How I AI

→ WHAT IT COVERS Sharadh Krishnamurthy, engineering manager at Stripe, explains how a 1.5-person team built Kai, Stripe's internal AI agent, in two weeks. Now serving 10,000+ employees with under 10 staff, Kai combines personalized context, project-based governance, a shared skills platform, and agent-ready data infrastructure. → KEY INSIGHTS - **Project-Based Governance:** Structure enterprise AI around "projects" rather than individual sessions.

→ WHAT IT COVERS Host Claire reviews GPT-6 Astra after early access, demonstrating its capabilities across computer use, browser automation, coding, and 3D asset generation. She walks through five real builds—CRM workflow automation, thumbnail generation, hardware hacking, a product intelligence wiki, and a Blender fashion game—completed in days using the new model.

→ WHAT IT COVERS After several weeks of testing, the host replaced her entire OpenClaw agent stack with GrokBot, a multi-agent platform from xAI. She walks through six production bots covering chief-of-staff duties, family logistics, PR management, SOC 2 compliance, customer support, and personal shopping, detailing exact routines and plugin configurations.

→ WHAT IT COVERS Daniel Blum, PM at Melio, demonstrates his Claude CoWork system that self-improves over time through automated weekly and daily briefings, context-updating loops, and a company-wide onboarding workstation — enabling him to complete in one day what previously required a full week. → KEY INSIGHTS - **Self-Improving Context Files:** Structure Claude around dedicated context files for every work area — colleagues, goals, initiatives — then schedule a recurring task every few weeks...

→ WHAT IT COVERS Solo founder Ryan Carson details spending $20,000 in a single month on Devin, a cloud-based AI coding agent, while building Untangle, a B2B legal tech product for family law firms. He contrasts cloud versus local agent workflows, agent prioritization systems, and explains why human customer conversations remain irreplaceable for finding product-market fit.

→ WHAT IT COVERS Host reviews three releases from the Cursor/xAI ecosystem — GrokBot (a multi-agent desktop app), Origin (an agent-native GitHub competitor in early beta), and Grok 4.6 (a coding model) — testing each against real workflows and comparing outputs to GPT-5.6 and Claude Sonnet/Opus models. → KEY INSIGHTS - **GrokBot multi-account connectors:** GrokBot solves a persistent gap no competitor has addressed — connecting multiple accounts per service simultaneously.

→ WHAT IT COVERS Solo founder Yana Welinder built Yanabana, an AI-native fashion brand, using ChatGPT, Codex, and computer use as her entire technical team — replacing engineers, pattern makers, and production researchers — demonstrating how AI enables a single creative founder to execute a full fashion business end-to-end. → KEY INSIGHTS - **Prompt as product spec:** Develop a detailed master prompt that defines every dimension of your creative output — silhouette, fabric behavior,...

→ WHAT IT COVERS AI teacher and marketing consultant Grace Clark demonstrates how she built a client pipeline operator, branded HTML proposals, and a Gmail replacement using Claude Code — showing small business owners how to automate relationship-driven workflows through conversational prompting rather than technical expertise, running entirely on voice notes and mobile.

→ WHAT IT COVERS Host Claire demonstrates how to build an AI-powered pull request review bot using Vercel's Eve agent framework in under 30 minutes. The bot automatically scores PRs as low, medium, or high risk using a 100-point system, auto-approves low-risk changes, and escalates others to humans via Slack. → KEY INSIGHTS - **PR Auto-Approval at Scale:** Intercom's AI PR review system delivers 5x faster approvals than human reviewers while simultaneously reducing production revert rates.

→ WHAT IT COVERS Nick Baumann from OpenAI demonstrates advanced ChatGPT workflows including voice-activated multi-thread delegation, browser-based task automation, ChatGPT Sites deployment, and AI-powered video editing using Codex — showing how these combined primitives create an always-on assistant capable of managing complex parallel tasks hands-free.

→ WHAT IT COVERS Maddie Reese, a non-coder turned hardware hacker, demonstrates three AI-assisted physical computing projects built with Cursor and a Raspberry Pi: a web-to-thermal-printer messaging system, a Twitter-connected pager, and a personal API exposing her coffee order, pet names, and San Francisco restaurant preferences. → KEY INSIGHTS - **Hardware purchasing validation:** When buying physical components for AI-assisted projects, run at least three verification passes with your AI...

→ WHAT IT COVERS Host Claire reviews Claude Opus 5 using the How I AI benchmark — a 70/30 host-to-AI-judge scoring system across PRD creation, prototyping, wireframing, bug triage, and agentic coding — comparing it against GPT-5.6 Soul, Sonnet 5, Fable, Gemini 3.1 Pro, and Opus 4.8 across front-end design outputs. → KEY INSIGHTS - **Model personality as evaluation signal:** When raw intelligence across frontier models becomes difficult to differentiate, analyzing behavioral personality reveals...

→ WHAT IT COVERS Browser and computer use in Codex (ChatGPT desktop app) enables AI to control your mouse, keyboard, and Chrome browser to complete digital tasks autonomously. Five real-world examples span QA testing, persona-based UX research, LinkedIn inbox management, remote device control via iPhone mirroring, and personal online shopping. → KEY INSIGHTS - **Browser Use Setup:** Enabling AI computer control requires two components installed simultaneously — the ChatGPT or Claude desktop app...

→ WHAT IT COVERS Morning Brew founder Alex Lieberman demonstrates his Claude-powered content machine at his AI company 10x, walking through a five-step system — Oracle, research, interview panel, voice drafting, and writer's council — that generates non-generic LinkedIn and X posts by extracting the creator's own words rather than inventing AI-generated text.

→ WHAT IT COVERS Solo builder Alex Finn runs five to six local AI machines simultaneously — including three 512GB Mac Studios, a DGX Spark, and an RTX 5090 PC — to power 24/7 ambient AI workflows covering automated security scanning, code review, market research, and an autonomous software factory loop for his SaaS product. → KEY INSIGHTS - **Hardware selection framework:** Three local AI hardware tiers serve distinct purposes: Mac Studios (512GB unified memory) run frontier-level models like...

→ WHAT IT COVERS Host Claire runs a weighted benchmark — 70% personal taste, 30% LLM judge — comparing GPT-5.6 Sol, Terra, Luna, Claude Fable 5, and Sonnet 5 across PRD writing, prototyping, debugging, and agentic voice tasks, concluding that GPT-5.6 Sol outperforms Fable on practical output quality despite costing half the price. → KEY INSIGHTS - **Model pricing strategy:** GPT-5.

→ WHAT IT COVERS Host Christina Cacioppo demystifies the term "harness" by building a live Sentry bug-triage harness using the Claude Agent SDK, connecting it to Sentry, Vercel, Linear, and GitHub, and demonstrating how structured code around AI agents produces more consistent, controlled outcomes than general-purpose coding tools alone. → KEY INSIGHTS - **Harness definition:** A harness is simply code wrapped around an AI agent to make it more effective for a specific use case.

→ WHAT IT COVERS Alessio Fanelli, founder of Kernel Labs, demonstrates how he runs autonomous coding agents using OpenAI Symphony integrated with Linear as a state machine, managing engineering tasks entirely from his phone, and applies the same agentic approach to automate Pokemon card pricing and inventory sourcing for his San Carlos trading card store.

→ WHAT IT COVERS Host introduces the "How I AI Bench," a repeatable evaluation framework testing Claude Sonnet 5 against GPT-5.5, Gemini 2.5 Pro, Opus 4.8, and Sonnet 4.6 across 64 generations spanning PRD writing, UI prototyping, agentic coding, and voice personality tasks, revealing surprising model rankings. → KEY INSIGHTS - **Benchmark design:** Build repeatable AI evals using frozen inputs, blind scoring, and a structured rubric rather than one-off vibe checks.

→ WHAT IT COVERS Gusto CTO Eddie Kim describes how four engineers and one designer built Gusto Cofounder, a new AI-powered product line, in ten weeks with zero meetings, no Figma files, no Jira board, no tech specs, and no dedicated product manager — using only Claude Code and a permanent Zoom room. → KEY INSIGHTS - **Zero-documentation development:** Eliminate tech specs, Figmas, Jira boards, and stand-ups for zero-to-one builds.