How I AI

→ WHAT IT COVERS Claire Vaux reviews GPT-5.5 and GPT-5.5 Pro after two weeks of early access testing, focusing on Codex-based autonomous coding tasks. She demonstrates three real-world use cases: security remediation, a 2-million-row data migration, and reverse-engineering a proprietary Bluetooth device — comparing results against Claude and GPT-5.4. → KEY INSIGHTS - **GPT-5.5 Pricing vs. ROI:** GPT-5.

→ WHAT IT COVERS Host Clervoe evaluates Claude Design, Anthropic's new web-based design tool, testing its design system import feature, marketing landing page generation, and slide deck creation, while also assessing OpenAI's GPT Image 2 model for brand kit generation and layout work across a 27-minute hands-on demo. → KEY INSIGHTS - **Claude Design best use case:** Claude Design performs strongest on marketing landing pages and slide decks rather than complex UX/app components.

→ WHAT IT COVERS Brian Scanlan, Senior Principal Engineer at Intercom, details how the company doubled engineering throughput (measured in merged PRs per R&D head) over nine months using Claude Code. He demonstrates the internal skills repository, telemetry infrastructure, session analysis tooling, and cultural frameworks that enabled a 150+ person R&D organization to ship at 2x velocity while maintaining or improving code quality.

→ WHAT IT COVERS JJ Englert from Tenex demonstrates how non-technical professionals can use Claude Cowork to build a personal daily operating system — connecting Gmail, Slack, and Calendar through one-click integrations, creating reusable skills, and orchestrating multiple AI agents simultaneously without writing a single line of code. → KEY INSIGHTS - **Project Architecture:** Create a dedicated folder on your computer, attach it to a Claude Cowork project, and add a "brain" file — a detailed...

→ WHAT IT COVERS Al Chen, field engineer at Galileo, demonstrates how non-engineers can clone all 15 of a company's repositories into VS Code, then use Claude Code to answer nuanced enterprise customer deployment questions that public documentation cannot address, while building customer-specific context libraries in Confluence to personalize technical responses.

→ WHAT IT COVERS Entrepreneur and new mom Hilary Gridley demonstrates how she uses Claude Code via terminal to manage her daily schedule, to-do list, and personal workflows — building an adaptive, low-setup "anti-system system" that learns from observed behavior rather than pre-configured rules or complex integrations. → KEY INSIGHTS - **Automation Decision Framework:** For any task, ask whether being 10x better at it would produce 10x the impact. If no, automate it entirely.

→ WHAT IT COVERS Stripe engineer Steve Kaliski explains how Stripe built "Minions" — AI coding agents triggered by Slack emoji reactions — that generate 1,300 pull requests weekly with no human involvement beyond code review, and demonstrates a second system where Claude agents transact with real third-party services using machine-to-machine payments.

→ WHAT IT COVERS Microsoft VP Marco Casalaina demonstrates five micro-agent workflows using Warp terminal, showing how CLI-based AI agents handle Azure role assignment, document scanning, video compression, calendar scheduling, and podcast monitoring — reducing administrative friction without requiring formal prompting or complex automation setup. → KEY INSIGHTS - **CLI-First Agent Strategy:** Warp excels at any task with a command-line interface, not just coding.

→ WHAT IT COVERS LinkedIn editor Daniel Roth, a career journalist with zero software engineering background, demonstrates his Claude Code workflow for building and shipping iOS apps to the App Store. He uses two named AI agents — Bob the builder and Ray the reviewer — operating across dual terminal tabs to produce production-grade code on weekends. → KEY INSIGHTS - **Dual-agent review system:** Run two separate Claude Code instances in parallel terminal tabs with distinct personas: Bob handles...

→ WHAT IT COVERS Figma engineers Gui Seiz and Alex Kern demonstrate bidirectional workflows between Figma and Claude Code using the Figma MCP server, showing how design and code can stay synchronized without manual handoffs, enabling designers and engineers to collaborate on live states rather than static artifacts. → KEY INSIGHTS - **Figma MCP as sync bridge:** Use the Figma MCP server connected to Claude Code or Codex to programmatically pull live app states directly into Figma frames.

→ WHAT IT COVERS AI creative director Jamey Gannon demonstrates a repeatable Midjourney workflow for generating consistent brand imagery using style references, personalization codes, and mood boards — replacing traditional agency retainer models with a client-empowering system that delivers reusable prompt packages and reference codes. → KEY INSIGHTS - **Style References Over Mood Boards:** When Midjourney mood boards produce inconsistent results, switching to individual SREFs (style...

→ WHAT IT COVERS Chintan Turakhia, Senior Director of Engineering at Coinbase, details how he drove Cursor AI adoption across 1,000+ engineers by leading hands-on, running company-wide PR speed runs, and building custom Slack-based agents that compress the full cycle from user feedback to shipped code. → KEY INSIGHTS - **Leadership by demonstration:** Engineering leaders who mandate AI tool adoption without personal hands-on usage fail.

→ WHAT IT COVERS Jesse Genet, mother of four and homeschool parent, runs five separate OpenClaw agents on dedicated Mac minis to manage homeschooling curriculum, personal finances via QuickBooks, coding projects, scheduling, and household inventory — demonstrating how AI agents can restore productive capacity to time-constrained parents without requiring technical expertise.

→ WHAT IT COVERS Brian Levin, designer at Notion AI, demonstrates how he built a shared Next.js prototype playground for Notion's design team, enabling code-first prototyping via Claude Code. The system uses shared components, Claude slash commands, skills, and MCP integrations to help 5–10 designers prototype directly in the browser without writing code manually. → KEY INSIGHTS - **Shared Prototype Repository:** Build a single Next.

→ WHAT IT COVERS Joe McCormick, principal software engineer at Babylist with Leber's hereditary optic neuropathy, demonstrates building Chrome extensions with Claude Code to improve accessibility. He creates tools like image description for Slack messages, spell checkers, and link summarizers in under 25 minutes each, using keyboard shortcuts, screen readers, and custom Claude skills to streamline his workflow.

→ WHAT IT COVERS Claire Vaux tests OpenAI's GPT-5.3 Codex and Anthropic's Claude Opus 4.6 models side-by-side on real coding tasks, shipping 93,000 lines of code across 44 pull requests in five days. She evaluates their strengths for redesigning marketing sites and refactoring complex codebases, revealing distinct use cases for each model. → KEY INSIGHTS - **Model pairing workflow:** Use Claude Opus 4.

→ WHAT IT COVERS CJ Hess demonstrates his custom AI development workflow using Claude Code, including Flowy, a self-built tool that converts JSON specifications into visual flowcharts and UI mockups. He shows how he uses model-to-model comparison with GPT Codex to review Claude's code, creates custom skills for automation, and bypasses permissions to accelerate development cycles.

→ WHAT IT COVERS Vercel CEO Guillermo Rauch demonstrates v0's new Git workflow integration that enables non-engineers to create production-ready code changes through natural language prompts, open pull requests, and deploy to preview environments—transforming how marketing, design, and engineering teams collaborate on web applications at scale. → KEY INSIGHTS - **Git workflow integration:** V0 now creates branches directly from the interface using standard naming conventions...

→ WHAT IT COVERS Reid Robinson, Product Manager at Zapier, demonstrates how Model Context Protocol servers transform AI tools into automated assistants for customer-facing work. He shows practical implementations using Claude Projects with Zapier's 8,000-app MCP platform to automate CRM updates, meeting preparation, and customer feedback synthesis while maintaining data quality through human-in-the-loop workflows.

→ WHAT IT COVERS Claire Vo tests ClaudeBot (MoltBot), an open source autonomous AI agent with computer access, by giving it control of her calendar, email, and desktop. She documents installation challenges, security concerns, workflow experiments including scheduling and research tasks, and evaluates whether autonomous agents are ready for consumer or enterprise use beyond developer experimentation.