Lenny's Newsletter
Intelligence extracted from Lenny's Newsletter newsletters.
7
Issues Tracked
15
Insights Extracted
5
Topics Covered
Topics
Key Insights from Lenny's Newsletter
**Sendbird** CEO John Kim built a gamified internal AI marketplace called Automators where employees complete 'quests' for automation tasks and earn XP redeemable for rewards, driving organic AI adoption.
**Sendbird** tracks token usage across five tiers—Beginner to AI God (100M+ tokens/day)—giving managers visibility into team AI fluency without tying it to performance reviews.
**Notion** uses spec-driven development as its core AI engineering workflow, as shared by Ryan Nystrom in a separate How I AI episode.
**Yash Tekriwal** built a custom AI-powered Slack inbox using **Perplexity Computer** that automatically categorizes and reduces 150 daily notifications to 30 actionable ones.
**Perplexity Computer** offers multi-model orchestration with cloud deployment and native connectors, eliminating technical overhead for non-engineers building automation tools.
**Claude Cowork** enables non-technical workers to automate daily workflows by creating reusable skills and brain files that teach AI individual working preferences and context.
**Al Chen** uses **Claude Code** to query **Galileo's** entire codebase across 15 repositories, reducing engineering interruptions to near-zero by self-serving customer technical questions
He maintains a 'customer quirks' **Confluence** page listing each enterprise customer's unique deployment requirements to make AI answers highly tailored and customer-specific
**Pylon** automatically converts detailed **Slack** support threads into knowledge base articles with one click, creating more current documentation than official docs
**Stripe** ships 1,300 AI-generated pull requests weekly using 'minions' triggered by **Slack** emoji reactions, with cloud dev environments enabling parallel AI workflows.
Latest issue: May 11, 2026
🎙️ How I AI: Quests, token leaderboards, and the elite AI adoption playbook & Notion’s spec-driven development
This edition of How I AI features two podcast episodes: John Kim (Sendbird CEO) shares his gamified internal AI adoption playbook using quests, token leaderboards, and a skills marketplace, and Ryan Nystrom discusses spec-driven development as Notion's AI engineering workflow. Key strategies include building secure app templates for non-technical builders, measuring token usage across tiers from Beginner to AI God, and treating internal tooling as a product rather than a top-down program.
🎙️ This week on How I AI: The internal AI tool that’s transforming how Stripe designs products
🎙️ This week on How I AI: GPT 5.5, Claude Design, and GPT Images 2.0 hands-on reviews—plus an inside look at Meme…
🎙️ This week on How I AI: Claude Cowork tutorial for non-engineers + Build your own Slack inbox (for $0)
This newsletter features two AI productivity episodes: Yash Tekriwal demonstrates building a custom AI-powered Slack inbox that reduces 150 daily notifications to 30 actionable ones using Perplexity Computer and OpenClaw, while JJ Englert shows how to use Claude Cowork to automate daily workflows without coding. Both episodes focus on building systems rather than just using AI for individual tasks.
🎙️ This week on How I AI: I gave Claude Code our entire codebase. Our customers noticed.
Al Chen from Galileo shares how he uses Claude Code to query their entire codebase across 15 repositories to answer enterprise customer technical questions without constantly pinging engineering. The episode covers his workflow for combining code repositories with Confluence and Slack to deliver accurate, real-time customer support.
🎙️ This week on How I AI: How Stripe built “minions”—AI coding agents that ship 1,300 PRs per week + How to turn …
This newsletter features two episodes from How I AI podcast covering AI coding agents at scale and personal productivity automation. The first episode explores how Stripe built AI 'minions' that ship 1,300 pull requests weekly from Slack reactions, while the second shows how Claude Code can serve as a personal life operating system.
🎙️ This week on How I AI: How Microsoft's AI VP automates everything with Warp
Microsoft's VP of Core AI Products, Marco Casalaina, demonstrates how he uses Warp, Microsoft 365 Copilot, and ChatGPT to build lightweight 'micro-agents' on the fly for tasks like document scanning, video compression, and Azure user management. The episode highlights how ad hoc agents are replacing complex permanent workflows, with CLI tools like NAPS2 and FFmpeg becoming more accessible through AI interfaces. Key examples include compressing a 1.7GB video to 13MB and automating two-sided document scanning without touching scanner software.