How this PM uses AI for PRDs, JIRA tickets, and replying to coworkers | Dennis Yang (Chime)

1. 0:00 – 3:00

   Introduction to Dennis Yang

   1. CVClaire Vo0:00

      We've seen so many people use tools like Cursor to write code. We actually haven't seen anybody yet just using Cursor to write, [chuckles] and that's what you're doing.

   2. DYDennis Yang0:10

      The reason why Cursor is my favorite UI for the AI is it has all the interfaces and interactions and connections into the tools that are critical for my daily product management.

   3. CVClaire Vo0:20

      I think we're at this really interesting place where, because these primitives are being built in the context of software engineering, you're getting these concepts of markdown, Git, commits, change tracking in these tools that used to be very software engineering-centric.

   4. DYDennis Yang0:36

      The most useful solutions will have interoperability as one of the key things. So any system that if it feels like it's locking that content or data away, I'm not gonna prefer to use that system. I don't care why you have these modes. I'm sure there's a good reason, but if that's my content, and I want all my systems to be able to access it when it needs to. It's really improving communication and reducing the time I'm spending writing status, and at the same time, improving the status content that is being circulated both up to leadership and across the organization. [upbeat music]

   5. CVClaire Vo1:06

      Welcome back to How I AI. I'm Claire Vo, product leader and AI obsessive, here on a mission to help you build better with these new tools. Today, we have a fun conversation with Dennis Yang, Principal Product Manager for Generative AI at Chime. Now, this one makes me sweat a little bit because I thought I was the alpha AI-powered PM, and Dennis shows me his workflows, which are way beyond anything I've seen before. He's gonna show you how to use Cursor to not only write your PRDs, but push them into Confluence or Notion, read comments, reply to comments, prototype AI tools, and more. This is a awesome one for anyone out there who's curious if you can make use of Cursor without writing code, and I think you're gonna learn a lot. Let's get to it. AI is supposed to make work easier, but I've been there: weeks of setup, endless back and forth with engineering, and yet another tool the team never really adopts. That's why I use Zapier's AI orchestration platform. It connects with nearly 8,000 apps, so I can finally put AI to work without the drama, without the delays, and without pulling engineering in every time I want to automate something. With Zapier, you can roll out AI-powered workflows that do real work across your whole company in days, not weeks. I use Zapier every single day. It automatically responds to leads with enriched, personalized data, it checks my calendar weekly and offers smarter ways to manage my time, and it even drafts emails for every new request that lands in my inbox. All of that running quietly in the background, so I can focus on the work that matters. And Zapier's built for scale. With enterprise-grade security, compliance, and governance, it's trusted by teams at Dropbox, Airbnb, Opendoor, and thousands more. Go to try.zapier.com/howiai to learn more about how Zapier can bring the power of AI orchestration to your entire

2. 3:00 – 4:53

   Why Cursor is ideal for product management workflows

   1. CVClaire Vo3:00

      org. Dennis, thanks for joining How I AI. I am really excited about this episode because we've seen so many people use tools like Cursor to write code, but we actually haven't seen anybody yet just using Cursor to write. [chuckles] And that's what you're doing, um, as, as a product manager and somebody who's thinking about strategy all the time. So before we dive in, why Cursor? Why writing? You're not writing a lick of code in here for at least this use case that we're gonna see. So how did you kind of get into this flow with this AI-powered IDE?

   2. DYDennis Yang3:37

      To me, Cursor... The reason why Cursor is my favorite UI for the AI is a few things. It has access to all of the models that I want to try. So, you know, in Cursor, you can talk to Claude, you can talk to GPT-5, you can do DeepSeek or whatever. Um, that's the first thing, and then the second thing is it has access to a file system, so it can write things down. Um, and then it can have access to Cursor Rules, which you, as you s- we're using more and more, you can start to tell it how you want to do things. And then the final big thing is interop. It actually works with all of the different tools that I need to work with, so that's through MCP. It can talk to Jira and Notion and Confluence, um, you know, look at Figma, all these things. So basically, not only does it have the AI, the UI for the AI, it has all the interfaces and interactions, um, and connections into the tools that are critical for my daily product management.

   3. CVClaire Vo4:29

      You know, and the other thing that I would say is running on the desktop is just fast. You know-

   4. DYDennis Yang4:34

      Yeah

   5. CVClaire Vo4:34

      ... it's, like, pretty fast at doing those things, as opposed to... You know, I think we're in this real moment where there's gonna be a question of, are we gonna start seeing more and more desktop apps for these AI-powered tools just because of the performance side of things compared to web? Web is very flexible.

   6. DYDennis Yang4:49

      Yep.

   7. CVClaire Vo4:49

      But I, I like Cursor 'cause it is, it's zippy.

3. 4:53 – 9:35

   Setting up Cursor for non-coding use cases with markdown preview

   1. DYDennis Yang4:53

      Yes.

   2. CVClaire Vo4:53

      So this is, this is your new hub for-

   3. DYDennis Yang4:57

      Yeah, this is-

   4. CVClaire Vo4:57

      - getting work done.

   5. DYDennis Yang4:58

      This is what my screen looks like. And that's-- The other thing I'm noticing is that I want bigger and bigger screens. [chuckles]

   6. CVClaire Vo5:03

      [chuckles]

   7. DYDennis Yang5:04

      Right? I'm running out of space 'cause I want my chat, right? I want my... the thing that, the artifact that I'm working on, and then I want the file system, and then over here, I actually have the... This is my, my settings pane, uh, docked to the bottom, 'cause you wanna make sure that it's still green, right? So I, I need more screen real estate, uh, and then... [chuckles]

   8. CVClaire Vo5:23

      Yeah, we had Lee from Cursor on recently-

   9. DYDennis Yang5:26

      Yeah

   10. CVClaire Vo5:26

       ... and he walked us through the three-pane kind of model of-

   11. DYDennis Yang5:29

       Mm-hmm

   12. CVClaire Vo5:30

       ... Cursor. For those who are listening and not watching, you have your file system on the left, where you're looking at what files you can work with or in context of Cursor. In the middle, you have your artifacts, whether those are code, um, code artifacts or content artifacts. On the right, you tend to have your chat.

   13. DYDennis Yang5:47

       Yep.

   14. CVClaire Vo5:48

       And then something I wanna call out for, for people is you also have this bottom pane you can pull up, and you non-

   15. DYDennis Yang5:55

       Yeah.

   16. CVClaire Vo5:55

       I was gonna say, me, as a developer, that pane for me is always the terminal.

   17. DYDennis Yang5:59

       Mm-hmm.

   18. CVClaire Vo6:00

       Uh, but this is a really nice little quality-of-life hack-

   19. DYDennis Yang6:03

       [chuckles]

   20. CVClaire Vo6:03

       ... that I'm gonna start to use. Your bottom pane in Cursor is actually the tools Cursor settings.

   21. DYDennis Yang6:10

       Yeah.

   22. CVClaire Vo6:10

       So you can turn on and off-... MCPs, which I actually do all the time and confirm that they're working.

   23. DYDennis Yang6:16

       Yeah, exactly. See, sometimes Cursor will be like, "I can't do that thing," and you look, and there's, like, a little red dot, and you gotta turn it back on, so.

   24. CVClaire Vo6:22

       Yeah. Well, you know what? Before we dive in, now that-

   25. DYDennis Yang6:24

       Yep

   26. CVClaire Vo6:24

       ... I'm curious and staring at your screen, would you mind sharing what- what MCPs just generally you have turned on? And then we'll go through the few that, you know, you, you really use on a daily basis, or at least in this workflow.

   27. DYDennis Yang6:38

       Sure. Sure. So I have MCP, and I have two, uh, that talk to Atlassian Suite. So one is our Jira direct MCP. This is before Atlassian launched their MCP, um, official server, uh, first-party server. This is, um, another one that I can just run locally. Notion, of course, it talks to my Notion. Figma, uh, talks to Figma, if you have Figma running, uh, and then GitHub talks directly. Uh, and then these two, uh, MCPs are... I'm actually gonna talk about them. I'll talk about News API, which is an MCP I wrote to talk to News API. It's just an API that searches, um, news articles. Um, and then Semrush is like an SEM, a search engine marketing MCP that I put together as well, um, using Cursor to write the MCP, and then you actually can use Cursor to install the MCP onto itself-

   28. CVClaire Vo7:23

       Okay

   29. DYDennis Yang7:23

       ... which I love, too. [chuckles]

   30. CVClaire Vo7:25

       AI all the way down-
4. 9:35 – 10:33

   Creating PRDs in Cursor and using source control for documentation

   1. CVClaire Vo9:35

      view. So, okay, we've done-

   2. DYDennis Yang9:36

      Right

   3. CVClaire Vo9:36

      ... we've done the setup. We've talked about extensions, cursors, your panes, your MCPs.

   4. DYDennis Yang9:41

      Mm-hmm.

   5. CVClaire Vo9:41

      Let's actually get into how you use Cursor as a hub for workflow, how you would achieve something as a product manager, sort of end to end-

   6. DYDennis Yang9:51

      Cool

   7. CVClaire Vo9:51

      ... using Cursor and these tools you've attached.

   8. DYDennis Yang9:54

      I think it's been well established that, uh, LLMs AI is really good for writing PRDs. So you should be doing your PRD creation in what, in whatever flow, um, that you want, you know, be it ChatGPT, or Claude, or, or ChatPRD, right? So, um, and for me, I actually do a lot of my writing, now that I have this, uh, Cursor setup, I, I do it directly in Cursor, and it's working on, you know, in Markdown, technically, and I can preview it here. But here at Chime, we actually... You know, it's not a single-player company. Um, and I think that's one thing that I really want to be pushing on here, is that the reason why you want to be interacting with all these other systems across, you know, not just your AI, is that there are other people usually in your company that you want to be working

5. 10:33 – 11:38

   Using MCPs to publish content to Confluence and Notion

   1. DYDennis Yang10:33

      with. So, um, we have a r- a ritual here at Chime, which is when PRDs are in early draft form, um, we'll share them out into our PRD drafts channel and then gather tons of comments. So I work inside Cursor. I'm making my PRD here. If it's in a, it's in an early stage, I don't want some comments, I'll throw it into the PRD draft channel. Um, I do use Git to control, to source control everything, but Git is not great [chuckles] for, uh, you know, the whole company to go into and make comments. So, um, I actually use the, um, the Confluence MCP to publish both into Notion and into Confluence. Um, because some people love using Notion, some people love using Confluence. Um, so then we have... Let's see here. So we have, here's this exact PRD pushed into, uh, Confluence. Um, I pushed it into this, uh, last night, and, and threw it into our, our comments channel, and already starting to get comments. [laughing]

6. 11:38 – 17:00

   Bridging the gap between engineering and product

   1. CVClaire Vo11:38

      Well, what I wanna, what I wanna call out really quickly before we go into-

   2. DYDennis Yang11:42

      Yeah

   3. CVClaire Vo11:42

      ... maybe how this, how this MCP actually works, because I think people just like to see it-

   4. DYDennis Yang11:46

      Mm-hmm

   5. CVClaire Vo11:46

      ... is, one, you know, we, we talked about using an IDE as basically your text editor, which is really interesting. You're not writing directly in Confluence or Google Docs or anything. You're writing in an IDE in Markdown-

   6. DYDennis Yang12:01

      Right

   7. CVClaire Vo12:01

      ... with a nice preview. The second thing you call out that I'm curious your thoughts on is Git and source control for-... non-code assets or-

   8. DYDennis Yang12:13

      Yep

   9. CVClaire Vo12:13

      ... non-explicitly code assets. I think we're at this really interesting place where, because these primitives are being built in the context of software engineering, you're getting these concepts of markdown, Git commits, like, change tracking in these tools that used to be very software engineering-centric.

   10. DYDennis Yang12:32

       Yes.

   11. CVClaire Vo12:33

       And I'm curious, just, like, let's take a minute as a, as as product people.

   12. DYDennis Yang12:37

       Mm-hmm.

   13. CVClaire Vo12:38

       Do you think we're gonna bridge that gap? Do you think there's gonna be like Git for... Well, maybe I should build it, but, like, Git for PMs, or do you think we're still a little- it, like, the abstraction is too high, um, for it to be useful, and you need some of that UX polish that you're seeing in some of these more classic productivity tools?

   14. DYDennis Yang12:56

       I have a lot of thoughts about this.

   15. CVClaire Vo12:57

       Yeah.

   16. DYDennis Yang12:57

       Um, so as we're sort of creating these artifacts that inform the product that we're building, traditionally today, these artifacts sit outside of the code base.

   17. CVClaire Vo13:07

       Yeah.

   18. DYDennis Yang13:07

       Right? So this PRD is sitting inside Confluence right here. Um, but now what I'm realizing is since I'm using Cursor and, and using Git to source control this artifact, it's actually now sitting inside this artifacts directory.

   19. CVClaire Vo13:23

       Yep.

   20. DYDennis Yang13:23

       And what I'm wondering is that if... I think I wanna start to see if the artifacts are actually sitting inside the repo into which the code is being developed, that adjacency actually encourages the engineers and the AI coding assistant-

   21. CVClaire Vo13:41

       Yep

   22. DYDennis Yang13:41

       ... to continually have access to this. They don't- you don't have to give it an MCP to Confluence. This is the source of truth, um, so it can read it. And when things happen, so PRDs are typically a snapshot in time of, "This is what we thought the thing should be at this moment." Um, in development, we constantly learn and iterate and learn and iterate, um, but rarely do we go back to the PRD to edit it. So what if I put a cursor rule in that says, "Hey, if I'm working on this feature and it- and I'm learning things about the feature as I'm working on it, remember to update the PRD with the latest of how you're thinking about this?"

   23. CVClaire Vo14:18

       That's, that's how the ChatPRD repo works.

   24. DYDennis Yang14:21

       Yep.

   25. CVClaire Vo14:21

       So we have-

   26. DYDennis Yang14:22

       Amazing

   27. CVClaire Vo14:22

       ... we have a, we have a docs-

   28. DYDennis Yang14:24

       Yeah

   29. CVClaire Vo14:24

       ... um, directory inside our sort of like repo for ChatPRD. It has a combination of product documentation and engineering documentation listed there. Um, even to-dos, like, we've even pulled some of the, like, just task tracking [chuckles] into, into the repo-

   30. DYDennis Yang14:41

       Yep
7. 17:00 – 21:37

   Reading and responding to document comments with AI assistance

   1. DYDennis Yang17:00

      so-

   2. CVClaire Vo17:00

      Let's get back to the workflow.

   3. DYDennis Yang17:02

      Yeah.

   4. CVClaire Vo17:02

      So you're making your PRDs in Cursor. You use the MCP, and it would be just really helpful for people, you know, who haven't used an MCP before-

   5. DYDennis Yang17:10

      Mm-hmm

   6. CVClaire Vo17:10

      ... just to show how simple it is to do something like this. So let's say you wanted to push this PRD into Notion or into Confluence-

   7. DYDennis Yang17:18

      Mm-hmm

   8. CVClaire Vo17:18

      ... can you show us how that, how that works for people who's never seen it before?

   9. DYDennis Yang17:22

      Right. So this looks like this PRD looks great. Actually, by this, I need to tell it, right?

   10. CVClaire Vo17:26

       Oh, look at that exclamation mark.

   11. DYDennis Yang17:27

       I know.

   12. CVClaire Vo17:27

       You're so polite. [chuckles]

   13. DYDennis Yang17:28

       I know. So let's publish, um, it into Confluence. Uh, and I already pu- pushed it, so I'm gonna tell it to [chuckles]

   14. CVClaire Vo17:39

       Yeah

   15. DYDennis Yang17:40

       ... don't overwrite the other one. We already pushed. Make a copy, please, and, um, I'm demoing this capability. All right, so we're demonstrating this capability. So this is basically all, it's easy. So you're always gonna, always wanna look to see that your MCP server is green, it's planning, it's planning its moves out, and then basically, just this is it. Like, it's just running. Um, it knows all of its tools. One thing, if you haven't seen how MCPs are set up-... if you click on Tools Enabled, you can, you can mouse over each one of these, and you can get an understanding for how each of these tools works or what they do. Um, and for me, just when I show people the MCP descriptions here, you start to form a mental model on what tools you've given your AI-

   16. CVClaire Vo18:35

       Yeah

   17. DYDennis Yang18:35

       -and what it could do, so-

   18. CVClaire Vo18:36

       And, and how to ask for it. And so the other thing is not only how to ask for things from your MCP, so really understanding the naming of the tools, but the other thing is to look across your tools. And I'll tell you all, a little painful-

   19. DYDennis Yang18:49

       Yeah

   20. CVClaire Vo18:49

       ... um, issue that I ran into is: a lot of SaaS projects h- or SaaS products have things called projects or files or docs, and when I say, "Update the project," it's like, do you want me to update the Confluence space? Do you want me to update the ChatPRD project? And so I think this ability to toggle on and off tools in the context of what you're working, helps it just narrow in on what task you wanna do. So a little lesson learned from Claire, and, um, named, poorly named, maybe not-- inspecifically named MCPs.

   21. DYDennis Yang19:20

       Exactly. The current MCP server seems to be having issues. [laughing]

   22. CVClaire Vo19:24

       [laughing] This is what we get for doing it live.

   23. DYDennis Yang19:27

       Yeah.

   24. CVClaire Vo19:27

       Well, and, and here's, here's the thing that you all, you know, here's the learning. How I AI. A couple things: I think MCPs are really opaque to people who-

   25. DYDennis Yang19:36

       Yes

   26. CVClaire Vo19:36

       ... have not set up their first one. To set one up, you're usually given, at least on a hosted MCP, a URL. You paste a couple lines of config into Cursor or whatever your client is. It'll, like, boop you to log into the app, just like you would sort of OAuth another app or put in an API token, and then that should give you access to it, and then you do exactly what we're watching Dennis do right now. Um, if you all wanna know the state of this highly stable technology and platform, which is you toggle this button on and off over and over again-

   27. DYDennis Yang20:05

       [chuckles]

   28. CVClaire Vo20:05

       ... till it turns green.

   29. DYDennis Yang20:06

       Till it turns green.

   30. CVClaire Vo20:07

       So we're gonna give you the benefit of the doubt-
8. 21:37 – 25:51

   Creating comprehensive Jira tickets directly from PRDs

   1. CVClaire Vo21:37

      nice flow. So other than kind of creating PRDs and pushing them-

   2. DYDennis Yang21:42

      Yes

   3. CVClaire Vo21:42

      ... into Notion and/or Confluence, and how, how product managery of you that they have to go both places? [laughing]

   4. DYDennis Yang21:51

      [chuckles] They're both great tools.

   5. CVClaire Vo21:52

      Which I find very funny.

   6. DYDennis Yang21:53

      Yeah, um-

   7. CVClaire Vo21:53

      Uh, yeah, what else are you doing with, with these MCPs in terms of, like, project management, project workflow, collaboration?

   8. DYDennis Yang22:00

      You know, we love to share our PRDs across, um, the company to see what comments. Uh, this is the thread where I'm now gathering, like I said, looks, looks like people have been commenting on the PRD. Please go through the comment one by one, and let's see how we'll respond. So what, what the MCP actually does is it reads the PRD. It sees the exact comments. So, I mean, I, I could use my own eyes and read the comments myself and respond to them here in Confluence, but that's no fun. Um, so we'll have Cursor read the comments, and then it actually does a breakdown, and this is, this I found quite hilarious. Um, it, it organized the comments into high priority, medium priority, and then, um, other different types of clarifications, and then actually wrote suggested responses, um, m- a lot of which sounded decent. So I started saying like, "Yep, that one's okay. Um, you can respond to that one." And since the MCP is authenticated as Dennis, as me, it appears to my other product managers at Chime that-

   9. CVClaire Vo22:59

      [chuckles]

   10. DYDennis Yang22:59

       ... I am responding, um-

   11. CVClaire Vo23:04

       To, to their comments

   12. DYDennis Yang23:04

       ... in this way.

   13. CVClaire Vo23:05

       Okay.

   14. DYDennis Yang23:05

       To their comments, yeah.

   15. CVClaire Vo23:06

       Okay, so this is, this is true behind-the-veil, behind-the-veil [chuckles] stuff. I have not seen this before, and this is spoken from somebody who has thought a lot about AI-generated PRDs. So just to clarify for people who are not [chuckles] watching-

   16. DYDennis Yang23:20

       [chuckles]

   17. CVClaire Vo23:20

       ... Dennis, Dennis writes his PRDs in AI, and he pushes them into Notion or to Confluence with AI.

   18. DYDennis Yang23:28

       Yes.

   19. CVClaire Vo23:28

       He then waits a little bit, reads the comments with AI, AI [chuckles] generates comments back-

   20. DYDennis Yang23:35

       Right

   21. CVClaire Vo23:35

       ... and you review them, and you either approve or not, and then they get posted-

   22. DYDennis Yang23:41

       They're back

   23. CVClaire Vo23:41

       ... as you.

   24. DYDennis Yang23:43

       Right. So here's-

   25. CVClaire Vo23:44

       I love this.

   26. DYDennis Yang23:45

       [chuckles]

   27. CVClaire Vo23:45

       I love it!

   28. DYDennis Yang23:46

       Yes, that's exactly the flow. Um, and I am, I'm in the loop, right? Like, one of the key things about building with AI is that you want to insert the human at the appropriate point, um, where they make a lot... They're, they're adding the most value, right? So gathering the comments, that's not value add, but reading them and understanding them and responding, like, I can provide perspective there, um.

   29. CVClaire Vo24:09

       Yeah.

   30. DYDennis Yang24:10

       Yeah.
9. 25:51 – 30:23

   Generating automated status reports from Jira data

   1. DYDennis Yang25:52

      All right, so what's next after you're gathering comments, your PRD's great, your, all of, all of your compatriots are loving the PRD that you've created and commented on? Um, typically, the next step in our workflow is to ticket this out into Jira-

   2. CVClaire Vo26:04

      Mm-hmm

   3. DYDennis Yang26:04

      ... right? So, uh, read the PRD and create an epic in the TIA project.

   4. CVClaire Vo26:15

      Mm-hmm.

   5. DYDennis Yang26:17

      So I created a, a, a task automation is our Jira project that we're gonna be using.

   6. CVClaire Vo26:22

      Yep.

   7. DYDennis Yang26:22

      I'm gonna make sure this is green, and then we'll watch it work now again. So what I really like about this is that when I'm doing this, right, it's reading the PRDs. I don't know what all of my other fellow product managers are like, but when Dennis creates tickets in Jira, there's... I could probably do a better job. [laughing] But when Dennis's Cursor creates the tickets, Cursor, Dennis's Cursor reads the PRD that I've spent a lot of time doing, and then splits the effective tickets. The story tickets in particular are very, very well described.

   8. CVClaire Vo26:54

      Yeah.

   9. DYDennis Yang26:55

      So I, I love doing this style of ticket creation because it really, it does what you wish you could do if you had infinite amounts of time. It's your words, it's your PRD, it's your stories, and it's putting them where they should, they should go, which is in the ac- actual story tickets that then go to the engineers. Um, and then they can, you know, you can always just say, "Read the PRD," but-

   10. CVClaire Vo27:16

       Yeah

   11. DYDennis Yang27:16

       ... they have to read the whole PRD. So let's create story tickets. Let's get this ready when it's ready. That are all... Let's create story tickets that are all associated with the parent epic for this feature. And again, this, this is sort of a conversational flow. Um, I've, I've in my, in my personal Cursor for product management, uh, Cursor roles, I'll say things like, "Remember to always associate story tickets with their parent epic."

   12. CVClaire Vo27:47

       Yep.

   13. DYDennis Yang27:47

       Um, I did notice that when I was doing this at first and I didn't say associate it, then it would just create orphaned tickets.

   14. CVClaire Vo27:53

       Yeah, orphaned tickets.

   15. DYDennis Yang27:54

       [chuckles]

   16. CVClaire Vo27:54

       Yep.

   17. DYDennis Yang27:54

       Without association. So this is the flow, right? It's, it's handling a lot of the busywork, right, of that I don't get a lot of value from doing.

   18. CVClaire Vo28:05

       Well, and I wanna go back to what you were saying, which is, this is, this is one of those tasks I say that is such a toil reducer for product managers, where you really hit cognitive fatigue on translating the same content for different audiences. And, like, PMs out there, we feel you. We know what you do. You take your customer notes, and you turn them into a PRD, and then your engineers don't wanna read the PRD, so you make a one-pager, and then the one-pager has to turn into an email for your boss, and the email for your boss needs to be three bullet points for your CEO. And, like, you just do all this translation [chuckles] , and then you get to, like, JIRA tickets or support documentation, and you're like: I can no longer do a good job here. I have reached the limit of my cognitive interest in this task. And so you get lazy, and you, like, kinda like do the, the epic name and the ticket names, and then you say, "Link to PRD" in the, in the description, and you push that cognitive load on another person in your team. And so I think one of these tasks that are kind of, like, administrative, low, um, [lips smack] you know, low incremental value is a really good thing to offload something to ch- or, you know, to, to Claude or AI with.

   19. DYDennis Yang29:25

       Completely. Um, a lot of this, like, housekeeping-

   20. CVClaire Vo29:29

       Mm-hmm

   21. DYDennis Yang29:29

       ... rigmarole, like, these tools are so good at. Um, and then what's-- as you're saying this, like, what's another thing that product managers constantly do, which is that same SXX shape? We update status. Um, so how might I use Cursor to update status? So here's, here's, here's that epic. Um, let's pretend I'm one of the engineers, and I pick up one of these tickets, and comment, and look at the, and look at the ticket. It has-

   22. CVClaire Vo29:59

       I know, it's... They're done well. [chuckles]

   23. DYDennis Yang30:00

       Has story, it has Gherkin, it has acceptance criteria. Man, like...

   24. CVClaire Vo30:04

       I built an agent or two that does this in a couple other platforms than, than Jira, and it's just like-

   25. DYDennis Yang30:09

       [chuckles]

   26. CVClaire Vo30:09

       ... everybody's like, "Ugh, I got a good ticket. I got definition of done. It's organized."

   27. DYDennis Yang30:15

       Right. Um-

   28. CVClaire Vo30:15

       So this is a better job than I would do, I'll tell you that.

   29. DYDennis Yang30:18

       I mean, this is... Cursor is a much better product manager than I ever was, so....

10. 30:23 – 35:03

    Building a morning briefing system with ChatGPT

    1. DYDennis Yang30:23

       and now we're gonna make it done, right? So we're gonna do some, a few tickets in here. Uh, again, once again, what is a status report other than using a tool-

    2. CVClaire Vo30:32

       Yeah

    3. DYDennis Yang30:32

       ... and doing a job? So let's, once again, it's time for status reporting. Let's write a status report and describe everything that has happened since nine twenty-four or for this epic. Give it this epic here. And what it'll do is it will look at-- it'll write JQL and essentially write a status report, right? And I've been doing this for about almost two months now, [chuckles] where every week, my weekly status report, I have a, I have a very long cursor rule now, um, that I'm able to do this sort of repeatedly. Um, 'cause one thing that you'll notice is, since I didn't give it what a status report was, it's gonna just figure it out. This is like a z- a zero, zero context, uh, status report request. Uh, and you likely will have, uh, have some ideas as to what you want from your status report. Um, so the recommendation here is you do it interactively first, and then at the end of this, end of this whole process, you would review the work and then give it feedback to do it better, and then you would save that into a cursor rule of, "This is my weekly status report," right? And what we learned when we started doing this on a weekly basis is that since the source of truth was in Jira, like, my engineers started commenting more in Jira about what was happening, 'cause they knew that someone was looking at it. [chuckles] Right? Um, and, and those words and, and that context was being added to the tickets, and even if you don't, even if you have a Jira ticket that simply goes from in progress to done and only has a ticket title and nothing in description, that's actually sufficient context to say that this thing went from this to done, right? Um, so it's really improving, like, communication. It's... I'm, I'm reducing, I'm reducing the time I'm spending writing status and, at the same time, improving the status content that is being circulated both up to leadership and, you know, across the organization.

    4. CVClaire Vo32:47

       Well, and I've been, I've been to, to your office, so I know you all have lovely and lots of nice time together, but I also wanna call out for anybody who's working in the hybrid or remote environment, one of the biggest taxes on organizations is synchronous communication, where, like, a PM is pinging an EM or an engineer, being like: "What's the update here?" And, um, and sort of like allowing those updates to go into a source of truth and then be queried in a really natural language way. Again, you don't have to ch-change your behavior as a PM. You can still ask, "What's the update here? What's the status?" [chuckles] Your life is better, but the source of that data is more structured, can be more asynchronous, I think allows people to, like, do less context switching, less synchronous, you know, communication, all those things that just give us more time to create. So I think that's a really interesting secondary effect of, of what you're showing here.

    5. DYDennis Yang33:42

       Definitely. And, you know, even if you're doing an in-person or over Zoom kind of status update, again, we have all these tools, you know, to record, transcribe, document, and put all of this content back into where it should go, like hang it off of the Jira ticket, and then it's all organized, um-

    6. CVClaire Vo33:59

       Well-

    7. DYDennis Yang34:00

       -for AI. Yeah.

    8. CVClaire Vo34:01

       And now you've given me, like... Maybe this is, like, a chaotic good idea, but I was like: "Oh, you know, as a PM, you really gotta get people to like you." Like, this is- [chuckles] it's one of these things. Pro tip, PM's gotta be likable. And I'm like, oh, man, you could use the cursor and, or the, not the Cursor MCP, the Atlassian MCP, to, like, put nice comments on Jira tickets that are done.

    9. DYDennis Yang34:22

       Right? Like, thank you. I mean-

    10. CVClaire Vo34:23

        Thank you!

    11. DYDennis Yang34:23

        I do a lot of, I do a lot of-

    12. CVClaire Vo34:24

        All of me

    13. DYDennis Yang34:24

        ... thank you emojis, um-

    14. CVClaire Vo34:26

        Yeah

    15. DYDennis Yang34:27

        ... right? It's the fabric of culture that we have to establish across.

    16. CVClaire Vo34:30

        Yeah, it's the fabric of culture and also just powered by a commercial lo- large language model. [chuckles]

    17. DYDennis Yang34:36

        Yeah.

    18. CVClaire Vo34:37

        This is where, this is where we're at. I, I love this.

    19. DYDennis Yang34:39

        [chuckles]

    20. CVClaire Vo34:39

        I think this is a really ex- interesting example, 'cause again, it doesn't matter what the content of what you're working on-

    21. DYDennis Yang34:45

        Yes

    22. CVClaire Vo34:45

        ... is. I think everybody can take away, "I can write an asset, I can push it to the right sources, I can query the comments, I can query the feedback, I can translate that for my team in whatever format they need, and I can get aggregate insights and updates." This is awesome. Awesome flow has given me a lot of ideas that I am going

11. 35:03 – 40:04

    Generating personal morning briefings using ChatGPT

    1. CVClaire Vo35:03

       to take. So we have one more quick, kind of like a little bit more personal workflow-

    2. DYDennis Yang35:07

       Yeah

    3. CVClaire Vo35:07

       ... that you were gonna show us. So let's bop over to that and see how you start your morning. Everything's a morning briefing with you, I guess.

    4. DYDennis Yang35:14

       Yeah, exactly. This, this is what-- this is how I, um... So how do I start my day? Um, one, one kind of fun thing that I like to start everyone, um, with when I'm talking to them about ChatGPT is you go into ChatGPT, and all you say is, "Write me a morning briefing based on what you know about me." And ChatGPT, ChatGPT has added, um, fantastic, um, memory, um, to, to its system, such that its morning briefing is actually pretty decent. Um, so how I begin my morning is with, with the, uh, with ChatGPT, every morning, it essentially compiles for me what it thinks I'm gonna be interesting- interested in. And I've been doing this for a long time, uh, and every morning at around five AM, it automa- automatically creates this morning briefing for me based on what it knows about me. Um, so you can see here, we had an earthquake. Uh, these, [chuckles] the national stories. Uh, and what I did notice is after a while, it's starting to actually starting to lose the plot. Um, so I need to, instead of informing it by just memory, I'm thinking now I need to give it more context, um, and specifics of what I want. So this, this to me is actually, it's informative-... in understanding that even OpenAI is not perfect at figuring out what memory context is relevant for a very, very small, you know, request, like morning briefing. But one of the key things that I really tell everyone in, in terms of how do, how do we, how do we learn how to use AI? You have to use it in this way, and you can kind of understand and get a gut feel for how it, how it does a bad job sometimes. Um, it really helps you understand, um, how to make better AI products.

    5. CVClaire Vo36:56

       And is this a, is this a custom GPT? Do you just literally write, "morning briefing," is it just a long-standing chat? What is it?

    6. DYDennis Yang37:04

       This is a, this is a ChatGPT project-

    7. CVClaire Vo37:06

       Okay

    8. DYDennis Yang37:07

       ... uh, into which I've placed-- I've given it no help.

    9. CVClaire Vo37:10

       Oh, okay.

    10. DYDennis Yang37:11

        Um, I, I have not told it anything around, like, what it should be doing-

    11. CVClaire Vo37:15

        Yep

    12. DYDennis Yang37:15

        ... or even given it files, um, because I'm actually trying to see how it does with only the, the previous threads-

    13. CVClaire Vo37:22

        Yep

    14. DYDennis Yang37:22

        ... that we've been doing.

    15. CVClaire Vo37:23

        Yep.

    16. DYDennis Yang37:23

        Yeah.

    17. CVClaire Vo37:24

        Interesting. And then you just say, "morning briefing," and it goes.

    18. DYDennis Yang37:27

        Yep. It used to do a fantastic job. I would say, uh, [clears throat] about a month ago, it, it did a great job every morning. It, it's feeling like either it's losing the plot, and this project is getting too big or some sort of model changes. I'm not really sure.

    19. CVClaire Vo37:42

        Yeah.

    20. DYDennis Yang37:42

        But mm.

    21. CVClaire Vo37:42

        Oh, no, that's a-- those are bullet points, so.

    22. DYDennis Yang37:44

        Yeah, these are-

    23. CVClaire Vo37:45

        That's, that's GPT-5 right there.

    24. DYDennis Yang37:47

        Yeah.

    25. CVClaire Vo37:48

        My boy.

    26. DYDennis Yang37:48

        But I do like how, you know, they're bringing those little screenshots in, which is nice.

    27. CVClaire Vo37:51

        Yeah.

    28. DYDennis Yang37:51

        Um, but this is like, "No, there's no AI news anymore," and like, where, where'd my AI news go?

    29. CVClaire Vo37:56

        Maybe the takeaway for folks here is, you know, if you're trying to get into AI, I think for two reasons. One, if you're trying to get into AI for personal productivity reasons, find a daily use case. It's, like, really simple, consistent, adds little value in your life, just because it'll add a little value in your life. I think the second-order effect of that, though, as somebody who's thinking about AI, is it's a really sort of natural, repetitive way to learn about the strength, weaknesses, evolution, skill sets of these core models on which almost every product, you know, for the next couple of years is gonna be built. And so you can start to form your own intuition as a product person of, okay, like, why is memory failing here? Why is context failing here? Where do instructions really help? Is my two-word prompt, which I have to call you out on, that just says, "morning briefing," like, is that sufficient? [chuckles] Um, I'm coming in, and I'm typing this in every morning. I should probably test the, like, schedule, repeated task thing. And so, again, I just think, get in there and find something that every day you're gonna find useful so that you're getting used to these tools, and you're really understanding what their capabilities are, and then if you become somebody who's gonna build these tools, you're a little bit ahead. You have more language about what makes a good user experience with AI.

    30. DYDennis Yang39:11

        Exactly. If you're not using it every single day, you will not notice-
12. 40:04 – 46:37

    The “super MVP” approach to AI product development

    1. CVClaire Vo40:04

       All right, so you showed us how you can just create this and kinda, like, prototype this morning briefing in ChatGPT, but I know you. You're an AI PM. You wanna build this thing. And I love the way you prototype your actual AI products and agentic products in Cursor. So let's whip back to Cursor, and I wanna, I wanna see how you would actually go about, as a PM, building that kind of product and prototyping it and testing it in Cursor in a really lightweight way.

    2. DYDennis Yang40:36

       That's a great... L- I love this question because I always tell people, "You should be prototyping all of your AI product ideas inside ChatGPT first," right? You should just try it, which that, that effectively was my morning briefing prototype, was ChatGPT, and now I use Cursor itself to continue to prototype in what I call typically a super MVP, super minimal, and the reason why it's super minimal is because I'm using Cursor itself, which is AI, to prototype the AI product that I'm about to build. Does, does that make sense, sort of like-

    3. CVClaire Vo41:11

       Yeah, yeah, yeah.

    4. DYDennis Yang41:12

       Okay.

    5. CVClaire Vo41:12

       Yeah, because Cursor has access to all these models.

    6. DYDennis Yang41:14

       Right.

    7. CVClaire Vo41:15

       So-

    8. DYDennis Yang41:15

       Okay

    9. CVClaire Vo41:15

       ... you don't have to set up too much to at least get the baseline sort of access.

    10. DYDennis Yang41:20

        So how, so how do we do this? So we have our PRD that we just wrote. Here's the problem. Here's some solutions. I have it write a TDD for itself. Here's my TDD. For super, I say, "You're gonna be a super MVP. You, Cursor, are going to help me prototype and under- and understand how to do this."

    11. CVClaire Vo41:38

        And-

    12. DYDennis Yang41:39

        And-

    13. CVClaire Vo41:39

        ... and just for folks that don't live in three-letter PM word, TDD is a-

    14. DYDennis Yang41:42

        Sorry

    15. CVClaire Vo41:42

        ... technical design document.

    16. DYDennis Yang41:43

        Yes. So Cursor itself will write a, an approach, a technical design document to prototype this product that I'm trying to build using AI, which is a morning briefing system. So what the super MVP instructions now are is it's going to create instructions, and this is what we're looking at now, for Cursor to do the task that I want it to do. In this case, you can see here, step one, load the configuration. Step two, read... We have the profiles about what news to look for. Step three, use the MCP news search tool to search for news, and then, uh, process the content, summarize it, and create a report.

    17. CVClaire Vo42:27

        Yep.

    18. DYDennis Yang42:27

        So this is effectively what some are calling prompt engineering, but instructions for the AI to do the job.

    19. CVClaire Vo42:33

        Yep.

    20. DYDennis Yang42:34

        That looks all great. Now I can just say-... at Super MVP agent instructions, run today's briefing.

    21. CVClaire Vo42:45

        Yeah.

    22. DYDennis Yang42:47

        Go. Make sure my MCP is still green while this is running. Looks good. [laughing] Um, and there it goes, right? So basically, it's creating this report that I just defined in our PRD, allowing me to prototype it. It's making... I love, I love their new to-do function, by the way.

    23. CVClaire Vo43:04

        Oh, me too. Love it.

    24. DYDennis Yang43:06

        Um, if you notice here, this is, uh, it's running date. A- amusingly, sometimes Cursor doesn't know what date or time it is, and it will argue with you, um, about what date it is. [laughing]

    25. CVClaire Vo43:17

        [laughing]

    26. DYDennis Yang43:18

        So I told it, um, "Make sure to run, like, the terminal date command-

    27. CVClaire Vo43:22

        Yep

    28. DYDennis Yang43:23

        ... um, so that you can check what date it is." And this effectively is doing the whole job right now of going to the news MCP, gathering news that I'm interested in. It's gonna read the output and then generate the report. And right now, this, I'm using Cloud for Asana.

    29. CVClaire Vo43:39

        Mm.

    30. DYDennis Yang43:39

        The amazing thing about this is I can use these same exact instructions-
13. 46:37 – 50:07

    Lightning round and final thoughts

    1. CVClaire Vo46:37

       Ah, love it. Very good. Bravo, my friend. Okay-

    2. DYDennis Yang46:42

       All right

    3. CVClaire Vo46:42

       ... Dennis, this was so fun. I have so many ideas, um, [chuckles] AI all the way, all the way down. I have, I have a couple lightning-round questions for you, and then we'll get you out of here.

    4. DYDennis Yang46:51

       Okay.

    5. CVClaire Vo46:51

       One, do your colleagues know that you're replying to their comments with AI?

    6. DYDennis Yang46:57

       [chuckles]

    7. CVClaire Vo46:57

       Or is this the sp- spoiler alert?

    8. DYDennis Yang46:59

       No, I, I don't, I-

    9. CVClaire Vo47:00

       Hello, hello, PMs.

    10. DYDennis Yang47:02

        One hundred percent, I think they all know. I think, um, the one, the one single benefit of us being returned to office in person is that before that, I don't think people believed that I was actually a real human. So-

    11. CVClaire Vo47:15

        [laughing]

    12. DYDennis Yang47:15

        ... um, they all know, uh, you know, that I'm, I'm fully AI-enabled. Um-

    13. CVClaire Vo47:21

        Perfect. I love it.

    14. DYDennis Yang47:23

        Yeah.

    15. CVClaire Vo47:23

        Um, okay, my, my second use case is, or my second question for you is: how, how would you recommend a PM, um, get started with Cursor? Are you just, like, literally opening up a Cursor and saying, "Hey, this is gonna be a, a directory for product documents, um, and artifacts. There's gonna be no code here. Set it up." Like, what's your zero to one quick, quick start?

    16. DYDennis Yang47:48

        Yeah, my, my zero to one quick start is basically you, you open it up, and you make a, a brand-new directory just called-

    17. CVClaire Vo47:55

        Mm-hmm

    18. DYDennis Yang47:55

        ... like, blank or-

    19. CVClaire Vo47:57

        Uh-huh

    20. DYDennis Yang47:57

        ... in that case, and then you just start talking to it, 'cause soon, as soon as you do that, you'll have a chat pane, right? So, uh, and then you can start learning, um, how this actually works.

    21. CVClaire Vo48:07

        Amazing. Okay, and then my last question, my favorite one, um, you're so pol... I, you're so polite to your, to your AI, so I know this will be a good answer, but when, for example, you're toggling on and off this MCP, or it's calling the wrong tool, or it's overriding your, um, epic tasks with the wrong thing, what is your prompting technique? What's your go-to?

    22. DYDennis Yang48:30

        I think most people that know me know me to be a very kind, nice person. I, I don't, I'm not a yeller at... I don't yell at the AI. Um, I say a lot of please. I say, like, as you noticed, I use a lot of exclamation points. Um, and sometimes I just kind of start the thread all over and just like, "All right, let's just start new," right? Completely, uh, time travel back in time and be like, "Let's, let's start over. Maybe you need a break."

    23. CVClaire Vo48:55

        Oh, that response has just, like, soothed my inner child. So I love to hear it, very calm, very positive, very kind, and just walk away when you need to. That's a wise response. Okay, Dennis, this has been so great. Where can we find you, and how can we be helpful?

    24. DYDennis Yang49:12

        Um, you can find me, I'm online typically as sind, uh, Dennis backwards, on Twitter, X, uh, and then LinkedIn, you can find me there. I'm just Den- Dennis Yang. Uh, and I'll be speaking at the Fintech NerdCon conference in November. Um, trying to gather as many AI-enabled people there, so come and, come and join me there.

    25. CVClaire Vo49:32

        Amazing. Well, thanks for being here. Really appreciate you walking us through this.

    26. DYDennis Yang49:36

        Thanks for having me. This was fun. [upbeat music]

    27. CVClaire Vo49:39

        Thanks so much for watching. If you enjoyed the show, please like and subscribe here on YouTube, or even better, leave us a comment with your thoughts. You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show. You can see all our episodes and learn more about the show at howiaipod.com. See you next time! [upbeat music]

Episode duration: 50:07