Amplitude AI Analytics

Claude Code + Analytics = Vibe PMing

Amplitude

Dapper Labs

Opendoor

Amazon

Frank Lee

AI Product Leader at Amplitude, Founder at Inari

Where your analytics stops giving useful signal on AI agent performance and what's missing.

How to spot the quality blind spot in your analytics stack

One data point that connects agent quality to the metrics your leadership already cares about.

The 2.3x retention benchmark to build your business case

How to scope what "good" looks like for your agent before you write a single line of tracking code.

The instrumentation questions to ask before your next sprint

Walk in with a problem. Walk out with a working prototype.

AI PM @Google - [Bay Area In Person]

Dr. Marily Nika

AI Product Lead @ Google, ex-Meta, Harvard Business School Fellow

AI Product @Google [Seattle In Person]

Diego Granados

AI Product @ Google

Virtual: Vibe Coding with AI Studio, Perplexity, and GPTs

athens in person - beginner

In 4 hours, you will research a real user problem, write a PRD that survives three senior reviewers, and build a working prototype -- without writing a single line of code yourself.This is not a lecture. You build the entire time.<h3>🗓️ Upcoming Cohorts</h3><ul><li>May 11 | 💻 Zoom Remote<ul><li>Lead: Marily | [101]</li></ul></li><li>May 16 | ☕ Seattle (In-person + Zoom)<ul><li>Lead: Diego | [ADVANCED]</li></ul></li><li>June | 🏛️ Athens (In-person + Zoom)<ul><li>Lead: Marily | [101] | Language: Greek</li></ul></li><li>July 17 | 💻 Virtual Only<ul><li>Lead: Diego | [101] | Language: Spanish / En Español</li></ul></li><li>July 21 | 💻 Virtual Only<ul><li>[ADVANCED]</li></ul></li><li>August 21 | 🏙️ Mountain View (In-person + Zoom)<ul><li>Lead: Marily | [101]</li></ul></li></ul>We will do this in-person but you can also join via zoom from anywhere!By the end of this session, you will have four real artifacts on your laptop:<ol><li>User research backed by real complaints from real people</li><li>A PRD with sections filled from actual evidence</li><li>A working prototype running in your browser with real UI, real sample data, and enough polish to show your stakeholders on Monday</li></ol>You also keep a GitHub repo with reusable templates and tools that work on any project, not just the workshop example.

PMs who want to move faster You use AI but haven't made it part of your daily workflow. Leave with reusable tools for PRDs, and reports.

PMs who want to prototype You have ideas but depend on engineering to see them built. Leave with a working prototype you built yourself.

Founders and builders Evaluating whether a problem is worth solving. Leave with user evidence, a PRD, and a prototype to make the call.

Leave with a working AI analyst system on your laptop (skills, agents, data connections) and a finished analysis ready for Monday.

Principal Data Scientist @ Ontra 

Shane Butler

Principal Data Scientist @ Ontra | Ex-Stripe, Nextdoor, PwC, Appfolio

Data Science Leader |Ex-Microsoft

Sravya Madipalli

Data Science Leader@Superhuman (Prev. Grammarly)| Ex-Microsoft, eBay, Nextdoor

Head of Data @ Ontra AI | Ex-LinkedIn

Hai Guan

Head of Data @ Ontra | Ex-Nextdoor, LinkedIn, Pinterest, Meta

Bootcamp 1

Bootcamp 2

**Please Note: Due to popular demand, price will go up by $300 after this cohort.This is a hands-on weekend bootcamp (4 hours Saturday, 4 hours Sunday) where you build AI analysts powered by Claude Code. Not a lecture series. Not a demo you watch. You set up your own environment, build custom skills and agents, connect to real data, and leave with a working system that turns business questions into charts, narratives, and presentations in minutes.No Python. No SQL. No coding of any kind. Claude Code writes all the code. You direct the analysis.By Sunday evening, you will have a complete AI analyst repo on your computer: 45 skills, 27 agents, data connections, and a finished analysis you can share with your manager Monday morning. Everything runs locally. No vendor lock-in. No proprietary platform. Just a repo you own.AI is changing how teams make decisions with data. The bottleneck is no longer the analysis — it is knowing how to set up the tools. This bootcamp gives you that setup in a weekend. You will not learn about agentic systems. You will build one.

Build agentic data analysts for your company in one weekend. No code.

Set up Claude Code as your personal AI analyst environment

Build custom skills that encode analytics best practices as markdown

 Build agents that automate multi-step analysis workflows

Produce a complete analysis with charts, narrative, and slide deck

Connect your own company data and analyze it before you leave

Product managers who are tired of waiting in the data team's queue. Stop waiting. Analyze it yourself.

Data scientists who want to multiply their output. You know how to do the analysis manually. Now automate it.

Engineers who want to make data-driven decisions without hiring a data team.

Raise the bar for your AI PM workflows. Live on Claude Code.

ex-Amazon Sr. PM, running 3 ventures

Esade

Typeform

Chargebee

Zoho

Gayathri Keerthana (GK)

Product & AI Consultant, ex-Amazon Sr PM (ML), running 3 ventures

Co-Founder, Level Up; $1B+ P&L; led 40+

Dentsu

Harvard Business Review

IPG Mediabrands

Techstars

Jason P. Yoong

Co-Founder & COO at Level Up (fmr Amazon, VP at Dentsu, Startup - $8M seed)

workshop-1

Most PMs are wondering "how to stay relevant in the AI-PM race."This is what we learned from over 15,000 product professionals who signed up for our <a target="_blank" rel="noopener noreferrer nofollow" href="https://maven.com/p/b062b8/raise-your-technical-bar-as-an-ai-native-pm">Lightning Lesson.</a>The real question for 2026 is how to go beyond PRDs and get closer to your leadership and engg teams.The answer is not prompt hacks or Claude tips, because they're not strategic enough to make your work look any different from the next PM's.In this 5h workshop, we teach how to produce AI PM artifacts using first principles:🔁 Working Backwards from customer problem to a product spec that engineering can directly build from. Then encode it into your CLAUDE.md so that your AI is context aware every session.🔍 Deep dive orchestrators that navigate fuzzy data and find real root causes. You save the day and present it right.📐Bar Raiser workflows that raise the quality of every AI output, from product specs to QBRs.🎯Agents that use the "8-persuasion factors", before any leadership review.We have seen these principles help scale startups and billion dollar orgs. We see what AI-enabled products are missing today.We will show you how to encode them in artifacts and agents using Claude Code.

Raise your bar as an AI-native product leader

Close the gap between product and engg

Become the Bar Raiser PM that defies AI slop

 You stop re-explaining context to your AI. Control token burn and hallucination

Finding the real root-cause and making it visible

LLM concepts underneath each framework

Every session runs inside Claude. Install Claude Code or Cursor before Session 1. A paid plan (Claude Pro/Max or Cursor Pro) is required.

Claude Code or Cursor installed on your computer

You'll build artifacts from your own context. Leadership reviews, problem scenarios, specs, planning docs, or a Notion/Drive export.



Example product docs, problems, and data you can work with

<pre><code class="language-markdown">Product People - anybody who wears the Product hat (not just PMs), want to raise their technical and quality bar. </code></pre>

<pre><code class="language-markdown">3–10 years in product or engineering; at least 2 years shipping features for a real customer base</code></pre>

<pre><code class="language-markdown">Mid-size, scale-up, or enterprise with an active AI product roadmap</code></pre>

You'll master basic and advanced skills in Claude Code for building and marketing products. 

AI PMM Leader, x-Google, Meta, Atlassian

Google

Microsoft

Atlassian

Databricks

Abhishek Ratna

Chief Product Officer - PMMSherpa | ex-Google, Meta, Microsoft, Atlassian

Batch 1

Most product and marketing teams treat Claude Code like a coding assistant. It isn't. It's a runtime for building AI products, instrumenting evals, and running go-to-market workflows that used to need a team of five.Over six weeks, you'll learn Claude Code from the ground up , then use it to build a working AI product and the agentic marketing system around it. No prior coding experience required.I'll teach you live using lessons from a real working AI product (PMMSherpa) used by 200+ users across 12 countries.What we'll cover:<ol><li>AI and Claude Code foundations: LLMs, agents, prompt engineering</li><li>Claude Code deep dive: CLAUDE.md, subagents, hooks, MCP</li><li>Evals: defining the right ones and instrumenting them in Langfuse</li><li>Designing your UX with Claude Code</li><li>Product marketing and GTM: Fortune 100 lessons from the Magnificent Seven</li><li>Building multi-agent marketing systems for your product</li></ol>You'll walk out completely comfortable building and marketing AI products with Claude Code. Learn from <a target="_blank" rel="noopener noreferrer nofollow" href="https://www.linkedin.com/in/abhishekratna">Abhishek Ratna,</a> a 16 year FAANG veteran in product and Go-to-Market (GTM), who has built and scaled AI products globally at Google, Atlassian, Meta, Microsoft and Databricks.

Build real AI products and ship agentic GTM workflows with Claude Code.

AI and Claude Code foundations

Claude Code Deep Dive

Evals

Fortune 100 lessons on Product Marketing and GTM

Building Multi-Agent Marketing Systems

Anyone who wants to build AI products with Claude CodeYou want to go from a basic familiarity to hands-on expertise

Product Marketers wanting to build AI systemsYou wish to master AI and Claude Code to 10x your outcomes

Technical founders/PMs wanting to shipYou need the full stack - product to GTM, and AI systems that make you win