How Amplitude built an internal AI tool that the whole company’s obsessed with (and how you can too) | Wade Chambers

Summary

Podcast Summary: How I AI - "How Amplitude Built an Internal AI Tool That the Whole Company’s Obsessed With (and How You Can Too)" featuring Wade Chambers

---

Introduction

In the August 11, 2025 episode of How I AI, host Claire Vo welcomes Wade Chambers, Chief Engineering Officer at Amplitude. The episode delves into how Amplitude developed an internal AI tool named Moda that swiftly became integral to the entire company. Wade shares insights into the decision-making process behind building the tool in-house, its implementation, and the profound impact it has had on the organization.

---

1. Build vs. Buy: The Decision to Develop Moda Internally

Wade Chambers discusses the strategic choice Amplitude made to build their own AI tool rather than purchasing existing solutions. This decision was influenced by the desire to leverage internal data more effectively and customize functionalities to better fit the company's unique needs.

• Efficiency and Speed: Wade emphasizes that developing Moda internally was faster and required less time investment than anticipated. "It didn't take us as long to do it and it's in spare time, people's spare time... probably like three to four weeks spare time of some pretty talented engineers" ([03:22]).

• Leverage and Customization: By building Moda, Amplitude could integrate various APIs and tools seamlessly, ensuring the tool was tailored to their specific workflows. "The way that you're going to want to use this and how you're going to get more leverage the more that you can do it internally... it's probably better off doing it yourself" ([03:22]-[04:00]).

---

2. Overview of Moda: Features and Capabilities

Moda serves as Amplitude's internal agent, enabling employees to access and query extensive business data effortlessly. It functions within Slack and a proprietary web interface, providing versatile access points for all team members.

• Data Integration: Moda connects to multiple data sources, including Confluence, Jira, Salesforce, Zendesk, Slack, Google Drive, Productboard, Zoom, Outreach, Gmail, Asana, Dropbox, GitHub, and HubSpot. "It does not have access to private, personal or restricted data sets. It's generally the public ones, well enterprise public ones that we have internally" ([10:06]-[11:16]).

• Functionality: Beyond simple queries, Moda can generate Product Requirements Documents (PRDs) and facilitate prototype generation, streamlining the product development lifecycle. "We have product management, engineering, sales, customer support, marketing, our CEO, our head of sales... all using it for lots of different things internally" ([05:57]-[12:45]).

---

3. Implementation and Rapid Adoption within Amplitude

The internal rollout of Moda was remarkably swift, gaining widespread adoption within a week of its initial release.

• Social Engineering Approach: Wade attributes the rapid adoption to what he terms a "social engineering approach." By making Moda's usage visible and encouraging employees to see their peers successfully using the tool, enthusiasm and engagement naturally followed. "If you can see people more credible or equally credible as yourself having great effect with this, it's an obvious thing that I want to use" ([08:19]-[09:18]).

• Ease of Access and Use: The tool's integration with familiar platforms like Slack and its user-friendly interface lowered barriers to entry, facilitating quick adoption across various departments. "It allows a lot of people to be able to engage with it. And that's what makes it catch like fire" ([06:24]-[09:18]).

---

4. Demonstration of Moda in Action

Wade provides a live demonstration of Moda, showcasing its ability to interact naturally and provide insightful outputs based on internal data.

• Self-Introduction: "Moda, what are you doing?" prompts Moda to explain its functionalities, ensuring users understand its capabilities. [09:20]

• Data Access and Querying: Wade illustrates how Moda accesses diverse datasets and how users can query specific information. For example, generating insights from recent Slack messages or customer feedback sourced from Zendesk and Outreach. [11:43]-[15:35]

• PRD and Prototype Generation: The demonstration includes Moda generating a PRD from a simple one-sentence prompt, showcasing its ability to expand ideas into detailed documentation quickly. "What I love about these and other PRD generators is you can go from that little snippet of an idea to something much more robust." ([14:06]-[24:38])

---

5. Impact on Product Management and Workflow

Moda has significantly enhanced the efficiency and effectiveness of Amplitude's product management process.

• Accelerated Workflow: By automating research, documentation, and prototype generation, Moda reduces the time from idea to prototype from weeks to mere days or even hours. "It's definitely changing the velocity, number one... now we can actually put those three different roles together and produce that in a single meeting" ([29:45]-[31:32]).

• Enhanced Collaboration: The tool fosters greater collaboration among product managers, designers, and engineers by providing a unified platform for accessing and utilizing data. "We've actually intentionally done that at times of where we've said okay, you're going to take on a different role... it was actually very functional" ([32:37]-[33:52]).

• Quality Assurance: Despite automation, Moda's outputs undergo rigorous review processes to ensure accuracy and relevance. "If the person who is doing the generating hasn't also done some follow up queries... you actually have to apply critical reasoning to see where it may have failed you." ([27:31]-[29:10])

---

6. Challenges and Strategies in Building AI Tools

Wade addresses the challenges faced during Moda's development and the strategies employed to overcome them.

• Prompt Engineering: Developing effective prompts is crucial for Moda’s performance. Amplitude's team leveraged both experienced engineers and recursive AI assistance to refine prompts. "AI is a good tool to use for building prompts... recursively ask AI to give you better prompts" ([22:12]-[22:44]).

• Continuous Improvement: Moda is maintained through collaborative efforts, with contributions from engineers, product managers, and designers. The tool is open-sourced within the company, allowing diverse input and rapid iteration. "It's all checked into GitHub... we've had designers that are contributing to this and product managers who are contributing to this." ([22:55]-[23:24])

• Handling Failures: When Moda doesn't perform as expected, the team employs strategies like revising inputs and providing constructive feedback to guide improvements. "I swim upstream... I'll give it feedback as we're going through it in a nice way because you need to be nice to your AI." ([37:20]-[37:48])

---

7. Future Implications and Team Dynamics

The introduction of Moda has not only streamlined workflows but also fostered a culture of empathy and cross-functional collaboration within Amplitude.

• Role Flexibility: Moda has encouraged team members to take on different roles, enhancing understanding and empathy across disciplines. "We've actually intentionally done that at times of where we've said okay, you're going to take on a different role... it's a nice, it's a nice skill development workflow." ([32:56]-[34:30])

• Increased Innovation: By reducing the time spent on repetitive tasks, Moda empowers teams to focus on more strategic and creative initiatives, potentially leading to more innovative products and solutions. "Multiply their value based on these tools... what we're going to be capable of doing." ([36:21]-[37:03])

---

8. Lightning Round: Thoughts on AI in Engineering

In a rapid-fire segment, Wade shares his excitement and concerns regarding AI in engineering.

• Excitement: The ability to manage technical debt more effectively and multiply engineering capabilities through AI tools like Moda. "This is going to give us the ability to do so much more for our customers. I'm genuinely excited by what this means for us." ([36:21]-[37:03])

• Concerns: Ensuring AI tools are user-friendly and reliable, and maintaining a balance between automation and human oversight. "You have to apply critical reasoning to see where it may have failed you." ([27:31]-[29:10])

---

Conclusion

Wade Chambers' insights into Amplitude's development and implementation of Moda highlight the transformative potential of internal AI tools. By prioritizing speed, customization, and cross-functional collaboration, Amplitude has set a benchmark for how companies can harness AI to enhance productivity and innovation. Wade's experiences offer valuable lessons for other organizations looking to integrate AI tools into their workflows effectively.

---

Notable Quotes

• "The way that you're going to want to use this and how you're going to get more leverage the more that you can do it internally... it's probably better off doing it yourself." — Wade Chambers ([03:22])

• "If you can see people more credible or equally credible as yourself having great effect with this, it's an obvious thing that I want to use." — Wade Chambers ([08:19])

• "What I love about these and other PRD generators is you can go from that little snippet of an idea to something much more robust." — Claire Vo ([00:20])

• "You can't assume it's going to. You actually have to apply critical reasoning to see where it may have failed you." — Wade Chambers ([29:10])

---

Final Thoughts

Wade Chambers' discussion on Moda underscores the importance of building tailored AI solutions that align closely with an organization's data and workflows. Amplitude's success with Moda serves as an inspiring case study for other businesses aiming to leverage AI for enhanced operational efficiency and innovation.

Transcript

[Wade Chambers]

I started showing a couple of people internally. It's like, oh, this is really cool. You got to look at this thing. And then a week later it seemed like the entire company was using it. Moda is that internal tool that we have that unlocks all of the data that we have internally and then allows us to answer questions to build artifacts like PRDs.

[Claire Vo]

What I love about these and other PRD generators is you can go from that little snippet of an idea to something much more robust.

[Wade Chambers]

I got to see it and I'm all excited about it. I'm like, when is this going to be pushed so that I can use it? Monday here added push live. I started showing a couple of people internally. It's like, oh, this is really cool.

[Claire Vo]

Okay, so this is my challenge to everybody listening. Mark the day. A month from now, I want you all to have your own internal tools just like this, or at least a prototype. Welcome 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. We've seen a lot of workflows using a lot of tools on this show I but today we have Wade Chambers, chief engineering officer at Amplitude, who's going to show us the tool they built themselves to do all their enterprise search, answer all their business questions, and I think build all their products. Let's get to it. To celebrate 25,000 YouTube followers on how I AI, we're doing a giveaway. You can win a free year to my favorite AI products including V0, Replit, Lovable, Bolt, Cursor and of course chat PRD by leaving a rating and review on your favorite podcast app and subscribing to YouTube. To enter, simply go to howiapod.com giveaway Read the rules and leave us a review and subscribe. Enter by the end of August and we will announce our winners in September. Thanks for listening. This episode is brought to you by coderabbit, the AI code review platform, transforming how engineering teams ship faster with AI without sacrificing code quality. Quality code reviews are critical but time consuming. Coderabbit acts as your AI copilot, providing instant code review comments and potential impacts of every pull request. Beyond just flagging issues, Code Rabbit provides one click fix suggestions and lets you define custom code quality rules using AST grep patterns, catching subtle issues that traditional static analysis tools might miss. Coderabbit brings AI powered code reviews directly into VSCode, Cursor and WinSurf. Coderabit has so far reviewed more than 10 million PRs been installed on 1 million repositories and has been used by 70,000 open source projects. Get Code Rabbit free for an entire year at coderabbit AI and use the code. Howia Wade, thanks for being here.

[Wade Chambers]

I am so looking forward to this. Thanks for having me on.

[Claire Vo]

One of the things that I think is so interesting about how you are approaching AI at amplitude is you all have decided to build some tools yourself instead of plucking a bunch of various things off the shelf. And I'm curious, what was the internal thought process around this sort of build versus buy decision or why did you go down this path of writing a bunch of code?

[Wade Chambers]

Well, let me start with first. It didn't take us as long to do it and it's in spare time, people's spare time. They actually put what we're going to talk about today. And so it's probably like three to four weeks spare time of some pretty talented engineers. One, that's a little bit in the rearview mirror. Two, in talking to a lot of my counterparts in other companies and asking them how they were approaching this and what they were doing, I had it kind of split. About half of them were saying, hey, I'm pulling things off of the shelf and using it. And the other half were kind of like, no. The way that you're going to want to use this and how you're going to get more leverage the more that you can do it internally. As long as you don't invest a lot in overbuilding it and over engineering it, you'd probably be better off doing it yourself. And so once we got into it, I found that we were able to pull a lot of things off the shelf like glean APIs and things along those lines. Lines which just allowed us to move really quick. And there's not so much of an investment in it that I, I worry about. If I need to, I will revisit it. I'll throw everything away, do it again. It's really unlocking people and the data that sits in the enterprise that I wanted to do the most.

[Claire Vo]

That tends to be my whole theme when building things with AI. It's so fast and it's almost so cheap. I think, you know, what if in three months I throw the whole thing away, it will have been worth it anyway, so I can definitely understand that mindset. Okay, so we're going to see this internal tool you built and I'm excited to show it off, apparently in the, in the free time of engineers over three, three to four weeks or at least a little. A little Sprint. So tell us what Moda is like.

[Wade Chambers]

A lot of different companies, I think that right now, Amplitude is going through that change of being AI native and wanting to really fast. And so I think that in all of those companies, you need to get access to the data that you have internally. You want as many people as possible to see it. You want to see others being successful with it and say, oh, that looks really easy. How could I do that? And so Moda is that internal tool that we have that unlocks all of the data that we have internally and then allows us to answer questions, to build artifacts like PRDs, things along those lines internally, but with the full scope of information that we have access to.

[Claire Vo]

Great. So you took all of your business data across, I'm sure, like BI sources and documentation sources, and you exposed it in the tool. And one of the things you were telling me before we started the show is one of the approaches you took was this social engineering approach, which is you went into the decision of what platform Moda would be built on. So can you tell me a little bit about how you incepted the organization with the design of this internal product?

[Wade Chambers]

The problem is everybody's starting in a different place, right? And so you use ChatGPT at home, or you use Claude, or you use something else. And some people are really advanced and others are not. And so how do you create this common language or this common fluidity, if you will, around AI? It felt like if we could do something, and that made it really straightforward, and we took a lot of the complexity and trying to push it down, it would allow a lot of people to be able to engage with it. And so step one. And by the way, great minds before me. Well, I wouldn't say I have great mind, but, like, great minds that I can leverage. The folks over at Abnormal Security Security had built a little agent in Slack that I got a chance to see, and it allowed all their employees to ask really good questions. And I'm like, oh, that's. That's genius. Because if I can see what other people are doing and it's adjacent to the work that I'm doing, I'll. I'll borrow the prompt, I'll borrow the. The question. Or if they've already done something that I can leverage, I'll just use the result on the other side. And I'm like, and that is the right way of doing this. The more that I can make this publicly visible and do real, solid work on the other side of it, provide great answers on the other side of it, then it should catch like fire. Well, that's the thesis. The truth is, is that one of our engineers had this working on a Friday afternoon. I got to see it and I'm all excited about it. I'm like, when is this going to be pushed so that I can use it? Monday? He had it pushed live. I started showing a couple of people internally. He's like, oh, this is really cool. You gotta look at this thing. And then a week later, it seemed like the entire company was using it. It's been pretty incredible.

[Claire Vo]

I don't know, you might be wasting your talent in B2B. It sounds like you got some consumer thinkers there with how viral this product went.

[Wade Chambers]

It's helpful. And anything that accelerates your thinking or allows you to get to a deeper truth, all of those things are just awesome. And so if this can help you with that and you can see other people doing it, True story. Right before I came on this, I was talking to one of our sales execs and she hadn't heard Emota yet. And so I was like, oh, well, that'll help you answer that question. And her first thing was, is she opened up the Slack channel, went in there, and she saw a colleague that's using it repeatedly. As she just scanned down, it's like, well, if it's good enough for him, I'm all in. And so I'm like, okay, that's the social engineering aspect of it. If you can see people more credible or equally credible as yourself having great effect with this. It's an obvious thing that I want to use.

[Claire Vo]

Great. So let's take a look at it.

[Wade Chambers]

Well, as an example, here's today's thing. And you can already see just how many people inside of the company have already been using it today. So let me go through and ask Moda to introduce itself. And so if I go through and just, hey, Moda, what are you doing? Well, he's chomping on data, nom nom, but it'll come back here pretty quickly and give an answer and say, well, I'm Moda internal agent. I search internal knowledge sources. I can also search the public. I always cite my sources so you can verify the information. You can access me by Slack. There's also a proprietary interface which we'll get into. You can even learn more about the implementation and things along those lines. And so if I wanted to know a little bit more about Moda, let's just ask it to tell us a Little bit more about itself. And again, it's just going to go through Parseit, send it out, gather information and put it back and just say that it was built. We have our own little stack that we've built to be able to process AI request called Langley Framework. But on top of that you can see that it leverages a lot of the things like glean to be able to access certain parts of this. But it can do external search and we already kind of covered that. Well, what about the datasets that it has access to internally? Because lots of people don't have the exact same things that we have. But let's go there. What data sets do you have access to? Well, wait, I'm glad you asked. So we can get into Confluence, Jira, Salesforce, Zendesk, Slack, Google Drive, productboard, Zoom, Outreach for transcribed meetings, those sorts of things, even some Gmail, Asana, Dropbox, GitHub, HubSpot. So it does not have access to private, personal or restricted data sets. It's generally the public ones, well enterprise public ones that we have internally. And so if I just was to go through and say, all right, well who is using you? Completely different way of looking at it. Just how widespread is it inside of the company and how many different groups are using this?

[Claire Vo]

And so you're product managing your own AI product, using your AI product here.

[Wade Chambers]

Exactly. Because if I can understand where we have any friction inside of the the company and what types of questions are being asked and where are people not having success on the other side? It's just a simple process of like, okay, where did we get the rules wrong? Where did we. How can we help out with prompting? What data sets do we need access to? Do we need to do any grooming of that on, on the output side of it. But you can see product management, engineering, sales, customer support, marketing, our CEO, our head of sales. I've seen our chief product officer in here. There's. Well, and you can see it just keeps going even as we're sitting here talking about it. So these are all. Well, I'm even a reference inside of here. But you can see that lots of different people are using it for lots of different things internally.

[Claire Vo]

So could you show us one of the common flows that you might. Somebody might use with modus? So it's pretty good at explaining itself, which is great. And see, seems like it has access to a lot of data, but oh, here we go. And then you can customize it.

[Wade Chambers]

Well, you know, I want to make sure that I understand everything that's going on with Moda. So I'm going to actually give it a little bit of attitude and let's go through there. So I want to go through and actually start. I mean, almost everything that our customers do, they need to understand what's going on, then they want to make a decision, then they want to act on it. So we need to do the same thing here. Why don't we actually go use all of these data sets that we've got access to to find out what's going on? I don't know that we actually need to see every the top themes and queries, but maybe it's a good place to start. I'm just looking for an insight that we can kind of chase down.

[Claire Vo]

No, I think this is great. So I think that thematic analysis and sort of trying to quantify more qualitative or. Yeah, more qualitative feedback is a very common kind of product manager use case. And so anything that can have access to a broad set of business data and do that analysis for you. Oh my gosh, these descriptions are ridiculous though.

[Wade Chambers]

Isn't this great?

[Claire Vo]

It really gave you Gen Z slang.

[Wade Chambers]

Bet bet.

[Claire Vo]

Dumb bet. No cap. All right, so this is doing something that I think would be very popular for a product manage. And so you're saying, let's take all this context I have, analyze it, quantify it, and then it actually gives you the scope of its research data. So it says it takes the 50 most recent slack messages. So that's a good resource. But then you're looking for another one with more external resources. So that last query was really about the modabot itself, but this query looks like it's about your actual product and you're looking for real customer feedback. And this is a very common workflow that a lot of product managers do quite manually.

[Wade Chambers]

Absolutely right. And so, you know, go into Product Board, go into Zendesk where things are going to be logged. Actually go into the transcriptions of conversations that we've had with various customers. And let's get to a point where we believe we know where there's some energy, where people want extensions to the product or want to improve the functionality of the product. Like connecting session replay to funnel analysis. That seems like a pretty good place to dig in. So why don't we just jump in and see what moda's got to tell us about that.

[Claire Vo]

Got it. So you're taking this wide funnel of data analysis, trying to figure out what are the sub themes and then you can use Moda and say, okay, I've picked plucked a sub theme, give me even more data around it. And do you think that's a useful flow for folks? Basically like start at a pretty wide data top of the funnel and narrow, narrow in. Is that how you approach things?

[Wade Chambers]

I think it's useful when you're going through and saying like okay, what could I learn from this? What's something that's new? And so this was me trying to start at the very top and say okay, let's go in and dig into, well, let's start at the top, say what are people asking for? And then if people are asking for this, let me make sure that I believe that what they're actually asking for, there's actual quotes, there's details behind it that I can look at and we could even ask the opposite of this. And so there's plenty of conversations that come through in this of where you can see specifically, you know, from Zendesk and from Zendesk from an outreach call. And so you can see the details of specifically what somebody is asking for and what they're trying to do inside of that. Which gives me a sense of like there's some heat here.

[Claire Vo]

As an AI founder, you're used to sprinting towards product market fit your next round or that first enterprise contract. But speed isn't enough for AI startups. Buyers expect security, compliance and transparency from day one. That's why serious AI startups use Vanta with deep integrations and automated workflows built for with fast moving AI teams. Vanta gets you audit ready fast and keeps you secure with continuous monitoring as your models infra and customers evolve. AI innovators like LangChain, Rider and Cursor scaled faster and closed bigger deals by getting security right early. With Vanta, listeners can claim a special offer of $1,000 off Vanta at vanta.com/how IAI AI for somebody who is building AI products for product managers, I know there's a whole cottage industry that is trying to build SaaS products for what you just what you just showed on this internal tool. And I'm curious if your product managers have by and large been quite happy with moda of their as their source of insights or if you feel like there are pieces that this kind of general purpose internal tool is missing maybe to serve this specific use case better.

[Wade Chambers]

I think that a lot of product managers that are here take this as a way of getting access to 100% of the data and seeing what AI would generate for it. And if it comes back and it doesn't match their instincts, they'll dig in. And if it does match their instincts, then they'll look for more detail inside of it. And so I think that for the most part, we have a lot of product managers using it to great effect. And I'll go into more detail on how it actually does this. We have a proprietary interface, actually. Let's jump over there.

[Claire Vo]

Yeah, I would love to see that, because I think my next question is like, how does it work behind the scenes for folks that say, well, I got a smart engineer in three weeks, how can I have this too? I'm curious how you've approached building this. A little bit more detail.

[Wade Chambers]

Yeah. And the nice part is you can even ask Moda on how it works. We have a framework that we've used internally and we have both a little bot that sits in Slack that can call out to that framework. But you can see that I can go into a web UI and basically be able to access the same thing in this flow, we've actually got a lot more capabilities that are associated with it. And so we can go in and create PRDs as an example. You can ask anything, you can do deep research on it, but you can create a PRD that then allows us to take some piece of this and go in even deeper. And if I was to go in, you can kind of look at just jumping into GitHub, right? Here's the YAML that kind of defines the high level, how we would do a Glean search on Ask Anything. We could go back up and even look at the PRD orchestrator on this side and you can see, you know, how it starts with a prompt and is able to sort of dig in a little bit more based on what you're trying to do. If it needs more details, it's going to ask you for that. It's then going to take all of this and break it down of where it will break things into. Let's make sure that we do proper problem exploration, solution exploration, detailed requirements that come out the other side. We like to move as quickly as possible to a prototype. And so if it can do prototype generation or at least the prompts that then we can plug in, we can copy and paste into Bolt, or you pick your lovable V0, pick your favorite and be able to move it around, then we can get through that fairly quickly. And then it will just go through using the Glean API, we'll get access to a lot of the content and be able to do a query. And so we use that as part of our rag to make sure that we go get the right content and then pass it off and it's able to evaluate all of that and come back with a much better answer.

[Claire Vo]

Yeah, I have a couple technical questions because as a builder, I'm just so curious here. So it sounds like you're using the Glean API for a bunch of your enterprise search. So that simplifies a little bit the data access and controls and all that piece, the rag piece of it. Then you've built these two kind of alternate interfaces, which is the Slack bot or the web ui, which is nice. And then it seems like you've built also some kind of specialized tools in terms of kind of the general chat, deep research chat or this PRD flow. And then just looking at that GitHub, if you don't mind pulling it up again. I'm so curious who got this good at writing prompts because this is a, this is a well structured prompt. And I think one of the things that is very mysterious to people right now trying to build something like this is they vaguely know the scent, like a sense of like tool calls and they vaguely know about instructions, but no less about like these sequential instructions or multi tool or parallel tool calls. And I'm just curious how your team up, leveled or upskilled on how to build great prompts, how to build great agents. Was that just learn as you go?

[Wade Chambers]

There was part of it that was learned as you go. I mean, we've got a couple of talented folks that have a lot of experience with AI and so I think we were able to use those. But also AI is a good tool to use for building prompts. And so you can just recursively ask AI to give you better prompts or things that would allow you to focus on very specific things that you want in the results that and AI will actually generate the prompt for you that you can use. You'll probably have to edit it a little bit, but it does pretty good job on its own.

[Claire Vo]

And then how does your team improve, improve this over time? Is it open to anybody to do a pull request on it? Is there a team that owns it? How have you set it up operationally?

[Wade Chambers]

Yeah, we've set it. I mean, it's all checked into GitHub. Most of our engineers can check it out. Even product managers and designers can probably do the same to it. We've had designers that are contributing to this and product managers who are contributing to this. We're currently going through an AI week this week of where there's a lot of things that are going on. One of my vibe coding ideas is I want to be able to add NCTs in addition to PRDs to all of this and see if I can do it totally on my own.

[Claire Vo]

Okay, well, speaking of PRDs, is there any way I could get you to create a PRD with this flow? I'd love to see that.

[Wade Chambers]

Let's do it. I was going to go through here and say, let's go through. I'm going to see if it will take it as is. Let's actually go through and create a prd.

[Claire Vo]

So for people listening in our Slack flow, we got this insight that people wanted session replay attached to Funnel Steps, which makes total sense. And so now we're taking that idea and that context and going it to the Create PRD prototype flow in Moda, which is asking us what we want to build.

[Wade Chambers]

So let's just give it the prompt that we had as an answer to a previous question and see if it's able to expand on that.

[Claire Vo]

Yeah. And again, for folks listening, this is one sentence. The customers want to see session replays directly linked to Funnel Steps so they can watch where users drop off or convert. And what I think is so powerful for product managers is they really convince themselves for, for many years that you needed many more sentences than that to convey what kind of product you need. But what I love about these and other PRD generators is you can go from that little snippet of an idea to something much more. Much more robust.

[Wade Chambers]

Yeah. And it's going to go through its stages and it's going to think a little bit and it's going to generate things. So I'm just going to very quickly jump over and say this is kind of what it will produce. And it also produces all of the PRDs in a place that, where anybody can go look at them and see the output of it. But it will talk about the problem exploration, it will talk about the actual solution exploration, it will talk about the detailed requirements that come through on top of it. And then it will go through and it will generate things that you need to do to generate a prototype on it. So it'll give you all of the prompting that you need to do it. In this specific one, they took those prompts and actually fed it to bolt, to figma, make, to V0 just to with the same exact prompt, see what different systems would actually suggest as a great prototype that you could interact with.

[Claire Vo]

And is this the product manager that's taking the output of this automatic PRD generator, which includes prototype instructions. And then they're just copying and pasting that into the prototype tool of their choice and then comparing the outputs and putting them in a Confluence doc for people to look at.

[Wade Chambers]

And they don't even have to put it in a Confluence. Yes, that's exactly what they're doing. On the other side of that, for everything else, it will generate and put it into the Confluence document. It looks like it's still thinking about it here, but that's exactly what happens here. And as soon as this comes back, we'll look at some of the results that are associated with it and go create our own prototype from it.

[Claire Vo]

What I like about the design of this internal flow is it's clearly multi step without user interaction, which is quite, quite interesting. And so instead of this sort of iterative, do you like this? Do you like this? Do you like this? Do you like this? It seems like you've built something that you're pretty confident is going to get you close to what you want with very little human intervention. Of course you can come and edit it in here, but I'm curious if that was an intentional choice or what drove that sort of kind of decision. Say, just get it all done at once.

[Wade Chambers]

We decided. I mean, it is a multi step process, but one of the things that you can do is you can go in here and actually say, oh, I don't agree with something in here. You can create a comment associated with it and then you can tell it to go reevaluate things. And so you're not stuck with the answer that you got based on your ability to comment, you can actually go and change things pretty rapidly. So if you don't think it got it right, like the downstream consequences are fairly minimal because you can just go to as high up in the stack as possible and say, well, the problem isn't right. Let me actually change some things along this. Just regenerate everything that's beneath it and you can just keep going down the stack as you need to.

[Claire Vo]

So I have to ask you about the AI generated product document. Elephant in the room. As somebody who's thought about this for.

[Wade Chambers]

A long time, you've thought about it a long time?

[Claire Vo]

I've thought about it a lot. You have created five beautiful detailed assets in, I don't know, three minutes. Does anybody actually read them or do they just click right to that prototype and say, yes, this is what we.

[Wade Chambers]

Want, we do review them. And matter of fact, if you go through and you look at the detailed requirements almost every Document that we produce on this side will have a review segment that we go through. And so we'll have people go through, actually we look at the problem statement, look at the solution statement, and we actually go through a review process to make sure that we agree. And honestly, if the person who is doing the generating hasn't also done some follow up queries to say, you know, what are the cons on this? And is there evidence that suggests other answers would be better? And even when you get to the prototyping phase, what are the multiple solutions that you looked at? What did you generate from a prototype perspective so that we can see three different variations, maybe four different variations on the other side and that will, and that will force you to change your prompt as well. And so all of this, or at least I don't feel like we've gotten to that place where you can just go yolo, you're going to have to, it's going to be an assist, it's actually going to speed up things. And in many cases it gets it perfect. But you can't assume it's going to. You actually have to apply critical reasoning to see where it may have failed you.

[Claire Vo]

I'm so curious because again, you've compressed a lot of work, you've compressed user research, quantitative qualitative research, idea generation, PRD generation, prototype generation into a very small compressed timeline using all the business data that you have built by an internal tool. I'm curious what the downstream effects you're seeing in the product and engineering and design organizations when something like this can get done so quickly. Are you, are you building more things? Are you getting more ideas? Are you getting better ideas, worse ideas? I'm curious your point of view of what this is changing.

[Wade Chambers]

It's definitely changing the velocity, number one. And so we see that in, you know, six months ago, eight months ago. You know, we're an agile shop. We move pretty quickly. You know, we, we employ a lot of scrum and able to sort of iterate through things pretty quickly. But even then you would say that there was somebody who was out there doing the research and needed to try and put it into a document so that other people could review it. And then when other people would review it, you would actually then move it into design. And somebody on the design side of things would use FIGMA to actually build some mockups and things along those lines, which then would get handed over to engineering for inspection and trying to figure out like, okay, how do I turn this design into something that's working code on the other side, that could take weeks. And I think the best case is that it took a couple of weeks. Well, maybe you could get it done in a week. And now we can actually put those three different roles together and actually produce that in a single meeting where we're going through and using Moda or other tools along those lines to actually say, let's go find evidence. Do we find customers are actually asking for this? Okay, you know, like, what's the right context to provide to Moda to make sure that we got it right? Or can it provide us that context by searching through all of the enterprise data that we've got and we'll get to a prototype in a very short period of time. So now when we do product review sessions, the PRD is a part of that, but oftentimes we're looking to get to the prototype as quickly as possible and work backwards from them.

[Claire Vo]

Do you feel like you have more ideas than capacity to execute, or are you keeping up speed on the engineering side because you're using all these AI engineering tools? I'm always wondering where there's a misbalance in the force, where it comes from, because you sit on a lot of prototypes and then I know you have a complex product. I'm just curious how you approach building those.

[Wade Chambers]

It does move around a little bit and that we'll find that if we're really trying to figure out a concept, you know, maybe Moda plus some prototyping tools can actually get you most of the way there. If it's something that is a product direction or a entirely new product, you're probably going to need to go do some market research. If it's something that is UI heavy or, you know, deeply integrated with a part of our product, we'll probably need to slow down a little bit and give design the time to actually go through and make sure that they've. They, like, stitch it all together and you can make sure that it's complete, coherent thought. So it's a little all over the place, depending on the type of project and the work that we're looking at.

[Claire Vo]

And then I can see how, because I love this idea and I've spoken about it before, that product design and engineering can all be done in a single meeting, in this single flow. I'm curious, do you see your team swapping roles? Do you see engineers going, I'll write The PRD or PM's being like, let me put up a PR.

[Wade Chambers]

Absolutely. And we've actually intentionally done that at times of where we've said okay, you're going to take on a different role. And so once we even had a demo where we had like the designer being the engineer, the engineer being the product manager, the product manager being the designer, kind of in the role to just show like how you could work through it. It was hilarious, it was fun, but it was actually very functional. The designer actually got into cursor and was able to extend some things in cursor. The engineer was able to come, I mean, very good product thinker anyhow, but they were able to come up with the right PRD and the right requirements. Even the product manager that was there was able to get in and do multiple iterations on a design until they actually found something that hit the sweet spot.

[Claire Vo]

This is a workflow I have not heard before. So for people listening, I want you to do it. I want you to take a Friday morning, bring your team together, screen share and do a little role swap. Because that's, it's genius. Just to show it's possible or see where there are struggles, see where there's opportunity. I'm also sure it gives empathy between the teammates, saying, you know what you do? When I say just vicode it, maybe I'm being a little silly. Or when I say we can just make the prototype, I understand now why, why we have UX designers. So it's a nice, it's a nice skill development workflow. But I bet it also brings the team kind of closer together in terms of empathy and respect for each other's craft.

[Wade Chambers]

Empathy, respect, and just like fluency in each other's craft and how AI can help with that.

[Claire Vo]

Okay, so you're setting the, you're very calm, but you've set the bar very high. So just to recap, you've told us that you don't have to buy it off the shelf. Just pluck a couple engineers in a couple weeks and build this thing by yourself. No big deal. It'll just have all your enterprise data in it that you can query on demand anytime you want. You built it in Slack and a UI so that your whole team can both access it as well as see each other's use of it and kind of learn from that. And then you've built these specialized tools and of course, you know, our audience's favorite is going to be this PRD to prototyping tools that kind of takes the best of all those workflows and puts them together for a purpose built, reusable flow that can get your business something that you really need faster. No big deal. All while running an amazing company that tons of product people just love. Right?

[Wade Chambers]

There's a fair amount of true. I mean, I may have minimized how much work it was, but honestly, it was not a bunch of engineers full time working on this for quarters or anything along those lines. It literally was four weeks and part time with a few engineers.

[Claire Vo]

Okay, so this is my challenge to everybody listening. Mark the date, put a month ahead. And from a month from now, I want you all to have your own internal tools just like this, or at least a prototype. Okay, wait, I am going to send you on your way in just a few minutes, but let's wrap with a couple lightning round questions. My first first is we've talked a lot about product and business data, but you're a builder running engineering organizations. What are you excited about on the engineering side? What are you nervous about? Kind of. What are your thoughts on all this AI powered coding?

[Wade Chambers]

Honestly, I've never worked at a place where it felt like we had tech debt under control and everything was fine and we didn't have too much surface space. Every company has those challenges. This just gives us a way of being able to deal with those things much more effectively moving forward. There's work that we have to do on our side to make it more AI friendly so that AI can do more work on our side. But this is going to give us the ability to do so much more for our customers. I'm truly excited. Take the same engineers and multiply their value based on these tools and just think about what we're going to be capable of doing. I'm genuinely excited by what this means for us.

[Claire Vo]

Yeah, and I'm glad you called out tech debt and all those challenges that engineering orgs have. Because one of my pitches to software engineers is like reduce, toil, get rid of misery. You know those corners of the app that you hate but you tolerate because you do not have time.

[Wade Chambers]

Exactly.

[Claire Vo]

Now you have a tool that you didn't have, that you didn't have before on those. So I think that's a great call out. And then you have built and your team has built such a structured, full of personality internal assistant. But I'm curious, what is your strategy when you have asked Moda to generate a prd, you know, five times, it's not doing the right thing. It's not listening or chatgpt or whatever your frustrating AI tool of choice is. What's your prompting strategy? How do you get it to listen?

[Wade Chambers]

I have a few different strategies. One is I swim upstream. It's like where did it start to go wrong? And like, let me edit that and actually go through and see if I can generate a different result on the other side. I always feel like it was an input problem on my side. So if I can figure out where it started to go wrong, let me change that and put it on a better path. Number two is I'll just give it feedback as we're going through it in a nice way because you need to be nice to your AI. But I will go through and say, hey, this didn't quite hit the mark. I was looking for something that felt a little bit more X or Y. I needed more detail here. I want to be able to use this to describe it to my grandmother. I want to have multiple use cases or I want to hear the customer's voice come through in this a little bit more concretely. I feel like the more that I can give it context but also tell it what I needed out of it after multiple rounds, you'll either figure out what it needed or it'll figure it out on its own and help you get there.

[Claire Vo]

Well, I'm going to give you a compliment because both of those strategies speak to a very good engineering leader. One, I was like, oh, you just go back to the last good commit and you start over again. And two, how you described giving feedback to an LLM is exactly how people want feedback from their manager. So that came through loud and clear. All right, Wade, this has been so fun. It's really interesting to see this behind the curtain. See how a company like Amplitude has built us themselves some tools that can be really practical for their team. How can we find you and how can we be helpful?

[Wade Chambers]

LinkedIn is probably the best way to find me personally and I will say there's going to be some news coming from Amplitude on some Agentix solutions. Stay tuned. It's going to be a lot of fun.

[Claire Vo]

Amazing. Well, thank you for being here. I appreciate it.

[Wade Chambers]

Awesome. Thank you.

[Claire Vo]

Thanks so much for watching. If you enjoyed this 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 [e-mail] See you next time.