Skip to content
How I AIHow I AI

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

Wade Chambers, Chief Engineering Officer at Amplitude, shares how his team built Moda—an internal AI tool that gives employees access to enterprise data across multiple systems, enabling faster product development and decision-making while fostering cross-functional collaboration. *What you’ll learn:* 1. How Amplitude built a powerful internal AI tool in just 3 to 4 weeks of engineers’ spare time 2. A social engineering approach that made their AI tool go viral company-wide in just one week 3. How product managers use AI to analyze customer feedback across multiple data sources and identify key themes 4. A streamlined workflow that compresses research, PRD creation, and prototyping into a single meeting 5. Why role-swapping exercises with AI tools build empathy and cross-functional fluency across product, design, and engineering teams 6. How AI tools are helping engineering teams tackle persistent tech debt challenges more effectively *Brought to you by:* CodeRabbit—Cut code review time and bugs in half. Instantly: https://coderabbit.link/howiai Vanta—Automate compliance and simplify security: https://www.vanta.com/howiai *25k giveaway:*  To celebrate 25,000 YouTube followers, we’re doing a giveaway. Win a free year of 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 the podcast on YouTube. To enter: https://www.howiaipod.com/giveaway. *Where to find Wade Chambers:* LinkedIn: https://www.linkedin.com/in/wadechambers/ Amplitude: https://amplitude.com/blog/meet-the-team-wade-chambers *Where to find Claire Vo:* ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo *In this episode, we cover:* (00:00) Introduction to Wade Chambers (02:53) The build vs. buy decision for internal AI tools (04:55) What Moda is and how it works (07:19) The social engineering approach to adoption (09:17) Demo of Moda in Slack (10:58) Data sources Moda has access to (12:43) Analyzing customer feedback themes with Moda (17:41) Behind the scenes: how Moda works technically (23:24) Creating a PRD from a single customer insight (27:30) How teams actually use AI-generated PRDs (29:09) Impact on product development velocity (32:37) Engineers, designers, and PMs swapping roles (34:38) Recap of creating Moda (36:00) Lightning round and final thoughts *Tools referenced:* • Glean: https://www.glean.com/ • ChatGPT: https://chat.openai.com/ • Cursor: https://cursor.com/ • Bolt: https://bolt.new/ • Figma: https://www.figma.com/ • Lovable: https://lovable.dev/ • v0: https://v0.dev/ *Other references:* • Amplitude: https://amplitude.com/ • Slack: https://slack.com/ • Confluence: https://www.atlassian.com/software/confluence • Jira: https://www.atlassian.com/software/jira • Salesforce: https://www.salesforce.com/ • Zendesk: https://www.zendesk.com/ • Google Drive: https://drive.google.com/ • Productboard: https://www.productboard.com/ • Zoom: https://zoom.us/ • Asana: https://asana.com/ • Dropbox: https://www.dropbox.com/ • GitHub: https://github.com/ • HubSpot: https://www.hubspot.com/ • Abnormal Security: https://abnormalsecurity.com/ _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email jordan@penname.co._

Wade ChambersguestClaire Vohost
Aug 10, 202540mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

Amplitude’s viral internal AI agent unlocks enterprise data for everyone.

  1. 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.
  2. 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.
  3. 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.
  4. 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.

IDEAS WORTH REMEMBERING

5 ideas

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.

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.

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.

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.

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.

WORDS WORTH SAVING

5 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

Build vs buy for internal AI toolsSlack-first distribution and viral adoption mechanicsEnterprise search + RAG using Glean APIUnified access to internal data sources with permissionsPRD orchestrator and multi-step agent workflowsPrompt engineering via recursive AI-assisted prompt writingWorkflow compression: research → PRD → prototype in one meetingGovernance: citations, dataset restrictions, review loops

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome