.820 ⇒ 00:03:43.770 Pranav Narahari: Yeah, so let’s kind of give some context, so right now is technically their busy season, because, the change in weather, you know.
51 00:03:43.770 ⇒ 00:03:44.300 Samuel Roberts: Oh, sure.
52 00:03:44.300 ⇒ 00:03:49.329 Pranav Narahari: A lot of people, like, doing more, maintenance work around their house.
53 00:03:49.340 ⇒ 00:03:50.530 Samuel Roberts: So…
54 00:03:50.840 ⇒ 00:04:03.629 Pranav Narahari: they’re basically seeing 3,200 calls per day. So, that’s how many transcripts that we’d be looking at per day, if we’re to do, like, just department-based insights, and that was supposed to be on a weekly basis, so…
55 00:04:03.740 ⇒ 00:04:05.309 Pranav Narahari: You know, multiply that by 5.
56 00:04:06.000 ⇒ 00:04:06.810 Samuel Roberts: Yeah, yeah.
57 00:04:07.320 ⇒ 00:04:09.780 Pranav Narahari: So, the idea here, too, is that
58 00:04:10.680 ⇒ 00:04:19.140 Pranav Narahari: I honestly feel less confident about giving them a solution that is going to really extract all of the insights from these transcripts.
59 00:04:19.140 ⇒ 00:04:34.690 Pranav Narahari: on an entire department basis, just off the bat. I think what we’re doing now makes a lot more sense, just pulling from a subset of these transcripts. And so what we’re gonna do is we’re gonna focus on home improvement, and then within home improvement, we’re gonna focus on
60 00:04:34.690 ⇒ 00:04:36.969 Pranav Narahari: Cleaning and washing.
61 00:04:38.020 ⇒ 00:04:57.389 Pranav Narahari: Okay. And so, that will be, like, a much more manageable number of transcripts per day, which we can have more, like, of a human-in-the-loop, like, behavior to know, like, how are we classifying certain things. Because one thing as well is we’re going to have to be the ones to classify transcripts as
62 00:04:57.410 ⇒ 00:04:59.910 Pranav Narahari: Canceled or not canceled?
63 00:05:00.050 ⇒ 00:05:08.519 Pranav Narahari: And so… Within that automation as well, what we want to do is we want to…
64 00:05:09.220 ⇒ 00:05:27.549 Pranav Narahari: if they fall into the category of canceled, what type of cancellation? And what was the re… well, more accurately, like, what was the reason for cancellation? So, was it because of, you know, they’re moving? Was it because, you know, they just needed the service temporarily? Was it because of price? Was it because they found a competitor? Like…
65 00:05:27.740 ⇒ 00:05:35.350 Pranav Narahari: Okay. All these different things, and they will be able to define the buckets for us once we get it to that point where it makes sense for them to define the buckets.
66 00:05:35.350 ⇒ 00:05:37.960 Samuel Roberts: Okay, cool, that was gonna be my next question. Cool, cool.
67 00:05:37.960 ⇒ 00:05:38.570 Pranav Narahari: Yeah.
68 00:05:38.860 ⇒ 00:05:41.749 Pranav Narahari: So, yeah, starting… like, I don’t think we need to…
69 00:05:41.880 ⇒ 00:05:43.859 Pranav Narahari: If there’s anything that requires, like.
70 00:05:44.210 ⇒ 00:05:51.060 Pranav Narahari: Industry knowledge, like, their day-to-day, like, subject matter expertise.
71 00:05:51.190 ⇒ 00:06:00.410 Pranav Narahari: we can fill in the gaps for right now, but we know that’s an area where we can go to them to tune things, and that’s kind of, like, what I try to do in our weekly meetings. Honestly, that’s kind of…
72 00:06:00.470 ⇒ 00:06:14.789 Pranav Narahari: as CSO, like, what you kind of do, just, like, on a week-to-week basis. Try to figure out where they can help us tune the solution. So, yeah, on Friday, I’ll let them know, like, where… certain areas where they can help us tune things.
73 00:06:15.440 ⇒ 00:06:23.310 Pranav Narahari: But yeah, for today, I created… Two tickets… Let’s see…
74 00:06:24.380 ⇒ 00:06:25.790 Samuel Roberts: Yeah, I saw one of them.
75 00:06:26.240 ⇒ 00:06:28.330 Pranav Narahari: I think it might just be one.
76 00:06:28.330 ⇒ 00:06:28.930 Samuel Roberts: Okay.
77 00:06:30.230 ⇒ 00:06:31.730 Pranav Narahari: Yeah, 2749.
78 00:06:32.240 ⇒ 00:06:33.800 Samuel Roberts: Yep, that’s the one I was looking at, cool.
79 00:06:34.050 ⇒ 00:06:39.059 Pranav Narahari: Okay, perfect. Yeah, so… Let me know if everything makes sense there,
80 00:06:39.720 ⇒ 00:06:42.660 Pranav Narahari: If you want to give it a quick read right now, and then just let me know.
81 00:06:43.370 ⇒ 00:06:44.600 Pranav Narahari: Further define this.
82 00:06:46.710 ⇒ 00:06:49.659 Samuel Roberts: Recent 14 calories of calls that we map.
83 00:06:50.300 ⇒ 00:06:53.649 Samuel Roberts: Within whom… okay.
84 00:06:55.660 ⇒ 00:06:57.010 Samuel Roberts: Yeah…
85 00:07:00.510 ⇒ 00:07:01.070 Casie Aviles: eat.
86 00:07:03.990 ⇒ 00:07:06.360 Samuel Roberts: Okay, yeah, I mean, this is making sense, I think.
87 00:07:07.620 ⇒ 00:07:12.899 Samuel Roberts: I’ll probably start with a smaller window for, like, getting it going, just cause… Totally.
88 00:07:13.240 ⇒ 00:07:17.859 Samuel Roberts: Yeah. You know, it’s a lot, even for limited ones sometimes.
89 00:07:17.860 ⇒ 00:07:19.019 Pranav Narahari: Yeah, I can actually…
90 00:07:19.720 ⇒ 00:07:23.959 Samuel Roberts: easily filter, but I’m… which I’m pretty sure I can,
91 00:07:24.120 ⇒ 00:07:29.700 Samuel Roberts: it’s just the 8x8 documentation, like I said, in the past, has been a little rough, so it’s just kind of…
92 00:07:29.900 ⇒ 00:07:30.829 Samuel Roberts: Guess and check the plane.
93 00:07:31.600 ⇒ 00:07:39.040 Pranav Narahari: And so you might also notice there that things have been tagged in 8x8 as canceled.
94 00:07:39.480 ⇒ 00:07:44.370 Pranav Narahari: However, our goal is to…
95 00:07:44.810 ⇒ 00:07:52.039 Pranav Narahari: and they may say canceled for a certain reason, right? So, our goal is to use the actual
96 00:07:53.200 ⇒ 00:08:04.560 Pranav Narahari: transcript to give, like, an AI analysis reason for cancellation. So, yeah, let me know, like, what 8x8 looks like currently, like, are you seeing… if things are tagged as cancellation.
97 00:08:04.750 ⇒ 00:08:08.569 Pranav Narahari: That’s actually pretty good for us.
98 00:08:08.570 ⇒ 00:08:10.080 Samuel Roberts: Yeah. Oh, excuse me.
99 00:08:10.080 ⇒ 00:08:18.400 Pranav Narahari: Now, but the reason itself is what Yvette was like, okay, I don’t feel super confident that the reasons are super accurate.
100 00:08:18.400 ⇒ 00:08:18.960 Samuel Roberts: Okay.
101 00:08:19.750 ⇒ 00:08:26.539 Pranav Narahari: So that’s what they want us to kind of focus on, like, not updating those tags, but we’ll just create our own tags saying, like.
102 00:08:26.540 ⇒ 00:08:27.420 Samuel Roberts: Yeah.
103 00:08:27.870 ⇒ 00:08:34.049 Pranav Narahari: likely… Likely tagged, or likely, canceled for…
104 00:08:34.220 ⇒ 00:08:39.000 Pranav Narahari: this reason. And then, I think I defined maybe a few buckets in that ticket.
105 00:08:39.130 ⇒ 00:08:44.289 Pranav Narahari: If not, I can, I can give you some more insight on that.
106 00:08:49.560 ⇒ 00:08:53.250 Samuel Roberts: I see cancellation and non-cancellation, I don’t see… I don’t know.
107 00:08:53.250 ⇒ 00:08:54.010 Pranav Narahari: Okay.
108 00:08:55.140 ⇒ 00:08:58.820 Pranav Narahari: Also, what might just be helpful, too, is…
109 00:08:59.430 ⇒ 00:09:03.980 Pranav Narahari: like, my transcript from yesterday with Yvette, so…
110 00:09:05.510 ⇒ 00:09:05.840 Samuel Roberts: Yeah.
111 00:09:05.840 ⇒ 00:09:09.039 Pranav Narahari: Yeah, I will give you these buckets as well for right now.
112 00:09:09.040 ⇒ 00:09:14.379 Samuel Roberts: Yeah, if you could throw the buckets in and just link the meeting, the ticket as well.
113 00:09:15.730 ⇒ 00:09:16.310 Pranav Narahari: Yeah.
114 00:09:16.770 ⇒ 00:09:17.330 Pranav Narahari: Definitely.
115 00:09:17.330 ⇒ 00:09:17.930 Samuel Roberts: Cool.
116 00:09:18.070 ⇒ 00:09:22.640 Samuel Roberts: And then, yeah, I’ll dig in and see, because if we can find those tags, that would be… that’s a really good, like…
117 00:09:23.490 ⇒ 00:09:29.500 Samuel Roberts: somewhat golden data set to, like, identify, okay, this kind of language was cancellation-related initially.
118 00:09:30.200 ⇒ 00:09:36.559 Samuel Roberts: Which I don’t think will be crazy, but having the tags will definitely help get started, so I’ll see what I can pull.
119 00:09:37.370 ⇒ 00:09:41.410 Pranav Narahari: Yeah, and… Yeah, they, so…
120 00:09:41.810 ⇒ 00:09:44.859 Pranav Narahari: I think part of this, too, might be, like…
121 00:09:45.060 ⇒ 00:09:50.289 Pranav Narahari: you know, we wanna… yeah, I think what you’re saying is, like, down the right path.
122 00:09:51.020 ⇒ 00:09:56.699 Pranav Narahari: Let’s use, kind of, yeah, previous transcripts that… you can probably just get, like, a…
123 00:09:56.850 ⇒ 00:10:08.419 Pranav Narahari: set of, like, 50 or 100 or whatever, like, run it through some, like, AI analysis to, like, assess, like, what are the commonalities between all these, and then just use those findings in a system prompt, or…
124 00:10:08.610 ⇒ 00:10:11.129 Pranav Narahari: Some other way to, like, assess…
125 00:10:11.400 ⇒ 00:10:15.869 Pranav Narahari: All future cancellation, or all future transcripts of their cancellation or not.
126 00:10:15.980 ⇒ 00:10:18.910 Pranav Narahari: So… Yep. Yeah, okay. I think we’re on the line.
127 00:10:18.910 ⇒ 00:10:21.670 Samuel Roberts: hygien probably is… yeah, I think… yeah, we’re thinking the same thing.
128 00:10:22.400 ⇒ 00:10:23.130 Pranav Narahari: Awesome.
129 00:10:26.070 ⇒ 00:10:36.599 Samuel Roberts: And even if we don’t have those tags, like, I don’t think it’s crazy to pass a bunch of stuff through and try to identify, but the tags will definitely simplify that first part. So, I’ll see what I can do.
130 00:10:36.600 ⇒ 00:10:37.110 Pranav Narahari: Absolutely.
131 00:10:37.590 ⇒ 00:10:38.740 Pranav Narahari: Totally, totally.
132 00:10:40.950 ⇒ 00:10:41.610 Samuel Roberts: Okay.
133 00:10:42.440 ⇒ 00:10:56.950 Pranav Narahari: Yeah, and then, so, at that point, too, kind of, like, putting things into certain buckets, you know, the idea here, too, is to eventually build this out in a way where we can cover all the departments, right? Yeah.
134 00:10:58.320 ⇒ 00:11:05.920 Pranav Narahari: And so Yeah, let me… Casey, I will work with you, right,
135 00:11:06.730 ⇒ 00:11:18.809 Pranav Narahari: maybe right after this, or actually, we have a little bit of time in this call, and we can probably just figure it out right now, because I want to just have something on your plate as well right now. Unless, let me first ask, do you have anything…
136 00:11:19.290 ⇒ 00:11:23.590 Pranav Narahari: Currently on… on your side that, is still pending?
137 00:11:24.380 ⇒ 00:11:29.620 Casie Aviles: I’m just wrapping up on one ticket, the one with phone numbers, since…
138 00:11:29.910 ⇒ 00:11:39.970 Casie Aviles: I’ve been resolving, like, those failed insertions, but yeah, I already wrote, like, a SQL query for that, so…
139 00:11:40.310 ⇒ 00:11:41.939 Casie Aviles: I’m just gonna wrap that up.
140 00:11:42.280 ⇒ 00:11:45.519 Casie Aviles: Should be able to finish that within the next hour.
141 00:11:46.230 ⇒ 00:11:51.710 Casie Aviles: And… I also just created a ticket from…
142 00:11:52.050 ⇒ 00:11:54.829 Casie Aviles: you know, what Janice was mentioning yesterday.
143 00:11:55.890 ⇒ 00:12:00.200 Casie Aviles: Regarding… The service managers, so…
144 00:12:00.660 ⇒ 00:12:05.970 Casie Aviles: That’s all I have right now, but we can reprioritize if there’s… Something more…
145 00:12:06.610 ⇒ 00:12:09.029 Casie Aviles: High priority to work on.
146 00:12:11.270 ⇒ 00:12:13.080 Pranav Narahari: Okay, cool. No, I think,
147 00:12:13.230 ⇒ 00:12:20.959 Pranav Narahari: You can… you can work on those, and then I think what actually would be better is if you spend some time on Eden today.
148 00:12:21.150 ⇒ 00:12:21.820 Casie Aviles: Okay.
149 00:12:22.240 ⇒ 00:12:23.469 Pranav Narahari: I think,
150 00:12:24.040 ⇒ 00:12:31.640 Pranav Narahari: the… the theme discovery now would be interesting, and I think what that looks like is basically just running a bunch of…
151 00:12:32.260 ⇒ 00:12:35.399 Pranav Narahari: Streamline queries through our current agents.
152 00:12:35.620 ⇒ 00:12:38.740 Pranav Narahari: And so…
153 00:12:40.200 ⇒ 00:12:53.919 Pranav Narahari: let me know when you get to that, and I’m happy to, like, hop in a call with you to kind of give more direction as well, but I think kind of, like, first pass, you can just ask the agent certain questions that would result in
154 00:12:54.190 ⇒ 00:12:59.950 Pranav Narahari: just theme discovery, you know, just like, okay, what are certain things that you’re noticing, like, across the company, right?
155 00:13:02.190 ⇒ 00:13:12.940 Pranav Narahari: And we can talk about how we can, like, really create a, like, a robust system for that, so that it does capture everything, and it’s exactly, kind of, in a…
156 00:13:14.770 ⇒ 00:13:18.010 Pranav Narahari: In a… well, it’s getting the insights that exactly…
157 00:13:18.260 ⇒ 00:13:27.689 Pranav Narahari: Danny is looking for. So, once you get to that, just let me know. We can define that further, too, if there’s any questions. And I know there’s… there’s some already tickets on that.
158 00:13:29.390 ⇒ 00:13:32.280 Casie Aviles: Yes, yes, I do have some tickets for that.
159 00:13:33.690 ⇒ 00:13:40.039 Samuel Roberts: One thing to think about there is that the current agent is… it’s probably a good starting place, but all the tools that we have could…
160 00:13:40.580 ⇒ 00:13:46.140 Samuel Roberts: Be worked into, like, a more… Deterministic workflow, perhaps?
161 00:13:46.520 ⇒ 00:13:47.340 Samuel Roberts: That, like…
162 00:13:47.970 ⇒ 00:13:55.930 Samuel Roberts: Automatically fetches, like, all the meetings from a given day, and looks at them, and then passes that into an agent that’s a little more focused or something.
163 00:13:56.740 ⇒ 00:13:57.370 Pranav Narahari: Yeah.
164 00:13:57.890 ⇒ 00:14:02.989 Samuel Roberts: So, there’s something to think about, I’m just gonna throw that out there, but I definitely start with the agent exits, because that’ll give you some good…
165 00:14:03.140 ⇒ 00:14:05.129 Samuel Roberts: Good, beginning.
166 00:14:05.130 ⇒ 00:14:05.780 Casie Aviles: Okay.
167 00:14:06.330 ⇒ 00:14:25.720 Pranav Narahari: Yeah, I totally agree. Like, I think the idea here is that we are already able to retrieve all the data. Now what we need to do is, like, exactly what Sam said, just make it more deterministic. Like, these reports on a weekly basis should be very consistent in structure, and consistent in, like, the way that it assesses the organization.
168 00:14:29.540 ⇒ 00:14:37.250 Casie Aviles: So… Alright, yeah, I’ll just leverage, you know, whatever data that the agent is already pulling from then.
169 00:14:40.280 ⇒ 00:14:40.810 Samuel Roberts: Yeah.
170 00:14:41.000 ⇒ 00:14:42.579 Samuel Roberts: Yeah, all the tools should be…
171 00:14:43.930 ⇒ 00:14:45.150 Samuel Roberts: You know, even if you would…
172 00:14:45.570 ⇒ 00:14:52.459 Samuel Roberts: Customize, like, okay, the first thing we’re gonna do is call the semantic search for a given whatever.
173 00:14:52.790 ⇒ 00:15:00.869 Samuel Roberts: And do that, like, 3 times for different things, and then feed that initially into a separate agent, rather than have the agent decide to do that kind of stuff.
174 00:15:01.020 ⇒ 00:15:03.949 Samuel Roberts: You know, it’s probably a good path to go down.
175 00:15:06.890 ⇒ 00:15:12.179 Samuel Roberts: Or, and then the next step in that is using the previous week
176 00:15:13.110 ⇒ 00:15:15.240 Samuel Roberts: Report that we will save.
177 00:15:15.750 ⇒ 00:15:22.130 Samuel Roberts: to influence the next one, so that it knows kind of what to look for, but that… I would not… I wouldn’t worry about that yet.
178 00:15:23.800 ⇒ 00:15:24.470 Casie Aviles: Okay.
179 00:15:26.070 ⇒ 00:15:28.150 Samuel Roberts: But just kind of high-level thinking about that.
180 00:15:32.470 ⇒ 00:15:33.180 Samuel Roberts: Cool.
181 00:15:37.320 ⇒ 00:15:38.070 Samuel Roberts: What else?
182 00:15:39.640 ⇒ 00:15:41.110 Pranav Narahari: I think we’re all set then, right?
183 00:15:42.350 ⇒ 00:15:42.940 Samuel Roberts: Yeah.
184 00:15:44.300 ⇒ 00:15:44.920 Pranav Narahari: Awesome.
185 00:15:45.640 ⇒ 00:15:46.810 Pranav Narahari: Okay, cool.
186 00:15:47.020 ⇒ 00:15:54.080 Pranav Narahari: Yeah, we’ll check in later today, and then, yeah, we’ll make sure to wrap certain things up, just because a couple of you guys are gonna be out tomorrow.
187 00:15:54.920 ⇒ 00:15:55.450 Samuel Roberts: Yeah.
188 00:15:55.590 ⇒ 00:16:01.099 Samuel Roberts: Yeah, I was gonna say, Casey, if you need any insight on Eden stuff, definitely, like, ping me or Mustafa.
189 00:16:01.770 ⇒ 00:16:02.590 Casie Aviles: Sure, sure.
190 00:16:03.160 ⇒ 00:16:08.560 Samuel Roberts: And then, yeah, by the end of the day, I’ll make sure that I’m at least in a good place to pass off.
191 00:16:09.170 ⇒ 00:16:11.980 Samuel Roberts: When I’m working on the transcript stuff.
192 00:16:13.680 ⇒ 00:16:16.900 Samuel Roberts: Or at least get a good, good update, so that can be run.
193 00:16:17.220 ⇒ 00:16:20.950 Samuel Roberts: Whoever needs to run with it tomorrow can do that. Cool.
194 00:16:23.220 ⇒ 00:16:24.080 Samuel Roberts: Alrighty.
195 00:16:25.250 ⇒ 00:16:25.810 Pranav Narahari: Cool.
196 00:16:26.060 ⇒ 00:16:27.820 Pranav Narahari: Alright. Thanks, y’all. Talk to you, guys.
197 00:16:28.940 ⇒ 00:16:29.530 Casie Aviles: Thank you.
198 00:16:29.530 ⇒ 00:16:30.149 Samuel Roberts: I eat.