Amplitude

They didn’t come to dribble... they came to pitch 🏀 The National Basketball Association (NBA) Foundation’s All-Star Pitch Competition spotlighted seven LA founders building startups that advance social and economic opportunity, with the winner receiving $400K in cash prizes. Amplitude is proud to help support the innovators changing the game 💙 https://lnkd.in/ewHg48x7

Two types of PMs are emerging from the same AI tooling wave. The first group treats Claude Code and MCP as research assistants. They ask questions, get answers, copy-paste insights into their existing docs and slide decks. Their workflow is the same, just slightly faster. They're still writing PRDs from scratch, still manually scanning dashboards, still spending Sundays on WBRs. The second group rebuilt their entire operating system around it. Frank Lee has skills that trigger specific analytical workflows with one slash command. His dashboard agents push reports before he wakes up. His feedback analysis runs across Zendesk, Gong, Salesforce, Slack, and app stores in a single prompt. His PRD drafts come from analyzed product data, not blank templates. And when the spec is ready, he routes it to Linear or prototypes it in Cursor without context-switching. Same tools. Completely different outcomes. The gap between these two groups compounds every single week because the second group is automating away the manual work that the first group is still accelerating incrementally. Here's how to be in group two: 1. Frank's Workflow: https://lnkd.in/geK3sBrr 2. My Claude Code OS: https://lnkd.in/gsH9RSfJ 3. Claude Code Tutorial: https://lnkd.in/eUyPEAma 4. Advanced Claude Code: https://lnkd.in/gvA6rZtX 5. Steal my Claude Skills: https://lnkd.in/eZyJzMnH The best time to build your PM OS was six months ago. The second best time is this weekend.

👎 Out: Digging through dashboards 👍 In: AI analytics Join Amplitude's Jacob Newman, Frank Lee, James Evans, William Newton, and Eric Carlson to see how our AI agents are changing the way teams build products. Save your spot: https://bit.ly/4rAzPQZ

Spotted: Krista Seiden and Jim Kultgen at Superweek Analytics Summit 👀 They spent the week in Hungary talking analytics, AI, and the evolving role of the analyst. 'Till next year!

Vibe coding changed engineering. Vibe PMing with Claude Code just changed PM. Today I'm releasing an episode with a principal PM at Amplitude who builds MCP and agent products for a living. Frank Lee shows, live on screen, what happens when you connect Claude Code directly to your analytics platform, your ticket system, and your customer feedback tools. 🎥 YouTube: https://lnkd.in/gU-kNePG 🎧 Apple: https://lnkd.in/eCYGNTdG 🟢 Spotify: https://lnkd.in/eyt7agKj ✍️ Substack: https://lnkd.in/gzpDgttx The agent parsed a chart URL, pulled the underlying data, cross-referenced customer feedback, checked feature flag changes, and returned a structured analysis. What would take a data analyst three hours took 90 seconds. Then he took that analysis, combined it with screenshots of the current product experience, and had Claude Opus brainstorm the solution. Two rounds of feedback later, a full PRD drafted in his team's template. Twenty minutes, start to finish. The workflow that killed me: automated Monday business reviews. You point a dashboard agent at the five dashboards you care about. Every Monday morning, a clean report hits your inbox with the top insights, week-over-week changes, and the one urgent thing that needs attention. At Epic Games, I spent three to five hours every Sunday pulling those metrics manually. We walked through five complete workflows: 1. Deep chart analysis (90-second root cause investigations) 2. Automated dashboard reporting (kills the Sunday night ritual) 3. Customer feedback synthesis (clusters Zendesk, Gong, NPS, app reviews) 4. Insight to spec (analysis becomes PRD in 20 minutes) 5. Spec to shipped (PRD becomes Linear ticket or merged PR) This is vibe PMing. You describe the problem. The agent pulls the data, synthesizes the feedback, drafts the spec, and files the ticket. The PMs who wire this up in the next six months are going to operate at a level that's hard to compete with manually. Brought to you by: Amplitude: https://lnkd.in/gncCbk7G Pendo: http://www.pendo.io/aakash Testkube: https://testkube.io Product Faculty: https://lnkd.in/eZ2uUySG Bolt: http://bolt.new/aakash Follow Aakash Gupta for daily AI PM workflows.

Custom Agents 🤝 your entire stack. They watch, triage, prep, schedule, and follow up. So you don't have to. What they can do with MCP: Capture brainstorms from Figma FigJam, extract sticky notes and annotations, and turn them into structured Notion pages. Sync workflows and issues from Linear, pull context from multiple sources, and generate recurring reports. Pull spend and vendor data from Ramp, track renewals, and stay on top of expenses automatically. Monitor Slack channels for requests, extract action items from threads, and route messages to the right workflows automatically. Query Amplitude for product usage data, track feature adoption, and answer engagement questions without leaving Notion. Pull revenue data from Stripe, search docs, track MRR and churn, and generate weekly reports for exec review. Surface errors and crashes from Sentry, track issue frequency, and route critical bugs to the right team before users notice. Sync contacts and deals from Attio, enrich records with context from other tools, and keep your CRM up to date automatically. Read incoming GitHub issues, categorize by type and severity, and route bugs to the right team automatically, without manual triage. Query Wiz for cloud security data, surface vulnerabilities, and answer compliance questions on the fly. Pull leads and pipeline data from HubSpot, track deal progress, and generate reports for sales reviews. Monitor conversations from Intercom, surface common issues, and route support trends to product teams automatically.

We get it, we're builders too 🤝 We know the pain of trying to translate dashboards into features, session replays into UI changes, and drop-offs into experiments. So we built the products to help you build better: https://lnkd.in/exApjEBM

Meet the newest member of your data team 🤝 We partnered with Notion to bring Amplitude analytics into Notion Custom Agents. Think of it as your new AI teammate that can summarize charts, spin up insights, and drop real product data into your notes and PRDs. Try it out: https://lnkd.in/ext3sSFE