Meeting Title: Annie ／ Amber | ABC onboarding Date: 2025-04-01 Meeting participants: Annie Yu, Amber Lin
WEBVTT
1 00:00:18.920 ⇒ 00:00:20.439 Amber Lin: Oh, hello!
2 00:00:20.440 ⇒ 00:00:22.459 Annie Yu: Hello! Hi! Amber
3 00:00:22.680 ⇒ 00:00:24.220 Amber Lin: Hi! How are you doing
4 00:00:24.480 ⇒ 00:00:26.409 Annie Yu: Not too bad. How are you?
5 00:00:27.482 ⇒ 00:00:29.090 Amber Lin: Back to back meetings
6 00:00:29.526 ⇒ 00:00:31.270 Annie Yu: Oh, I hate those
7 00:00:31.270 ⇒ 00:00:37.959 Amber Lin: Glad I get some time to switch off my brain. I didn’t even have time to log my time, so
8 00:00:40.227 ⇒ 00:00:45.239 Annie Yu: Do we still have to lock our time being a full time
9 00:00:45.616 ⇒ 00:00:53.139 Amber Lin: Yes, because if we don’t log our time we’ll we don’t know how much time you spent on certain things
10 00:00:53.140 ⇒ 00:00:53.880 Annie Yu: Okay.
11 00:00:54.000 ⇒ 00:01:08.500 Amber Lin: I still log it. I do a lot. So I log it to even like 5, 10 min. But you can if you if you want, because engineering is a lot different, because I have different clients. So you could maybe just log it per ticket.
12 00:01:08.640 ⇒ 00:01:13.249 Amber Lin: Say, today, this ticket took this amount of time approximately.
13 00:01:13.280 ⇒ 00:01:40.090 Amber Lin: because then we’ll want to track eventually. How long each things take you and that will influence one. How we build clients of oh, things are taking too long, we should probably build them more, which affects how much money we’re getting and 2 also to see where we can improve on what took you too long? And just so that we can monitor everything in the and the process and make it better
14 00:01:40.560 ⇒ 00:01:43.070 Annie Yu: Got it. Okay, cool.
15 00:01:45.530 ⇒ 00:01:48.359 Annie Yu: And for today
16 00:01:48.500 ⇒ 00:01:50.659 Amber Lin: What you? What have you been working on
17 00:01:52.743 ⇒ 00:01:58.390 Annie Yu: I am giving cause. Joby hired a new analyst. So I’m
18 00:01:58.390 ⇒ 00:02:02.069 Amber Lin: Well, yeah, I know you’re good in the walkthrough right?
19 00:02:02.290 ⇒ 00:02:07.869 Annie Yu: Yeah. Well, wish me luck, but it’s good that Robert will be there. I think he
20 00:02:07.870 ⇒ 00:02:08.650 Amber Lin: Okay.
21 00:02:08.650 ⇒ 00:02:14.630 Annie Yu: Because I think he built lots of the visualization there, so he can chime in whatever
22 00:02:14.960 ⇒ 00:02:16.879 Amber Lin: Wait is Robert. I did it.
23 00:02:16.880 ⇒ 00:02:18.290 Annie Yu: I’m not sure. I think
24 00:02:18.290 ⇒ 00:02:24.340 Amber Lin: That’s the sale that’s crazy, actually. Wait! I don’t think he’s going. Probably not.
25 00:02:24.340 ⇒ 00:02:26.200 Amber Lin: Oh, you’re on your own girl.
26 00:02:26.200 ⇒ 00:02:29.019 Annie Yu: I think his, his bullet’s optional
27 00:02:29.020 ⇒ 00:02:29.990 Amber Lin: Okay.
28 00:02:30.280 ⇒ 00:02:39.680 Annie Yu: But yeah, it should be pretty straightforward, I wanna say at least the the dashboards. I think we’re focusing on just 2 dashboards tomorrow. So
29 00:02:39.680 ⇒ 00:02:40.240 Amber Lin: Shouldn’t.
30 00:02:40.240 ⇒ 00:02:42.090 Annie Yu: Too complicated.
31 00:02:42.520 ⇒ 00:03:02.289 Amber Lin: Okay, how are you feeling on that? I know they’re trying to get you to to be on more tasks because we had some part time folks, and it was kind of hard to have them focus and do things. So how are you? How are you feeling on that? Do you feel like you’re getting to the point where you have enough work or
32 00:03:02.290 ⇒ 00:03:10.509 Annie Yu: I think so far I cause I haven’t really started any task
33 00:03:10.510 ⇒ 00:03:11.279 Amber Lin: Oh, okay.
34 00:03:11.280 ⇒ 00:03:12.005 Annie Yu: With
35 00:03:13.160 ⇒ 00:03:20.269 Annie Yu: with Eden or ABC. I know there are tickets for me, but I don’t think I think there’s this dependency on
36 00:03:20.270 ⇒ 00:03:20.850 Amber Lin: Good.
37 00:03:21.390 ⇒ 00:03:33.979 Annie Yu: Other tickets. So so far, I’m really just working with Joby, and I’m also like spending some time learning about the data tables on different projects.
38 00:03:34.170 ⇒ 00:03:34.750 Amber Lin: Oh!
39 00:03:34.750 ⇒ 00:03:38.720 Annie Yu: Oh, yeah, I guess. Started working on something.
40 00:03:39.940 ⇒ 00:03:41.740 Annie Yu: Deliverables, wise
41 00:03:41.740 ⇒ 00:03:43.130 Amber Lin: Oh.
42 00:03:43.530 ⇒ 00:03:56.040 Amber Lin: I see, I mean it takes time. It took me like, and I’m not the engineer. So I took like 2 weeks approximately to ramp up. But for engineering it says a lot more that you need to
43 00:03:56.040 ⇒ 00:04:03.770 Annie Yu: I think the the challenge will be for me is the like. Each team uses different platforms
44 00:04:03.770 ⇒ 00:04:04.590 Amber Lin: Okay.
45 00:04:04.590 ⇒ 00:04:10.742 Annie Yu: And I think I’m definitely more comfortable with Snowflake. But I know that Eden is using bigquery. So I’m gonna
46 00:04:11.300 ⇒ 00:04:14.904 Annie Yu: like, educate myself how to navigate that
47 00:04:15.420 ⇒ 00:04:16.140 Amber Lin: I see.
48 00:04:16.140 ⇒ 00:04:24.840 Annie Yu: But as long as as far as for the data structure, things are probably gonna be pretty similar across teams
49 00:04:25.300 ⇒ 00:04:25.850 Amber Lin: Okay.
50 00:04:26.848 ⇒ 00:04:41.600 Annie Yu: But yeah, I I brought this up to Akash. I asked him, cause he’s pming like 2 of my projects. Ask him like, I know this is not gonna be possible. But can you like try to spread out my
51 00:04:41.840 ⇒ 00:04:47.289 Annie Yu: task deadlines throughout each week, so I don’t like have to land everything at once.
52 00:04:48.120 ⇒ 00:04:49.550 Amber Lin: Oh, I see!
53 00:04:49.550 ⇒ 00:04:55.781 Annie Yu: But yeah, but I’ll I’ll I’ll let you guys know if I’m drowning. But so far, so good
54 00:04:56.110 ⇒ 00:05:25.589 Amber Lin: Sounds good, I mean, for for the ABC team. Today, we have the meeting with their internal data team. So that’s probably going to be most of the stuff you’ll be working on, because right now, Casey and Miguel is the AI engineers on our team. And they’re not data people. So they we had to put Casey on the spot and made him learn all the data stuff and dashboards. So we’re really happy to have you here and sort of take that on from from now
55 00:05:26.430 ⇒ 00:05:30.880 Annie Yu: Cool, and I I did kind of poke around the real
56 00:05:31.430 ⇒ 00:05:39.849 Annie Yu: I am seeing with the dashboards you have now. They’re all for kind of like evaluation of performance of the
57 00:05:40.410 ⇒ 00:05:43.199 Annie Yu: machine learning is that is that it
58 00:05:43.510 ⇒ 00:05:45.870 Annie Yu: is that how the team wants to track
59 00:05:49.090 ⇒ 00:06:00.610 Annie Yu: Or will I be working with, like the these types of data in terms of kind of measuring the AI performance? Or I will be working with different kind of data
60 00:06:01.540 ⇒ 00:06:14.750 Amber Lin: I think mostly it’s on. There’s 2 things. So what we’re using AI for is to help the Csrs. At least, that’s the current thing we’re
61 00:06:15.320 ⇒ 00:06:27.640 Amber Lin: working on right now. So how is this? AI gonna help their Csrs, which is customer service representatives? So then they comes 2 things of one how the AI performed.
62 00:06:28.030 ⇒ 00:06:29.740 Amber Lin: and 2
63 00:06:30.120 ⇒ 00:06:44.450 Amber Lin: how the customer service representatives perform, because that’s the business out right? Because we have the product performance. And we have the business performance. So what we’re gonna meet with the data analysts, if they’re in house data analysts is to
64 00:06:45.045 ⇒ 00:07:07.419 Amber Lin: see how we can get their internal data. I think they already have it pulled of how we’re gonna convert that clean that put in models. I don’t know all the technical stuff and essentially convey, hey? Our AI is performing like this, performing pretty well, and that it has improved your business outcomes. So we’ll need to measure both of them
65 00:07:07.650 ⇒ 00:07:11.190 Annie Yu: Okay, okay, that makes sense. That’s helpful.
66 00:07:11.190 ⇒ 00:07:11.880 Amber Lin: Hmm.
67 00:07:12.625 ⇒ 00:07:20.939 Annie Yu: So does that mean? I’ll also be covering the data engineering side of things or their internal folks will be
68 00:07:21.351 ⇒ 00:07:48.499 Amber Lin: You can probably make them do that because I think they have pretty good data team. So probably your role of when I discuss Witham is, you’re gonna look at real and look at our data. And right? And say, this is what I think needs to be done. Or this is, we kind of need more work there. So because you’re working with eventual visualization
69 00:07:48.680 ⇒ 00:07:49.230 Annie Yu: Okay.
70 00:07:49.550 ⇒ 00:08:04.979 Amber Lin: You’ll know what’s needed, right? Because their in-house analyst doesn’t have that much context of what we’re doing and stuff. So you’ll be essentially data bridge between us and helping us with the dashboards.
71 00:08:05.160 ⇒ 00:08:06.700 Amber Lin: Okay, yeah, alright.
72 00:08:07.240 ⇒ 00:08:15.190 Amber Lin: We’ll know more during the meeting, because I also don’t really know how this is gonna be structured. I’ve never met their in house team yet. This is my 1st time talking to them
73 00:08:15.750 ⇒ 00:08:17.970 Amber Lin: They will have a lot more context
74 00:08:18.260 ⇒ 00:08:20.369 Annie Yu: Okay, that’s cool.
75 00:08:20.370 ⇒ 00:08:23.120 Amber Lin: So have you got a chance to
76 00:08:23.280 ⇒ 00:08:29.959 Amber Lin: get a sense of who this client is? Have you been able to ask the AI agent in our slack channel
77 00:08:30.378 ⇒ 00:08:37.329 Annie Yu: I think I am pretty comfortable with the idea of what they do. And then
78 00:08:37.830 ⇒ 00:08:42.129 Annie Yu: our kind of our our goals with this client
79 00:08:42.130 ⇒ 00:08:48.540 Amber Lin: Can you? Can you walk me through your understanding of that? So I can. I can see where we’re aligned
80 00:08:49.636 ⇒ 00:08:54.553 Annie Yu: Okay. So I know that our main goal with them is
81 00:08:56.610 ⇒ 00:08:59.240 Annie Yu: what? What do you call them? The Csr
82 00:08:59.240 ⇒ 00:09:01.250 Amber Lin: Yeah. The customer service representatives.
83 00:09:02.090 ⇒ 00:09:12.380 Annie Yu: Yeah, to help them to evaluate how their Csr performs as well as how our AI agents or our AI products help them
84 00:09:13.180 ⇒ 00:09:14.300 Annie Yu: with their
85 00:09:15.490 ⇒ 00:09:20.480 Annie Yu: Is that the delivery time? With the
86 00:09:20.480 ⇒ 00:09:21.570 Amber Lin: Other calls.
87 00:09:21.570 ⇒ 00:09:24.970 Annie Yu: I’m yeah, yeah, I don’t know what that call yet.
88 00:09:25.370 ⇒ 00:09:26.890 Amber Lin: Hmm, it’s okay.
89 00:09:27.080 ⇒ 00:09:27.940 Amber Lin: Yeah.
90 00:09:31.100 ⇒ 00:09:33.980 Amber Lin: Anything else. Before I chime in
91 00:09:35.793 ⇒ 00:09:40.460 Annie Yu: Let me think about it. I haven’t got a chance to take a note.
92 00:09:44.100 ⇒ 00:09:50.709 Annie Yu: I think. Wait, to my knowledge. That’s the 2 main things right for this, for this project
93 00:09:52.330 ⇒ 00:09:57.240 Amber Lin: Yeah, so I I guess here, I’ll just run you through really quickly.
94 00:09:57.240 ⇒ 00:09:57.580 Annie Yu: Okay.
95 00:09:58.240 ⇒ 00:10:02.199 Amber Lin: This client is a pretty big
96 00:10:02.760 ⇒ 00:10:06.059 Amber Lin: home and Home Surf Service Company
97 00:10:06.060 ⇒ 00:10:06.820 Annie Yu: Okay.
98 00:10:06.820 ⇒ 00:10:21.260 Amber Lin: So their name is ABC. Home service and Commercial. So home service is like, oh, you do plumbing, you have bugs you deal with that you have. You need to trim trees. So imagine everything someone needs if they live at a home. So like
99 00:10:21.360 ⇒ 00:10:28.680 Amber Lin: all of that maintenance stuff that you need a painter, whatever you can go through their website and look it up
100 00:10:28.680 ⇒ 00:10:41.319 Annie Yu: I did. I did. And I recently moved to a house. So I’m like, this is pretty cool because I had to contact different providers, different contractors for different projects, and now they are like kind of like a 1 stop shop for home
101 00:10:41.320 ⇒ 00:10:50.909 Amber Lin: I know they have everything, and that’s why, right now. So we’re working with their pest department. So they deal with all the bugs, and but
102 00:10:51.310 ⇒ 00:11:19.870 Amber Lin: down the road we want to expand to their other divisions. So there’s a lot more work and a lot more revenue that we can generate here. But right now we’re working just with their pest department. And so we’re working with their pest Csrs. And all the information is related to what kind of pest service you have. What kind of procedures you need to do to schedule all these things? So it’s all about pest right now.
103 00:11:19.870 ⇒ 00:11:24.270 Annie Yu: And we also track products or not
104 00:11:24.720 ⇒ 00:11:26.239 Amber Lin: What do you mean? Products.
105 00:11:26.858 ⇒ 00:11:34.230 Annie Yu: Like. Let’s say, how many people opt in for organic chemicals
106 00:11:34.890 ⇒ 00:11:38.069 Amber Lin: Oh, I see, I don’t think we’re
107 00:11:38.240 ⇒ 00:11:49.790 Amber Lin: doing that. That’s a diff. So that will be a different project right now. We’re just making a bot to help the Csr, so we’re limited pretty much in the Customer Service Department.
108 00:11:49.790 ⇒ 00:11:51.300 Annie Yu: Right? Okay, okay.
109 00:11:51.300 ⇒ 00:12:11.029 Amber Lin: Yeah. So the 2 bots right now, this, this, the one for the customer service representatives, is getting deployed. We’re test deploying to 5 Csrs. Well, they have 25 in total. So that’s 1 thing. And the other thing is, you know, the trainers, the managers for these
110 00:12:11.090 ⇒ 00:12:21.960 Amber Lin: Csrs. They have a lot of documentation. And we need to make it easier for them to update. So we’re creating update bot a little bit down the line. And
111 00:12:22.030 ⇒ 00:12:35.539 Amber Lin: here the main problem that they’re facing. So the main problem for this client that we’re tackling is that they have too much documents. So every single time the customer asks a question.
112 00:12:35.790 ⇒ 00:12:57.240 Amber Lin: The Csrs have to search 50 documents in Google, drive and find the right one and then find the answers and then tell the customers the answer. So the customers are on hold for a long, long time, and for the business that just means the customer will leave. They don’t want to wait 30 min to get a question. They’ll ask someone else
113 00:12:57.240 ⇒ 00:12:57.830 Annie Yu: Yeah.
114 00:12:57.830 ⇒ 00:13:21.560 Amber Lin: So we’re trying to solve that. And so we want the bot to give answers fast, and we wanted to give it accurately. And we want it to be helpful for the Csr essentially. That’s why what we’re measuring on real. So you’ll see the quality score you’ll see the S average
115 00:13:22.596 ⇒ 00:13:23.193 Annie Yu: Okay.
116 00:13:24.063 ⇒ 00:13:28.169 Amber Lin: And you’ll also see the error rate of. Are we actually accurate in our responses?
117 00:13:28.430 ⇒ 00:13:37.309 Annie Yu: And okay for for these ones you just mentioned the quality score, execution, time and error rate, that’s all. Just for the the bot, the chat
118 00:13:37.310 ⇒ 00:13:45.259 Amber Lin: That’s the bot. Today. We’re talking with them about, how are we gonna get your internal call data integrated as well. So that’s an important conversation
119 00:13:45.260 ⇒ 00:13:47.899 Annie Yu: Internal call. Oh, interesting!
120 00:13:47.900 ⇒ 00:13:52.629 Amber Lin: Yeah, no, we’re calling with. You’re in that meeting, too. Right? So the next meeting we’re gonna have
121 00:13:52.810 ⇒ 00:13:57.599 Amber Lin: with the internal data folks from ABC
122 00:13:58.470 ⇒ 00:14:09.749 Amber Lin: Yeah. And I think a problem we’re facing right now is our error measurements and our quality score measurements are not very good.
123 00:14:10.120 ⇒ 00:14:15.390 Amber Lin: So the error score. One is pretty high
124 00:14:15.600 ⇒ 00:14:20.250 Amber Lin: and 2 because we want errors to be 0 and 2. It’s
125 00:14:20.850 ⇒ 00:14:25.520 Amber Lin: flagging some questions as wrong when it’s right.
126 00:14:26.680 ⇒ 00:14:42.960 Amber Lin: The measurements are not that great? So probably what you’ll do is you’ll look at the data and say, Hey, here, I think here it might have got it wrong. Here’s what you guys might need to do to adjust on the inside. Do you know anything about data modeling
127 00:14:44.447 ⇒ 00:14:45.459 Annie Yu: You mean, like
128 00:14:45.690 ⇒ 00:14:53.060 Annie Yu: writing sequel and then build a table for me to use for visualization is that is all you’re referring to.
129 00:14:53.550 ⇒ 00:14:59.399 Amber Lin: I think that’s more like, what is data modeling to you? Because I also don’t know that much
130 00:14:59.670 ⇒ 00:15:08.239 Annie Yu: I. To my knowledge, I think my understanding is that if I can do something with my visualizations
131 00:15:08.510 ⇒ 00:15:17.839 Annie Yu: tool, then we would have to build a data table in order for me to get those columns into my visualization
132 00:15:17.840 ⇒ 00:15:22.480 Amber Lin: Okay, yeah. So I think.
133 00:15:24.630 ⇒ 00:15:27.779 Annie Yu: Could be wrong, or that could be just part of it.
134 00:15:27.780 ⇒ 00:15:41.930 Amber Lin: It’s part of is most most of it, but probably just part of it, most part of it. I was just talking to them a lot a little bit earlier. I think there’s the ingestion and transformation. And then the and then the bi tools right
135 00:15:42.720 ⇒ 00:15:57.219 Amber Lin: You’re dealing more with the bi tools and maybe a little bit of information. But they’re the ones doing the ingestion. And right now that’s Casey and Miguel. So we have brain trust is where we do all the evaluations for the AI bot.
136 00:15:57.370 ⇒ 00:16:09.569 Amber Lin: So we have all the evaluations go in there. We’re putting that data into Snowflake. And then I guess from there you take over and then build it into a visualization
137 00:16:11.000 ⇒ 00:16:11.360 Annie Yu: Okay.
138 00:16:11.360 ⇒ 00:16:23.289 Amber Lin: That’s how it goes. We’ll need to confirm with Utah more specifically what part you will be responsible for, because I’m not exactly sure how we define the lines between aes and analysts in this company.
139 00:16:23.410 ⇒ 00:16:23.930 Amber Lin: But
140 00:16:23.930 ⇒ 00:16:28.466 Annie Yu: Yeah, I think. in in in joby, usually.
141 00:16:29.030 ⇒ 00:16:33.459 Annie Yu: because that that’s all the sample I have. Now, I do have knowledge
142 00:16:33.930 ⇒ 00:16:46.829 Annie Yu: with like SQL, and then data engineering. But obviously like a Weish and Kyle have more knowledge around what’s really behind the data. So if there’s like a more complex things.
143 00:16:47.060 ⇒ 00:17:10.499 Annie Yu: They would be the one to handle that. But if I just need, let’s say, add another column, I or or if I see that the the model wish build was not exactly what I want. And then I can read his code and then realize, okay, I probably just need to add this row of line to make it. How I want it! Then I would make a Pr. Request, and that wish to be the one
144 00:17:10.500 ⇒ 00:17:11.329 Amber Lin: Oh, I see!
145 00:17:11.339 ⇒ 00:17:24.439 Annie Yu: Yeah, that’s all I like am able to do now with Joby. But I know that with like a building, a new data model from scratch. That’s more complicated. They will be the one to handle it
146 00:17:25.270 ⇒ 00:17:26.480 Amber Lin: I see.
147 00:17:26.480 ⇒ 00:17:31.149 Annie Yu: But I’m not sure how how that works. Within this team, because I think
148 00:17:31.310 ⇒ 00:17:36.700 Annie Yu: Eden also has a different working process around that
149 00:17:38.890 ⇒ 00:17:42.240 Amber Lin: I see cool. That’s helpful. So I think.
150 00:17:42.530 ⇒ 00:17:56.986 Amber Lin: Well, we’ll probably need to talk to Casey in more detail on how he’s handling all of that, because apparently he well, we only have 2 people on the team, so he has to be handling all the data modeling. So you’ll probably talk to him about how that is going
151 00:17:57.270 ⇒ 00:17:58.370 Annie Yu: Yeah, yeah.
152 00:17:58.370 ⇒ 00:18:01.230 Amber Lin: Okay, sounds good. Any other questions you have
153 00:18:03.340 ⇒ 00:18:06.640 Annie Yu: I think so.
154 00:18:06.960 ⇒ 00:18:13.349 Annie Yu: I know that you’ve created some tickets for me on linear
155 00:18:14.420 ⇒ 00:18:16.359 Amber Lin: Let me go check that!
156 00:18:17.900 ⇒ 00:18:19.170 Amber Lin: See
157 00:18:24.530 ⇒ 00:18:34.950 Annie Yu: And really just about the onboarding process. So I know that you mentioned I will need to, I think, get familiar with real data
158 00:18:34.950 ⇒ 00:18:35.560 Amber Lin: Yeah.
159 00:18:35.560 ⇒ 00:18:38.659 Annie Yu: And then the snowflake. I know that
160 00:18:38.810 ⇒ 00:18:50.600 Annie Yu: Casey provided specifically one table. That’s important. So not where I start. And is there any other data tables I should focus on first, st
161 00:18:50.917 ⇒ 00:18:59.490 Amber Lin: That would be a Casey question. I have no clue. What goes on in there? Where is? Let me find your ticket, and I will put
162 00:19:01.380 ⇒ 00:19:07.299 Amber Lin: took it there. I’m going to delete this documentation because I don’t really want to spend time doing that
163 00:19:07.630 ⇒ 00:19:10.300 Annie Yu: Okay, and let me see.
164 00:19:10.300 ⇒ 00:19:18.194 Annie Yu: he provided one yesterday. And and, to be honest, I’m not yet familiar with that one. So I can definitely just start with that one
165 00:19:18.510 ⇒ 00:19:20.249 Amber Lin: Okay, okay, sounds good.
166 00:19:21.340 ⇒ 00:19:31.090 Amber Lin: Let’s see, I’ll put one here of ask case meets
167 00:19:31.750 ⇒ 00:19:43.779 Amber Lin: book wanna I guess. Book call with Casey to understand? Heard data, structure
168 00:19:44.230 ⇒ 00:19:49.589 Amber Lin: tables, etc. So I’ll put note there.
169 00:19:50.980 ⇒ 00:19:55.180 Amber Lin: I’ll say, by the end of end of this week
170 00:19:55.630 ⇒ 00:19:56.290 Annie Yu: Okay.
171 00:19:56.500 ⇒ 00:20:05.819 Amber Lin: And I think another thing is, do you know how to use real like? Are you familiar with real
172 00:20:05.820 ⇒ 00:20:12.150 Annie Yu: No, I I’m I’m able to log in, but I haven’t really poke around
173 00:20:12.150 ⇒ 00:20:25.850 Amber Lin: I see not just, I think, not just our real, but just do you know how to set it up in your desktop like? Do you know the developer environments? We versus a cloud environments? Do you know how to pivot or add things like
174 00:20:29.010 ⇒ 00:20:38.710 Annie Yu: So I’m not sure how familiar it is with like tableau and other bi tools. But if we’re just talking about real, specifically, I haven’t
175 00:20:38.710 ⇒ 00:20:44.959 Amber Lin: That’s what we use. Yeah, I think a good idea would be to set up.
176 00:20:45.470 ⇒ 00:20:58.950 Amber Lin: We’re on local and then do sound do like a magic. Alright. Spare with me.
177 00:20:59.750 ⇒ 00:21:07.350 Amber Lin: Yeah, maybe see data. And in particular, I’ll say.
178 00:21:07.800 ⇒ 00:21:18.602 Amber Lin: figure out how the canvas is working. We have the external channel with the real folks directly. So if you have any questions you can definitely ask to be added there and then
179 00:21:19.110 ⇒ 00:21:20.270 Amber Lin: passed up
180 00:21:20.640 ⇒ 00:21:21.350 Annie Yu: Okay.
181 00:21:22.738 ⇒ 00:21:36.879 Amber Lin: And we want to add a real campus. So that’s more when it’s that’s more like the tableau that you have worked with. So you’ll probably be familiar with that. But you just need to learn how to set it up. That’s all.
182 00:21:37.030 ⇒ 00:21:38.779 Annie Yu: Okay, real canvas
183 00:21:39.435 ⇒ 00:21:39.949 Amber Lin: Yeah.
184 00:21:40.180 ⇒ 00:21:50.700 Amber Lin: So there’s a few things in real. Just I think this week will be a lot of familiarizing yourself with that, because that’s mostly what you’ll be working based in.
185 00:21:50.910 ⇒ 00:22:00.420 Amber Lin: But maybe you can do a sample project, or whatever I’ll say. Also at the end of this week.
186 00:22:01.650 ⇒ 00:22:05.320 Amber Lin: so I’ll put tickets in there.
187 00:22:06.350 ⇒ 00:22:09.480 Amber Lin: Put a to do in cycle.
188 00:22:14.580 ⇒ 00:22:15.920 Amber Lin: Where is this
189 00:22:21.020 ⇒ 00:22:21.790 Amber Lin: -
190 00:22:34.890 ⇒ 00:22:39.280 Amber Lin: That’s that’s all. From my side.
191 00:22:39.780 ⇒ 00:22:45.239 Annie Yu: And hey, all. One more question is, who what’s what’s kind of the roles
192 00:22:45.440 ⇒ 00:22:51.250 Annie Yu: of everyone on this project so casey is the yeah, can kind of
193 00:22:52.260 ⇒ 00:22:55.729 Annie Yu: walk me through, because I know there’s also a Miguel
194 00:22:55.730 ⇒ 00:22:59.900 Amber Lin: Yeah, Miguel’s more the head of AI. He
195 00:23:00.090 ⇒ 00:23:09.530 Amber Lin: used to be more on development side right now. But he right now he’s moving more into a leadership role, so he will help he will help coach, and he will
196 00:23:09.720 ⇒ 00:23:09.910 Annie Yu: No.
197 00:23:10.820 ⇒ 00:23:33.000 Amber Lin: do pair programming. But mostly he’s gonna be more of the directional guy. If you need to help things with how things are done with like estimates, with deadlines or any help you need will go to him. Casey’s gonna main be the main AI developer on this team. I’m gonna be the project manager, and
198 00:23:34.680 ⇒ 00:23:43.069 Amber Lin: the product owner is on the client’s team. So I guess I do have to write this documentation and
199 00:23:45.260 ⇒ 00:23:58.560 Amber Lin: So there’s our main point of contact is Janice, and so Janice’s boss is Yvette.
200 00:23:58.920 ⇒ 00:24:07.449 Amber Lin: and there’s other like more exec folks that we only meet on Friday, which I don’t think any of the engineers need to be at that meeting. So that’s okay.
201 00:24:08.090 ⇒ 00:24:15.680 Amber Lin: And under Janice, which is our main point of contact. That we talk every day with is managers. That’s
202 00:24:16.100 ⇒ 00:24:42.940 Amber Lin: a little bit lower, and talks even closer to the Csr. So like mid level managers, and we have Shannon and Grace, and then we have the Csrs, right? So we’re kind of with the mid to higher level management is what we talk to pretty frequently, and they are very supportive. They’re very nice people, and they they’re very communicative. They want to be want this project to succeed. So a lot less
203 00:24:43.080 ⇒ 00:24:50.149 Amber Lin: a lot less problems than what Eden is facing right now. So I thought the easier clients, though
204 00:24:50.150 ⇒ 00:24:58.460 Annie Yu: That’s great to hear, and I know that I heard about like Eden’s being like emotionally challenging. But what’s
205 00:24:58.460 ⇒ 00:24:58.840 Amber Lin: So.
206 00:24:58.840 ⇒ 00:25:07.737 Annie Yu: Like, what’s what’s the because I haven’t really worked with them or interacted with them. So what’s what’s there to like? I guess? Be careful for
207 00:25:09.040 ⇒ 00:25:11.449 Amber Lin: In this client. I mean
208 00:25:12.080 ⇒ 00:25:17.920 Amber Lin: this class, mostly nice, and we’re on track. So we’re good for now.
209 00:25:18.170 ⇒ 00:25:27.689 Amber Lin: and they don’t have. They don’t have a lot of random requests here and there. They’re pretty much know what we’re working on. They know the priority. So that’s good
210 00:25:28.060 ⇒ 00:25:29.000 Annie Yu: Great, awesome.
211 00:25:29.270 ⇒ 00:25:30.090 Amber Lin: Okay.
212 00:25:30.470 ⇒ 00:25:38.129 Amber Lin: awesome. I need to jump to another meeting. Thank you for the call, and I’ll see you later in the other meeting.
213 00:25:38.320 ⇒ 00:25:39.760 Annie Yu: Alright! Alright! Thank you. Amber
214 00:25:39.990 ⇒ 00:25:40.950 Amber Lin: Bye.