Meeting Title: CTA Access and AI Overview Sync Date: 2026-04-07 Meeting participants: Awaish Kumar, Amber Lin
WEBVTT
1 00:01:38.760 ⇒ 00:01:40.050 Amber Lin: Hello!
2 00:01:40.580 ⇒ 00:01:41.150 Awaish Kumar: Hi.
3 00:01:49.310 ⇒ 00:01:50.330 Awaish Kumar: How you doing?
4 00:01:50.850 ⇒ 00:01:52.749 Amber Lin: Hi, I’m doing well.
5 00:01:54.510 ⇒ 00:01:59.520 Amber Lin: Alright, so I know we weren’t wanting to start on CTA today.
6 00:01:59.520 ⇒ 00:02:02.119 Awaish Kumar: Okay, so did you get the access?
7 00:02:03.420 ⇒ 00:02:07.389 Amber Lin: Access to which ones?
8 00:02:08.009 ⇒ 00:02:10.899 Awaish Kumar: access to anything for CTA? Have you received anything?
9 00:02:13.040 ⇒ 00:02:22.700 Amber Lin: I think I will have everything in one pass, but other than that, is there, is there a CTA GitHub that I should have access to?
10 00:02:22.700 ⇒ 00:02:25.650 Awaish Kumar: So, you need access to Okta?
11 00:02:27.500 ⇒ 00:02:28.580 Amber Lin: Guys.
12 00:02:28.920 ⇒ 00:02:38.970 Awaish Kumar: Optizer… Kind of a… Platform that manages authentication between multiple systems.
13 00:02:39.190 ⇒ 00:02:44.240 Awaish Kumar: So you just have to get a, you just have to see where…
14 00:02:45.020 ⇒ 00:02:52.819 Awaish Kumar: login, password for Okta, or invite for Okta, so you can create, sign up, but it’s something, like, you can…
15 00:02:53.700 ⇒ 00:02:59.699 Awaish Kumar: Actually, I can tag, someone there and get you in, and then…
16 00:02:59.700 ⇒ 00:03:02.709 Amber Lin: do that. I actually don’t know what that would be.
17 00:03:02.710 ⇒ 00:03:10.289 Awaish Kumar: Okay, and then, once you have that access, you can… once you… and log into that, you will have
18 00:03:11.090 ⇒ 00:03:13.350 Awaish Kumar: through that, like, I can show you.
19 00:03:13.690 ⇒ 00:03:14.165 Amber Lin: Hmm.
20 00:03:15.420 ⇒ 00:03:19.459 Awaish Kumar: Through that, you will be accessing, kind of, everything.
21 00:03:20.430 ⇒ 00:03:21.470 Awaish Kumar: Basically.
22 00:03:23.000 ⇒ 00:03:26.370 Awaish Kumar: It should look… Sign in.
23 00:03:26.820 ⇒ 00:03:30.520 Awaish Kumar: Okay, it should look like, something…
24 00:03:36.220 ⇒ 00:03:42.669 Awaish Kumar: Okay, once you sign in to Okta Dashboard, you will have Some of the apps here.
25 00:03:44.040 ⇒ 00:03:46.029 Awaish Kumar: Please, like, we… like, you…
26 00:03:46.460 ⇒ 00:03:49.549 Awaish Kumar: We need the GitHub, Snowflake, production, and AWS.
27 00:03:49.750 ⇒ 00:03:56.580 Awaish Kumar: So, you have to log into this, and then you can log into GitHub. From here, log into Snowflake, and log into EWS.
28 00:03:56.710 ⇒ 00:03:57.650 Awaish Kumar: I see.
29 00:03:57.650 ⇒ 00:04:14.299 Amber Lin: Okay. I, I mean, I see your account in 1Pass, so, I mean, worst case, I can maybe use your account in OnePass to look at them today, if we don’t get access soon enough. So, like, I will be able to look at them through your account, I think.
30 00:04:15.180 ⇒ 00:04:15.970 Awaish Kumar: Okay.
31 00:04:19.589 ⇒ 00:04:23.990 Awaish Kumar: Okay, yeah, if you’re just using it manually, you can use my account.
32 00:04:25.500 ⇒ 00:04:32.870 Awaish Kumar: We don’t make any changes to EI, or since… It would be my… Name one.
33 00:04:34.560 ⇒ 00:04:35.390 Awaish Kumar: But, yeah.
34 00:04:35.390 ⇒ 00:04:39.690 Amber Lin: Yeah, I agree. If you were to push any changes, I probably should have my account.
35 00:04:40.090 ⇒ 00:04:43.030 Awaish Kumar: Okay, but apart from that.
36 00:04:43.160 ⇒ 00:04:49.919 Awaish Kumar: But I will just ping him, and they will get you soon. But you can look… losing my account, you can just explore what is there.
37 00:04:51.200 ⇒ 00:04:54.630 Awaish Kumar: Obviously, they will get you access, like, I think, by…
38 00:04:54.730 ⇒ 00:04:57.319 Awaish Kumar: Today or tomorrow, so you, you won’t have to.
39 00:04:57.770 ⇒ 00:05:17.590 Awaish Kumar: Like, we won’t delay on that, so that’s not an issue. But it’s just, I’m showing you, this is how it will look like. You can… you have to go to GitHub, you’ll get access to the repo, but then AWS is where we have our leg, like, the data lake, where we… all the data we have, right, for CT is kind of coming via S3.
40 00:05:18.180 ⇒ 00:05:19.240 Awaish Kumar: So…
41 00:05:20.030 ⇒ 00:05:35.989 Awaish Kumar: But you don’t have to work on that. It’s, like, I don’t know if you need access, I can ask that you should have access to AWS, but mainly you will be working in production, since Umputa mentioned that you will be working more with Cortex.
42 00:05:36.040 ⇒ 00:05:43.060 Awaish Kumar: I mean, so it’s more inside… everything is inside Snowflake. So one thing in the snowflake,
43 00:05:44.600 ⇒ 00:05:50.099 Awaish Kumar: There are some models that we have created, and there’s… there’s a concept of Cortex code, and
44 00:05:50.560 ⇒ 00:05:53.199 Awaish Kumar: Agents, like, the…
45 00:05:54.480 ⇒ 00:05:59.680 Awaish Kumar: And, agents, analysts, search, codec search, and things like that.
46 00:05:59.830 ⇒ 00:06:03.940 Awaish Kumar: And it is, like, this Azure Analyst search.
47 00:06:04.260 ⇒ 00:06:05.420 Awaish Kumar: So…
48 00:06:06.000 ⇒ 00:06:17.340 Amber Lin: Cool. Can you show me… I think Utam wanted you to show me what the models we have, and maybe, if you can, also walk me through, like, the AI stuff.
49 00:06:18.940 ⇒ 00:06:21.100 Awaish Kumar: That’s where we are moving towards.
50 00:06:21.250 ⇒ 00:06:25.010 Awaish Kumar: So this is the… Explorer.
51 00:06:26.050 ⇒ 00:06:28.700 Awaish Kumar: The data that we ingest from S…
52 00:06:28.860 ⇒ 00:06:32.689 Awaish Kumar: S3 is going into raw database, similar to.
53 00:06:32.690 ⇒ 00:06:33.180 Amber Lin: Okay.
54 00:06:33.180 ⇒ 00:06:37.099 Awaish Kumar: The conservancy is… as per our other clients, right?
55 00:06:37.560 ⇒ 00:06:42.660 Awaish Kumar: and everything in raw. So these are the sources from which we are getting the data.
56 00:06:43.350 ⇒ 00:06:45.100 Awaish Kumar: Cvent is one of the source.
57 00:06:45.430 ⇒ 00:06:47.910 Awaish Kumar: Salesforce Marketing Cloud is another source.
58 00:06:48.090 ⇒ 00:06:50.330 Awaish Kumar: Is there another suits.
59 00:06:50.470 ⇒ 00:06:54.430 Awaish Kumar: archive data. It’s a CES data.
60 00:06:54.570 ⇒ 00:06:56.840 Awaish Kumar: So they have CES event.
61 00:06:57.180 ⇒ 00:06:57.760 Awaish Kumar: Right.
62 00:06:57.760 ⇒ 00:06:58.240 Amber Lin: Hmm.
63 00:06:59.870 ⇒ 00:07:11.069 Awaish Kumar: if you’re familiar with this, like, what they do is they run events, right? And one of their main events is CES, so for… the data for that lives in the archive data.
64 00:07:11.220 ⇒ 00:07:15.579 Awaish Kumar: Schema, and then other events are in the C event.
65 00:07:15.700 ⇒ 00:07:25.400 Awaish Kumar: then we have Salesforce, then we have Shopify. And then the concept of, layers of dbt. So we have a staging,
66 00:07:25.630 ⇒ 00:07:37.759 Amber Lin: Yeah. I think what will be helpful is just to go through the prop marks. I understand the layers, because I’ve worked with things we’ve built before. Can you show me what type of models we have in…
67 00:07:37.760 ⇒ 00:07:38.350 Awaish Kumar: Yeah.
68 00:07:38.350 ⇒ 00:07:39.700 Amber Lin: Broad or something?
69 00:07:40.130 ⇒ 00:07:45.499 Amber Lin: Like, ultimately, I’m just thinking of what business question they would be asking.
70 00:07:46.320 ⇒ 00:07:54.709 Awaish Kumar: Yeah, so yeah, we are going there. Yeah, there’s a little bit of changes in the naming, so that’s why I’m trying to explain.
71 00:07:54.960 ⇒ 00:07:55.790 Amber Lin: Oh, okay.
72 00:07:55.790 ⇒ 00:08:11.650 Awaish Kumar: QA. So, we have a, like, normally we have dev, maybe CICD, and product here, we don’t have CICD, we call it QA. This is where you… anything you made a DBD… if you make a change in DBD model, it will be reflected here in one of these
73 00:08:11.650 ⇒ 00:08:18.490 Awaish Kumar: databases. And once it’s… after it’s merged, obviously, it’s going to broad, and then… These are the,
74 00:08:19.400 ⇒ 00:08:23.250 Awaish Kumar: all the… Mars that we have created so far.
75 00:08:25.190 ⇒ 00:08:36.540 Awaish Kumar: So we have Shopify… so we don’t have exactly Shopify as per all the models. It’s a Shopify download, it’s mainly created by Kyle, so he…
76 00:08:36.890 ⇒ 00:08:40.839 Awaish Kumar: He added the models that were needed for one of the reports.
77 00:08:42.070 ⇒ 00:08:44.360 Awaish Kumar: As orders, customers, companies.
78 00:08:45.430 ⇒ 00:08:49.010 Amber Lin: They use Shopify for customers.
79 00:08:49.280 ⇒ 00:08:51.360 Amber Lin: Products?
80 00:08:51.930 ⇒ 00:08:56.129 Awaish Kumar: they sell some of the products, right? We can look at this in this…
81 00:08:56.720 ⇒ 00:09:01.589 Amber Lin: Oh, so if customer orders, like, an event, it wouldn’t show up here.
82 00:09:01.860 ⇒ 00:09:03.240 Amber Lin: Right, or will it?
83 00:09:03.240 ⇒ 00:09:12.899 Awaish Kumar: orders, obviously, they buy something from Shopify, but they can buy… they can buy, for example, some… there is some research document, or, like, the research paper.
84 00:09:12.900 ⇒ 00:09:15.030 Amber Lin: Oh, okay, okay.
85 00:09:15.030 ⇒ 00:09:18.549 Awaish Kumar: digital assets. They’re not selling, like, a…
86 00:09:18.710 ⇒ 00:09:28.689 Awaish Kumar: physical things, it’s mainly the digital assets, and I… some publications and things like that. I’m not sure why it’s scrolling towards the right, but…
87 00:09:29.100 ⇒ 00:09:30.220 Awaish Kumar: I shouldn’t.
88 00:09:31.580 ⇒ 00:09:32.270 Amber Lin: Okay.
89 00:09:32.620 ⇒ 00:09:39.740 Awaish Kumar: there are some fields… school, right? So in that school, you can figure out, like, what type of product that is.
90 00:09:42.100 ⇒ 00:09:42.910 Amber Lin: Cool.
91 00:09:43.110 ⇒ 00:09:44.760 Awaish Kumar: Then we have,
92 00:09:46.050 ⇒ 00:10:01.240 Awaish Kumar: Salesforce Marketing Cloud, that we ingested and we modeled, but it’s… the PR is not merged, that’s why we can’t see it here, but that should be here. Salesforce Marketing Cloud, basically, they are using this for…
93 00:10:01.690 ⇒ 00:10:10.769 Awaish Kumar: Sending, like, running campaigns, sending emails, to people, like…
94 00:10:11.690 ⇒ 00:10:16.010 Awaish Kumar: Like, for example, you get an… Invite for… for an event.
95 00:10:16.040 ⇒ 00:10:17.140 Amber Lin: Only…
96 00:10:17.580 ⇒ 00:10:27.459 Awaish Kumar: And, like, the CTA thinks, like, you might join, they send you an invite, but that is… happens through… that happens through Salesforce Marketing Cloud, and then…
97 00:10:27.460 ⇒ 00:10:28.080 Amber Lin: Hmm.
98 00:10:28.700 ⇒ 00:10:33.989 Awaish Kumar: Using that link, if you register and you come in the event, then you are an attendee.
99 00:10:34.140 ⇒ 00:10:35.160 Awaish Kumar: So…
100 00:10:35.950 ⇒ 00:10:44.159 Awaish Kumar: And that, for the attendee, we have a different data where we have all the people that join, so we can actually measure the people
101 00:10:44.320 ⇒ 00:10:56.829 Awaish Kumar: the number of people who invited, and then how many of those actually end up joining for each of the events. So sales marketing cloud is mainly for running these email campaigns, and you have information.
102 00:10:57.380 ⇒ 00:10:58.150 Amber Lin: Okay.
103 00:10:58.440 ⇒ 00:11:01.739 Awaish Kumar: Who clicked on the email, who clicked on… opened the email, who…
104 00:11:02.080 ⇒ 00:11:07.860 Awaish Kumar: who opened the link, links inside of that, and it’s all of that information. And then we have…
105 00:11:08.120 ⇒ 00:11:12.010 Awaish Kumar: ExpoCAD. ExpoCAD is the data regarding their
106 00:11:12.500 ⇒ 00:11:17.460 Awaish Kumar: Exhibitor, like, the physical locations in their event.
107 00:11:17.650 ⇒ 00:11:20.110 Awaish Kumar: So in CS events, if they have a
108 00:11:22.160 ⇒ 00:11:28.560 Awaish Kumar: They have, like, people actually can… Register for the booth, right?
109 00:11:28.650 ⇒ 00:11:46.840 Awaish Kumar: So, this is the… where that information lives. So, Brainforce can go into CJ’s event as an exhibitor, we can have our own booth, and in that booth, then you have information regarding that, like, okay, what company joined, what people from Brainforce came in the…
110 00:11:48.480 ⇒ 00:11:49.310 Amber Lin: Mmm.
111 00:11:49.310 ⇒ 00:11:53.259 Awaish Kumar: They rent, and then what was their location in their…
112 00:11:53.430 ⇒ 00:12:01.470 Awaish Kumar: physical, whatever, place they have, what was their booth member, and things, things like…
113 00:12:02.340 ⇒ 00:12:05.900 Awaish Kumar: Okay, and then we have CRM, it’s more like…
114 00:12:06.140 ⇒ 00:12:10.209 Awaish Kumar: Remembers is a tool, basically, platform that they use.
115 00:12:12.470 ⇒ 00:12:14.839 Awaish Kumar: For their membership engagement.
116 00:12:15.220 ⇒ 00:12:16.160 Awaish Kumar: Things.
117 00:12:16.380 ⇒ 00:12:24.870 Awaish Kumar: And, this is where that data lives under CRM. It is more about membership engagement data.
118 00:12:26.390 ⇒ 00:12:36.700 Awaish Kumar: Choosing… coming from remembers, so we have raw data in the raw layer, and then basically creating this information regarding team individual, team organization, fact table.
119 00:12:37.590 ⇒ 00:12:41.109 Awaish Kumar: And then we are trying to tie it all together, like.
120 00:12:41.370 ⇒ 00:12:50.509 Awaish Kumar: First of all, cases, like, so we have demorganization, which is the cleanest data possible for the organization who
121 00:12:51.210 ⇒ 00:12:55.380 Awaish Kumar: basically come to the CES event, right?
122 00:12:55.830 ⇒ 00:13:02.290 Amber Lin: I see, and this is kind of tied to the other, like, CES event tables, or maybe order tables?
123 00:13:02.290 ⇒ 00:13:06.449 Awaish Kumar: Then we have some tables, like, That do identity switching.
124 00:13:06.800 ⇒ 00:13:11.480 Awaish Kumar: It’s not possible, like, very cleanly to do that, so we have some of the…
125 00:13:12.790 ⇒ 00:13:16.500 Awaish Kumar: Tables, that’s… that says org.
126 00:13:17.900 ⇒ 00:13:27.309 Awaish Kumar: Maybe I… search for that. So there are some of the… Models, and the intermediate layer.
127 00:13:27.430 ⇒ 00:13:44.260 Awaish Kumar: let’s say, or a good resolution, like the member engagement, veg skins, so you have veg skin data, but then there’s some company name, but then how we are going to tie it with the CRM, so it’s like, it will have some ID.
128 00:13:44.560 ⇒ 00:13:46.030 Awaish Kumar: So…
129 00:13:46.660 ⇒ 00:13:49.440 Awaish Kumar: Created this table based on some of the rules, like.
130 00:13:49.650 ⇒ 00:14:02.939 Awaish Kumar: Maybe we have some ideology that we can use to join it, then if that is… for those where it is null, we may be using email addresses, or domain, or the name of the company.
131 00:14:04.530 ⇒ 00:14:05.859 Amber Lin: Mmm, okay.
132 00:14:05.890 ⇒ 00:14:10.830 Awaish Kumar: Things to figure out that, and… Normally, you don’t have to…
133 00:14:11.060 ⇒ 00:14:17.210 Awaish Kumar: Do that mapping yourself, because we have done it in these correlation tables.
134 00:14:18.340 ⇒ 00:14:21.130 Awaish Kumar: That should be, yeah, this wide label.
135 00:14:21.430 ⇒ 00:14:24.179 Awaish Kumar: You have this org resolution here? Yeah.
136 00:14:24.180 ⇒ 00:14:25.460 Amber Lin: Sounds good.
137 00:14:25.670 ⇒ 00:14:26.630 Amber Lin: For the shop.
138 00:14:26.630 ⇒ 00:14:28.729 Awaish Kumar: grab this log. So it…
139 00:14:29.150 ⇒ 00:14:34.209 Awaish Kumar: for some of the sources, you might not have, so then you have to create a table, okay, let’s…
140 00:14:34.470 ⇒ 00:14:35.010 Awaish Kumar: do that.
141 00:14:35.010 ⇒ 00:14:39.770 Amber Lin: Okay, okay, sounds good. Is that all the models?
142 00:14:40.960 ⇒ 00:14:43.059 Awaish Kumar: Yeah, these are all the…
143 00:14:44.050 ⇒ 00:14:44.780 Amber Lin: Cool.
144 00:14:45.040 ⇒ 00:14:45.790 Awaish Kumar: Never one.
145 00:14:45.970 ⇒ 00:14:46.780 Awaish Kumar: Things we have.
146 00:14:46.780 ⇒ 00:14:47.420 Amber Lin: Yeah.
147 00:14:47.530 ⇒ 00:14:56.909 Amber Lin: Can you give me, like, a quick overview of the AI stuff there? I don’t think I’ve, like, touched it ever before.
148 00:14:57.670 ⇒ 00:14:59.549 Awaish Kumar: for the AI stuff,
149 00:14:59.550 ⇒ 00:15:04.850 Amber Lin: Yeah, you were mentioning these. Have you worked with it yet, or were you mostly just modeling?
150 00:15:05.480 ⇒ 00:15:13.329 Awaish Kumar: I have, I have a little bit of it, and then, like, I was kind of doing modeling and Otam trying to drive it, so…
151 00:15:15.270 ⇒ 00:15:20.380 Awaish Kumar: maybe, yeah, he did a lot more than me, but I have some experience.
152 00:15:21.780 ⇒ 00:15:27.339 Awaish Kumar: So this is what he has created. You can go into this AIML agents, and you can see
153 00:15:27.470 ⇒ 00:15:30.300 Awaish Kumar: what all agents put them created, for example.
154 00:15:30.480 ⇒ 00:15:31.060 Amber Lin: Okay.
155 00:15:31.060 ⇒ 00:15:34.859 Awaish Kumar: I don’t see anything, right? So there is no agent.
156 00:15:35.690 ⇒ 00:15:38.740 Awaish Kumar: Maybe you have to select the database.
157 00:15:44.570 ⇒ 00:15:45.920 Awaish Kumar: Thank you.
158 00:15:49.440 ⇒ 00:15:53.409 Awaish Kumar: Okay, so we need to figure out where… Khutam might have created.
159 00:15:53.880 ⇒ 00:16:00.559 Awaish Kumar: those agents, if it is in Broadmarts, or in Snowflake itself.
160 00:16:04.130 ⇒ 00:16:05.580 Awaish Kumar: Yeah, so…
161 00:16:06.030 ⇒ 00:16:18.499 Awaish Kumar: It should be… yeah, once you select it, select it. So, if Utam has created… Utham, obviously, I’ve created analysts, so it will be some… it should be somewhere here. I am… oh yeah, vertex Adoption, I don’t know.
162 00:16:19.500 ⇒ 00:16:22.320 Amber Lin: That’s okay. I’ll… I think I’ll meet with him later.
163 00:16:24.140 ⇒ 00:16:26.810 Awaish Kumar: Yeah, maybe I… if I change it to power admin.
164 00:16:31.240 ⇒ 00:16:37.530 Awaish Kumar: But this is where you can see analysts, agents, And then…
165 00:16:38.280 ⇒ 00:16:40.889 Awaish Kumar: then there is, like, Streamlata apps.
166 00:16:41.310 ⇒ 00:16:48.039 Awaish Kumar: that you create… using… the models. So, these are the apps.
167 00:16:48.040 ⇒ 00:16:49.289 Amber Lin: What are these?
168 00:16:50.440 ⇒ 00:16:54.190 Awaish Kumar: So, these, like, have you… are you familiar with Streamlit?
169 00:16:54.740 ⇒ 00:16:55.530 Amber Lin: Though…
170 00:16:55.780 ⇒ 00:17:00.059 Awaish Kumar: It is a Python package. Using that, you can create apps.
171 00:17:00.890 ⇒ 00:17:01.370 Amber Lin: Hmm.
172 00:17:01.370 ⇒ 00:17:06.879 Awaish Kumar: It has provided a way to basically host those apps in Snowflake.
173 00:17:07.190 ⇒ 00:17:08.650 Awaish Kumar: So that, that created…
174 00:17:09.170 ⇒ 00:17:19.679 Awaish Kumar: web pages, right? If you create locally, then you have to host it somewhere so that I can access it. But Snowflake has provided you that
175 00:17:20.180 ⇒ 00:17:21.780 Awaish Kumar: Hosting platform, kind of.
176 00:17:23.150 ⇒ 00:17:25.990 Awaish Kumar: Basically, these apps on top of this.
177 00:17:26.280 ⇒ 00:17:29.050 Awaish Kumar: Snowflake, platform.
178 00:17:29.290 ⇒ 00:17:30.660 Awaish Kumar: And then,
179 00:17:31.620 ⇒ 00:17:39.269 Awaish Kumar: Then we push it, like, you can create from UI, obviously, but then it’s really difficult to code it here.
180 00:17:39.520 ⇒ 00:17:48.089 Awaish Kumar: So what happens is Utam has created some guide… guidelines on, how you make changes. You can make changes using,
181 00:17:48.340 ⇒ 00:17:52.110 Awaish Kumar: cursor that, okay, make changes have…
182 00:17:52.440 ⇒ 00:18:00.660 Awaish Kumar: add more table, then it has created guides to how to deploy, so you can… You have to create from here?
183 00:18:01.480 ⇒ 00:18:04.719 Awaish Kumar: I think that’s the easiest part of…
184 00:18:05.500 ⇒ 00:18:08.899 Awaish Kumar: Then you can just reference that app, okay.
185 00:18:09.040 ⇒ 00:18:11.689 Amber Lin: Oh, okay, cool. Sounds good.
186 00:18:12.950 ⇒ 00:18:19.990 Awaish Kumar: These are, like, everybody’s creating apps here. These are apps by many, many different…
187 00:18:21.060 ⇒ 00:18:25.689 Awaish Kumar: people in the team. This is… we can look at this one. This is created by Autom.
188 00:18:28.320 ⇒ 00:18:33.540 Awaish Kumar: So, this is an app which… Basically, Shows you the…
189 00:18:33.690 ⇒ 00:18:37.530 Awaish Kumar: dashboard of, like, different charts, what we have in OmniFrame?
190 00:18:42.860 ⇒ 00:18:46.200 Awaish Kumar: I close this, okay, so it is just, like, different…
191 00:18:47.490 ⇒ 00:18:51.770 Awaish Kumar: Feedback, users, it’s failing for some reason.
192 00:18:51.950 ⇒ 00:18:55.680 Awaish Kumar: But this is the concept. These are all, kind of…
193 00:18:55.680 ⇒ 00:18:59.420 Amber Lin: So this is also, like, an app. Oh, okay.
194 00:18:59.650 ⇒ 00:19:03.040 Awaish Kumar: behind in the app, like, it’s a Python code that is running.
195 00:19:03.670 ⇒ 00:19:04.340 Awaish Kumar: Still with that.
196 00:19:04.340 ⇒ 00:19:07.270 Amber Lin: Microcode references are data.
197 00:19:07.590 ⇒ 00:19:11.140 Awaish Kumar: Yeah, yeah, that, obviously, that Python code
198 00:19:11.380 ⇒ 00:19:19.459 Awaish Kumar: you create Python code separately, like, based on your requirements, what you want to show? For example, you want to say, okay, for the remembers data.
199 00:19:19.810 ⇒ 00:19:25.790 Awaish Kumar: access my ProdMarts, and help me generate a chart which shows what users…
200 00:19:26.060 ⇒ 00:19:28.499 Awaish Kumar: Count the number of people who were
201 00:19:29.850 ⇒ 00:19:34.489 Awaish Kumar: count the Fortune 500 companies that were part of CS events, for example.
202 00:19:34.490 ⇒ 00:19:35.590 Amber Lin: Hmm, okay.
203 00:19:35.710 ⇒ 00:19:40.729 Awaish Kumar: And you will give that question… question to cons… cursor. Kursner might come up with some,
204 00:19:40.870 ⇒ 00:19:43.079 Awaish Kumar: chart based on that. So it… what.
205 00:19:43.080 ⇒ 00:19:44.380 Amber Lin: Oh, okay.
206 00:19:45.140 ⇒ 00:19:51.160 Amber Lin: kind of like, if we make a parallel to Omni, this is kind of the dashboards.
207 00:19:51.160 ⇒ 00:19:52.200 Awaish Kumar: Yeah, just…
208 00:19:52.200 ⇒ 00:19:54.980 Amber Lin: ask the AI chats, then.
209 00:19:56.750 ⇒ 00:19:58.000 Awaish Kumar: Sorry, what is the AI?
210 00:19:58.370 ⇒ 00:20:05.879 Amber Lin: I think I remember Utam said they will be asking AI questions, similar to Blobby, like, where would that be?
211 00:20:06.110 ⇒ 00:20:06.760 Awaish Kumar: This is…
212 00:20:06.760 ⇒ 00:20:08.790 Amber Lin: Oh, oh, okay.
213 00:20:11.380 ⇒ 00:20:11.830 Awaish Kumar: Is this…
214 00:20:11.830 ⇒ 00:20:16.929 Amber Lin: know which data set to look at, or is that part of what I’m gonna do?
215 00:20:17.570 ⇒ 00:20:23.610 Awaish Kumar: Oh, it has access to… It has… based on the…
216 00:20:23.980 ⇒ 00:20:36.269 Awaish Kumar: based on the role it has given, like Utham has made that configuration already, so based on the role it has access to ProdMarts, it can access to ProdMarts. But where to look? It’s like giving…
217 00:20:37.090 ⇒ 00:20:39.240 Awaish Kumar: Giving the context, right? It is…
218 00:20:39.240 ⇒ 00:20:40.260 Amber Lin: Mmm…
219 00:20:41.030 ⇒ 00:20:44.669 Awaish Kumar: It has to come from, Central, right?
220 00:20:46.870 ⇒ 00:20:47.540 Awaish Kumar: Cool.
221 00:20:47.540 ⇒ 00:20:48.320 Amber Lin: Okay.
222 00:20:48.320 ⇒ 00:20:56.309 Awaish Kumar: The context will see, for example, table scheme, like, you can provide table descriptions, you can provide column descriptions, right?
223 00:20:56.450 ⇒ 00:20:56.960 Awaish Kumar: Huh.
224 00:20:56.960 ⇒ 00:20:58.500 Amber Lin: Oh, wow, okay.
225 00:20:58.500 ⇒ 00:21:10.260 Awaish Kumar: It will get the context of what this field means, what this table means, what this data is about, and if there are any rules you will define there.
226 00:21:12.410 ⇒ 00:21:17.689 Awaish Kumar: You can chat. Based on your question and the context, it will come up with something.
227 00:21:18.100 ⇒ 00:21:18.980 Amber Lin: Okay.
228 00:21:18.980 ⇒ 00:21:19.950 Awaish Kumar: And secondly?
229 00:21:19.950 ⇒ 00:21:20.410 Amber Lin: Good.
230 00:21:20.410 ⇒ 00:21:22.240 Awaish Kumar: These are two different things here.
231 00:21:22.790 ⇒ 00:21:24.090 Amber Lin: Yeah, yeah, yeah, I know.
232 00:21:24.090 ⇒ 00:21:33.840 Awaish Kumar: I think you have to do work on maybe both of the things. They want people to chat about the data, but they also want to show dashboards, and also…
233 00:21:33.840 ⇒ 00:21:35.710 Amber Lin: Yeah, makes sense.
234 00:21:35.710 ⇒ 00:21:39.840 Awaish Kumar: They also want people to create their own dashboards, so it’s more like…
235 00:21:41.470 ⇒ 00:21:46.270 Amber Lin: Can Cortex create, like, these Streamlit apps?
236 00:21:46.780 ⇒ 00:21:52.560 Awaish Kumar: Just, like… Cortex can do that, Castle can also do that.
237 00:21:52.790 ⇒ 00:21:53.320 Awaish Kumar: Oh.
238 00:21:53.320 ⇒ 00:21:59.130 Amber Lin: Okay, gotcha. So their people would use Cortex if they ever want to make a dashboard.
239 00:21:59.130 ⇒ 00:22:00.150 Awaish Kumar: Yes, yes.
240 00:22:00.150 ⇒ 00:22:01.610 Amber Lin: Okay, okay.
241 00:22:01.610 ⇒ 00:22:10.910 Awaish Kumar: This is all coming from our app, our GitHub repo. In our GitHub repo, we have all these apps in there, we have their…
242 00:22:11.550 ⇒ 00:22:20.409 Awaish Kumar: if somebody doesn’t create… didn’t create it here, so it’s like, if you create it in the code, you push it to GitHub, right? And…
243 00:22:21.480 ⇒ 00:22:31.920 Awaish Kumar: But I think it’s not being deployed through GitHub, it is being deployed locally. So once you create with Amazon script, like, guide, how to deploy for Cursor, you can ask Cursor to deploy, it will deploy.
244 00:22:32.280 ⇒ 00:22:40.590 Amber Lin: Okay, sounds good. Yeah, I think this is great. I’ll take a look around, and I’ll ask him for, like, specific tasks I need to do.
245 00:22:44.000 ⇒ 00:22:50.909 Awaish Kumar: And then, one… yeah, you can ask Khazar how to deploy my Streamlit app, it will show you exactly.
246 00:22:52.160 ⇒ 00:22:58.820 Awaish Kumar: What else? And I don’t think there’s anything else here.
247 00:22:58.820 ⇒ 00:23:02.879 Amber Lin: That’s all. I’ll let Utam know what we looked at.
248 00:23:03.050 ⇒ 00:23:05.720 Awaish Kumar: Just have to get yourself familiar with the…
249 00:23:05.870 ⇒ 00:23:10.049 Awaish Kumar: with the roles, so you can ask us what the context is in the GitHub.
250 00:23:10.200 ⇒ 00:23:15.960 Awaish Kumar: Like, it’s a role chat, and should be using… You should have access to…
251 00:23:16.960 ⇒ 00:23:23.690 Awaish Kumar: role developer and role chat, and that’s… that’s all, and using that, you can create and steal it apps and… and push it.
252 00:23:23.690 ⇒ 00:23:24.320 Amber Lin: Okay.
253 00:23:24.320 ⇒ 00:23:25.020 Awaish Kumar: Okay.
254 00:23:25.020 ⇒ 00:23:26.170 Amber Lin: Sounds good.
255 00:23:26.980 ⇒ 00:23:27.770 Amber Lin: Cool.
256 00:23:28.760 ⇒ 00:23:33.829 Amber Lin: Okay, yeah, I’ll let Utam know that we met, and then I’ll ask him for assignments.
257 00:23:35.100 ⇒ 00:23:36.040 Awaish Kumar: Okay, sure.
258 00:23:36.040 ⇒ 00:23:36.960 Amber Lin: Alright.
259 00:23:38.140 ⇒ 00:23:41.469 Amber Lin: Yeah, thank you. I’ll talk to you later about Eden OS.
260 00:23:41.720 ⇒ 00:23:42.490 Awaish Kumar: Okay, okay.
261 00:23:42.490 ⇒ 00:23:43.790 Amber Lin: Alrighty, bye.