How Coinbase Scaled AI to 1,000+ Engineers | Chintan Turakhia
Coinbase engineering leader Chintan Turakhia says the company has successfully scaled AI across a 1,000+ engineer organization to boost velocity and rebuild a major consumer-facing app under an aggressive six- to nine-month timeline. Adoption succeeded after leadership became hands-on with tools, demonstrated practical use cases, and drove daily experimentation rather than mandate-only rollouts. Early tooling flopped for some engineers, so the team focused on making AI “stick” by integrating it into everyday coding, debugging, and operational workflows. The shift also changes leadership expectations toward fewer meetings and more coding and tool-driven mentoring.
Physical Partitioning Is a Real Security Strategy for OpenClaw Agents
The video explains a security‑first approach to managing OpenClaw agents by physically partitioning their access and responsibilities. The creator has instantiated multiple agents—Sylvie for homeschooling content and Finn for accounting—each confined to its own “family vault,” ensuring that data never...
Claude Skills Let You Fix Root Problems, Not Just Patch Symptoms
The video demonstrates how Claude’s custom “skill” framework can be used to address fundamental AI‑generated errors rather than merely patching symptoms. The presenter describes a recurring problem where the model labels UI icons with the most obvious name—e.g., “search icon”—even...
5 OpenClaw Agents Run My Home, Finances, and Code | Jesse Genet
Jesse Genet, a homeschooling parent and entrepreneur, runs five specialized OpenClaw AI agents on separate Mac Minis, layered over her Obsidian “second brain.” Each agent handles a distinct domain—homeschool, finance, scheduling, development, and operations—allowing automated lesson‑plan generation, rapid app development,...
5 OpenClaw Agents Run My Home, Finances, and Code | Jesse Genet
In this episode, host Claire Vo talks with homeschooling mother and AI enthusiast Jesse Genet about how she uses five OpenClaw agents on multiple Mac minis to automate her family’s homeschooling, finances, and personal workflows. Jesse explains how she layered...
Notion’s Prototype Playground
The video introduces Notion’s internal tool called Prototype Playground, a centralized repository where engineers and designers post their Next.js prototypes. By listing each prototype chronologically and by author, the platform gives the entire product team a single pane of glass...
“I Haven’t Written a Single Line of Front-End Code in 3 Months”: Notion’s Prototype Playground
Notion’s design team, led by Brian Lovin, launched a shared Next.js prototype playground powered by Claude Code, allowing designers to build and iterate functional prototypes without writing front‑end code. The environment replaces isolated repos and static Figma mockups with collaborative,...
Building a Custom Chrome Extension Using Claude Code
The video demonstrates how to create a lightweight Chrome extension using Claude Code that activates within Slack, captures any external URLs in a focused message, and initiates an automated workflow. When the user presses Ctrl‑Shift‑1, the extension opens each link in...
Use Model-to-Model Comparison to Improve Code Quality
The video discusses leveraging a model‑to‑model comparison workflow—specifically using Codeex to review code generated by Claude—to elevate overall code quality. Rather than relying solely on Claude’s output, the presenter treats Codeex as a QA layer that flags not only logical...
Skills Are the Secret to Making Claude Work with Your Custom Tools
The video explains how developers can create custom "skills" that teach Anthropic’s Claude to understand and manipulate proprietary development tools, such as flowchart generators and UI mockup utilities. By embedding themselves in the tool’s repository and iteratively crafting examples, they...
Claude Opus 4.6 vs GPT-5.3 Codex: Which Is the Better Software Engineer?
The article pits OpenAI’s GPT‑5.3 Codex against Anthropic’s Claude Opus 4.6 (and the faster Opus 4.6 Fast) in a real‑world engineering sprint. By redesigning a marketing website and refactoring complex components, the author shipped 44 pull requests, 98 commits across 1,088 files in...
D0: Vercel's Data Analysis Agent
Vercel showcased its AI‑powered data analyst assistant, DZ, highlighting a dramatic surge in pull‑request merges linked to the new Vzero integration. In a live demo, the agent reported that merged PRs jumped from near zero in early January to roughly...
AI Can Be Your "Always-On Team" That Works While You Sleep
The video showcases how AI can serve as an “always‑on team,” automatically gathering and presenting customer intelligence while the user sleeps. Using Databricks as a data lake, the speaker built a workflow that, given an email address, pulls a comprehensive profile—company...
Build Custom CLI Tools for Your Specific AI Workflows
The video showcases a custom command‑line interface, dubbed Sketch, that acts as a wrapper around Google’s Gemini model to streamline specific AI‑driven web design tasks. By feeding structured prompts—such as building a Christmas‑decorations store with a GitHub‑light theme—the CLI orchestrates...
How to Safely Delegate Calendar Scheduling to Clawdbot (Moltbot)
The video documents a user’s attempt to hand over family calendar management to an AI assistant, Clawdbot (Moltbot), by granting it edit permissions and issuing scheduling commands through Telegram. While the bot could read and categorize events, it lacked awareness of...
Clawdbot as an Executive Assistant
The video demonstrates a founder’s experiment using Claude bot as a virtual executive assistant, assigning it a separate email address and read‑only access to his personal calendar to test how closely it can mimic a human EA. By granting only read...
I Gave Clawdbot (Now Moltbot) Access to My Computer, Calendar, and Emails: Here’s What Happened
The episode documents a hands‑on trial of Claudebot—now renamed Moltbot—an open‑source AI agent that can act on a user’s desktop, calendar and email. The host invites the bot into a Riverside podcast via Telegram, then walks through granting microphone, camera...
Context and Diagrams Are the Best Way to Get AI to Do What You Want
The video explains how providing explicit context—particularly through visual diagrams—enables large language models to perform code‑related tasks more accurately. It argues that AI agents start each session with a blank slate, unaware of the relationships between components in an application,...
Use an Index File Strategy to Help AI Discover Relevant Context
The video explains how the creator uses an index‑file strategy—organizing prompts and reference material in an Obsidian vault—to give Claude, an Anthropic language model, richer context for every interaction. By feeding Claude a comprehensive writing style guide that the model helped...
Automating Academic Research with Claude
The video showcases a workflow built around Claude, an AI assistant, to automate the daily hunt for new academic papers on a pre‑print server. By instructing Claude to run a routine search each morning, the user receives a markdown file...
Claude Code for Product Managers: Research, Writing, Context Libraries, Custom To-Do System, and More | Teresa Torres
In this episode, Teresa Torres walks listeners through how she transformed her productivity by building a custom task‑management system in Claude Code, moving from Trello to a markdown‑driven workflow integrated with Obsidian. She demonstrates automating daily research digests, organizing context...
Automated Code Review Has Become OpenAI's Most Widely Adopted Codex Feature
The video highlights OpenAI’s Codex automated code‑review feature, now the platform’s most widely adopted capability. By typing a simple "/review" prompt, developers can trigger a full‑stack analysis of their code without any GitHub integration, and the model adopts a reviewer...
"With Coding Agents, It Doesn't Get Easier, but You Just Move Way Faster."
The video showcases how coding agents such as Codex can automatically generate a self-contained, milestone-driven plan stored in a markdown file, shifting developers from manual outlining to AI-assisted planning. By feeding the specification into a prompt, the agent produces a roughly...
“A Full Software Engineering Teammate”: OpenAI Product Lead on Getting the Most Out of Codex | Alexander Embiricos
In this episode, OpenAI Codex product lead Alexander Embiricos walks listeners through practical workflows for using Codex—from simple VS Code prompts to parallel coding with Git worktrees and detailed implementation plans via a Plans.md approach. He shares how OpenAI built the...
Extract Your "Unspoken Culture" From Meeting Data
The video showcases how Granola’s AI can turn raw meeting recordings into an “unspoken culture handbook,” automatically summarizing how a company actually operates based on conversational data. By feeding months of transcript data into a single prompt, the tool surfaces concrete...
Using Grok to Find "Diamonds in the Rough" Talent
The video demonstrates how recruiters can leverage the AI‑driven platform Grok to surface under‑the‑radar social‑media creators who align with niche topics such as Zapier, no‑code, agent building, automation, and music. By issuing a natural‑language prompt—e.g., “find X posters who are fans...
Zapier's CEO Shares His Personal AI Stack | Wade Foster
Wade Foster, co‑founder and CEO of Zapier, joins the How I AI podcast to walk through his personal AI stack and demonstrate how the company embeds artificial intelligence into everyday workflows. He argues that leadership must go beyond memos about...
Preparing for a Business Dinner with the Help of AI
The video demonstrates how an executive used generative AI to prepare for a CXO Collective dinner. By taking a screenshot of the guest list and feeding it into an AI agent, the system automatically searched the web and LinkedIn for...
How Webflow’s CPO Built an AI Chief of Staff to Manage Her Calendar, Prep for Meetings, and Drive AI Adoption...
In this episode, Webflow CPO Rachel Wolan explains how she built a custom AI "chief of staff" that syncs with her calendar, email, and other tools to triage tasks, prep for meetings, and give candid feedback on her time usage....
Interactive Sessions Beat Presentations Every Time
The video argues that interactive sessions consistently outperform traditional slide‑based presentations, using a live, hands‑on demo to illustrate the point. The presenter walks the audience through a simple exercise on bolt.new, asking everyone to copy‑paste a prompt that generates a...
If You're Doing a Repeated Task Every Week, Spend that Time Automating It Instead
The video introduces Exec Prep GPT, a generative‑AI assistant built to automate the preparation and feedback of “tee‑up” documents that executives use to surface decisions. The presenter feeds the model a deliberately weak tee‑up—lacking clear purpose, approver, and background—to showcase how the...
Automate Your Weekly Meeting Prep with AI Agents
The video introduces an AI‑driven workflow designed to automate the preparation for weekly meetings by acting as a personal “second brain.” The presenter explains that the agent first scans the user’s calendar, flags meetings that require advance work, and then...
Transform Static Research Into Interactive AI Personas
The video showcases a new AI-driven platform that converts static market research into dynamic, conversational personas capable of interacting 24/7. By feeding research data into the system, marketers can generate distinct virtual characters—such as “Balanced Blake” and “Aiden”—that embody the...
How to Create Your Own AI Performance Coach: Optimizing Your Unique Nutrition, Recovery, and Injury Management Needs | Lucas Werthein...
Lucas Werthein, COO and co‑founder of Cactus, explains how he built a personalized AI wellness coach using ChatGPT that integrates medical imaging, blood work, wearables and nutrition data to protect his joints, speed recovery, and sustain peak athletic performance despite...
“Farm-to-Table Software”: How I Built a Thanksgiving Party Hub Using Lovable for Managing Invites, Dishes, Shared Recipes, and Photos
In this pre-Thanksgiving episode, the host demonstrates how they built a custom Thanksgiving party hub in Lovable, covering guest management, dish tracking, recipe sharing, and photo galleries. They detail the process of refining AI‑generated designs with Google Fonts, Tailwind, and...
“Nobody Wanted to Do This Work”: How Emmy Award–Winning Filmmakers Use AI to Automate the Tedious Parts of Documentaries
In this episode, Tim McAleer, a technology lead at Ken Burns’s Florentine Films, explains how he built custom AI tools that automate the most labor‑intensive parts of documentary production, from extracting metadata and OCR’ing historic documents to creating searchable vector...
