How Amplitude built an internal AI tool that the whole company’s obsessed with (and how you can too)
Wade Chambers (guest), Claire Vo (host)
In this episode of How I AI, featuring Wade Chambers and Claire Vo, How Amplitude built an internal AI tool that the whole company’s obsessed with (and how you can too) explores amplitude’s viral internal AI agent unlocks enterprise data for everyone. Amplitude’s Chief Engineering Officer Wade Chambers demos Moda, an internal AI tool that unifies access to company knowledge (Slack, Jira, Confluence, Salesforce, Zendesk, etc.) and answers questions with cited sources.
Amplitude’s viral internal AI agent unlocks enterprise data for everyone.
Amplitude’s Chief Engineering Officer Wade Chambers demos Moda, an internal AI tool that unifies access to company knowledge (Slack, Jira, Confluence, Salesforce, Zendesk, etc.) and answers questions with cited sources.
They chose a lightweight build approach—3–4 weeks of part-time work—by combining off-the-shelf components (notably Glean APIs for search/RAG) with an internal orchestration framework and Slack-first distribution.
A key driver of adoption was “social engineering”: making usage and successful queries visible in Slack so employees can copy prompts, learn patterns, and trust outcomes through peer proof.
Moda also operationalizes product work by generating multi-step PRDs (problem/solution/requirements) and prototype prompts, while emphasizing review, critique, and iterative regeneration rather than blindly accepting AI outputs.
Key Takeaways
Start where people already work: Slack as the default AI interface.
Amplitude embedded Moda in Slack so adoption didn’t require new habits; visibility of others’ queries made it easy to copy prompts and learn fast.
Get the full analysis with uListen AI
Make AI work observable to drive trust and “prompt reuse.”
Seeing credible peers use Moda successfully acted as social proof and enabled employees to borrow prompts/results instead of starting from scratch.
Get the full analysis with uListen AI
Build quickly by mixing off-the-shelf search with lightweight internal orchestration.
They avoided overengineering by leveraging Glean APIs for enterprise search/RAG and layering a simple internal framework plus purpose-built workflows on top.
Get the full analysis with uListen AI
Citations and source transparency are non-negotiable for enterprise Q&A.
Moda “always cites sources,” allowing verification and reducing the risk of hallucinated decisions when querying company knowledge.
Get the full analysis with uListen AI
Use AI to compress the product cycle—but keep human review gates.
Moda can generate detailed PRDs and prototype prompts in minutes, yet teams still review problem/solution/requirements and ask for cons or alternative evidence.
Get the full analysis with uListen AI
Iterate by ‘swimming upstream’ to the earliest wrong assumption.
When outputs miss the mark, Chambers recommends editing the earliest step (like a bad commit) and regenerating downstream artifacts for faster correction.
Get the full analysis with uListen AI
AI enables role flexibility and cross-functional fluency.
They intentionally role-swapped (designer as engineer, PM as designer) using tools like Cursor, improving empathy and showing how AI lowers barriers between crafts.
Get the full analysis with uListen AI
Notable Quotes
“I started showing a couple of people internally… and then a week later, it seemed like the entire company was using it.”
— Wade Chambers
“Moda is that internal tool… that unlocks all of the data that we have internally, and then allows us to answer questions, to build artifacts like PRDs.”
— Wade Chambers
“If you can see people more credible… having great effect with this, it’s an obvious thing that I want to use.”
— Wade Chambers
“You can go from that little snippet of an idea to something much more robust.”
— Claire Vo
“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
Questions Answered in This Episode
What was the exact architecture of Moda (agent orchestration, tool-calling, evals), and what parts would you replicate vs replace at a different company?
Amplitude’s Chief Engineering Officer Wade Chambers demos Moda, an internal AI tool that unifies access to company knowledge (Slack, Jira, Confluence, Salesforce, Zendesk, etc. ...
Get the full analysis with uListen AI
How did you decide which internal sources Moda can access (and which it cannot), and how are permissions enforced end-to-end?
They chose a lightweight build approach—3–4 weeks of part-time work—by combining off-the-shelf components (notably Glean APIs for search/RAG) with an internal orchestration framework and Slack-first distribution.
Get the full analysis with uListen AI
What specific ‘viral’ design choices in Slack mattered most—public channels, shared threads, prompt libraries, or leader participation?
A key driver of adoption was “social engineering”: making usage and successful queries visible in Slack so employees can copy prompts, learn patterns, and trust outcomes through peer proof.
Get the full analysis with uListen AI
How do you measure Moda’s quality over time (answer accuracy, citation usefulness, time saved, adoption by org), and what dashboards/metrics do you track?
Moda also operationalizes product work by generating multi-step PRDs (problem/solution/requirements) and prototype prompts, while emphasizing review, critique, and iterative regeneration rather than blindly accepting AI outputs.
Get the full analysis with uListen AI
In the PRD generator, what’s the prompt/YAML structure that reliably produces problem exploration → solution exploration → requirements without constant babysitting?
Get the full analysis with uListen AI
Transcript Preview
I started showing a couple of people internally. It's like, "Oh, this is really cool. You've 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.
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.
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. It's like, "Oh, this is really cool."
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. [upbeat music] 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, but today we have Wade Chambers, Chief Engineering Officer at Amplitude, who's gonna 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 twenty-five thousand 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, ChatPRD, by leaving a rating and review on your favorite podcast app and subscribing to YouTube. To enter, simply go to howiai pod.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. CodeRabbit 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 VS Code, Cursor, and Windsor. CodeRabbit has so far reviewed more than ten million PRs, been installed on one million repositories, and has been used by seventy thousand open source projects. Get CodeRabbit free for an entire year at coderabbit.ai, and use the code HOWIAI. Wade, thanks for being here!
I am so looking forward to this. Thanks for having me on.
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, you know, a bunch of various things off the shelf, and I'm curious, what was the internal thought process around this sort of build vs buy decision, or why did you go down this path of writing a bunch of code?
Install uListen to search the full transcript and get AI-powered insights
Get Full TranscriptGet more from every podcast
AI summaries, searchable transcripts, and fact-checking. Free forever.
Add to Chrome