How I AI

In this mini episode, I break down OpenAI’s new GPT 5.5 and GPT 5.5 Pro after weeks of early testing. I walk through three real jobs I threw at the model:  building an app for me to teach my second grader more advanced subtraction concepts, tackling a tech debt problem in the ChatPRD codebase, and hacking into a proprietary Bluetooth pixel display that every other model had failed me on. My verdict: higher intelligence, better efficiency, and genuinely autonomous long-running loops that change what I think is worth tackling.

What you’ll learn:
How I think about GPT 5.5 Pro’s pricing vs engineering time, and when I believe the “intelligence tax” is worth paying
Why I treat GPT 5.5 as a developer model first, and why I couldn’t find a consumer use case that justified its intelligence
The exact prompt pattern I use to unlock a long-running autonomous subagent loop
How I got a near-six-hour autonomous run to one-shot 98% of edge cases in a migration over millions of chat threads and drop my Sentry error rate to the floor
Why I’m now throwing GPT 5.5 at tech debt, flaky tests, and security backlogs first
How I combined a Bluetooth packet sniffer and GPT 5.5 to reverse-engineer a proprietary pixel speaker after Claude Code and GPT 5.4 both gave up
How I use the /personality command inside Codex to swap the default “baked potato” tone for something I actually enjoy working with
—
In this episode, I cover:
(00:00) Introduction to GPT 5.5 testing
(00:40) What is GPT 5.5 and how much does it cost?
(03:23) Testing GPT 5.5 in ChatGPT: the intelligence overhang problem
(07:12) Moving to Codex: where GPT 5.5 really shines
(16:01) Hacking a Chinese Bluetooth speaker
(21:47) Final thoughts on GPT 5.5’s intelligence and efficiency
—
Tools referenced:
• GPT 5.5 and GPT 5.5 Pro: https://openai.com/index/introducing-gpt-5-5/
• Codex: https://openai.com/codex/
• ChatGPT: https://chat.openai.com/
• Claude Code: https://claude.ai/code
• Sentry: https://sentry.io/
• Divoom MiniToo: https://divoom.com/products/minitoo
—
Other references:
• OpenAI Codex Security: https://openai.com/index/codex-security-now-in-research-preview/
—
Where to find Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].

In this mini episode, I do a full walkthrough of the AI design tools that dropped in April 2026: Anthropic’s new Claude Design, OpenAI’s GPT Images 2.0, and Google Labs’ open-source DESIGN.md format. I import a full design system from Lenny’s Newsletter, build a landing page, turn my own article into a polished deck, generate a brand kit for ChatPRD, and run a personal color analysis from a photo.

What you’ll learn:
How Claude Design handles design system imports and whether it can actually replace Figma
The three best use cases for Claude Design: marketing landing pages, slide decks, and creative redesigns
Why ChatGPT Images 2.0 is a breakthrough for brand kits and layout work
Google’s new DESIGN.md standard
The practical limits of AI design tools (spoiler: you’ll hit credit limits fast)
—
Brought to you by:
WorkOS—Make your app enterprise-ready today
Rippling—Stop wasting time on admin tasks, build your startup faster
—
In this episode, we cover:
(00:00) Welcome and what’s in the spring 2026 AI design drop
(01:45) Claude Design overview
(03:05) Importing Lenny’s Newsletter design system into Claude Design
(04:06) How Claude Design structures a design system
(05:42) Google Labs’ DESIGN.md standard
(06:41) Building Lenny Doc, a PRD generator landing page using the Lenny design system
(09:44) Why the three-variation output is Claude Design’s smartest UX choice
(10:20) Hitting the Claude Design limit and paying $200 to keep going
(11:05) Where Figma still wins
(13:20) Reviewing Lenny Doc
(16:19) Turning an Open Claude article into a branded slide deck
(17:57) The ’90s GeoCities “Lenny’s Product Zone” redesign
(19:44) Claude Design recap
(20:15) ChatGPT Images 2.0 and what makes it the first “thinking” image model
(21:25) Generating a multi-page brand kit for ChatPRD and iterating with reference images
(23:43) Personal color analysis demo
(26:02) Recap
—
Detailed workflow walkthroughs from this episode:
• How I Put Claude Design and GPT Images 2.0 to the Test: Building Landing Pages, Slides, and Brand Kits: https://www.chatprd.ai/how-i-ai/claude-design-and-gpt-images-2-building-landing-pages-slides-and-brand-kits
• How to Generate a Professional Brand Kit with GPT Images 2.0: https://www.chatprd.ai/how-i-ai/workflows/how-to-generate-a-professional-brand-kit-with-gpt-images-2-0
• How to Convert an Article into a Polished Slide Deck with AI: https://www.chatprd.ai/how-i-ai/workflows/how-to-convert-an-article-into-a-polished-slide-deck-with-ai
• How to Build a High-Fidelity Landing Page with Claude Design: https://www.chatprd.ai/how-i-ai/workflows/how-to-build-a-high-fidelity-landing-page-with-claude-design
—
Tools referenced:
• Claude Design: https://claude.ai/design
• ChatGPT Images 2.0: https://openai.com/index/introducing-chatgpt-images-2-0/
• Midjourney: https://www.midjourney.com/
—
Other references:
• Google’s DESIGN.md: https://stitch.withgoogle.com/docs/design-md/overview
• Lenny’s Newsletter: https://www.lennysnewsletter.com/
• Jamie Gannon “How I AI” episode on reference styles: https://www.lennysnewsletter.com/p/mastering-midjourney-how-to-create
• Brand prompt inspiration: https://x.com/riomadeit/status/2046682442791071787
• Figma team “How I AI” episode on design systems: https://www.lennysnewsletter.com/p/from-figma-to-claude-code-and-back
—
Where to find Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].

Brian Scanlan is a senior principal engineer at Intercom, where he’s led the company’s transformation to AI-first engineering. In just nine months, Intercom doubled their R&D throughput while maintaining code quality, with 100% of engineers—plus designers, PMs, and TPMs—now shipping code via Claude Code.

What you’ll learn:
How Intercom doubled their merged PRs per R&D employee in just nine months using Claude Code
The telemetry infrastructure they built to measure AI adoption and quality across hundreds of engineers
Why they built a skills repository with hooks that enforce engineering standards automatically
How they’re preparing their product for an agent-first world with CLIs, MCPs, and ephemeral APIs
The permission and accountability framework that enabled rapid AI adoption
Why backlog zero is now achievable and what that means for engineering culture
—
Brought to you by:
Celigo—Intelligent automation built for AI
Cursor—The best way to code with AI
—
In this episode, we cover:
(00:00) Introduction to Brian Scanlan
(02:40) Why Intercom went all-in on AI for both product and engineering
(05:01) The breakthrough moment with Opus 4.6 and Christmas break 2025
(07:02) Demo: Intercom’s merged PRs per R&D head
(12:50) Agent-first work as a fundamental reimagining of technical workflows
(14:27) The cost tradeoff: treating AI spend as an investment
(16:47) Measuring quality
(21:22) Demo: Shipping a redirect in the Rails monolith with Claude Code
(24:03) Creating a custom PR skill
(26:33) Building a software factory with predictable quality standards
(30:15) Telemetry infrastructure: Honeycomb for skill usage tracking
(32:10) Session data collection and personalized usage insights
(36:08) Quick overview
(39:20) Walking through Intercom’s skills repository
(42:16) Deep dive: The flaky spec skill and how it reached 100x capability
(46:44) The “and then” workflow for building comprehensive skills
(52:31) The live website and overview of workflows
(53:32) How internal AI experience informs customer product decisions
(56:18) Making SaaS products agent-friendly with CLIs and helpful hints
(01:03:49) Why conversion drop-off is invisible in agent-driven workflows
(01:05:28) Lightning round and final thoughts
—
Detailed workflow walkthroughs from this episode:
• How Intercom Doubled Engineering Output: Brian Scanlan's 4 AI Workflows for Claude Code: https://www.chatprd.ai/how-i-ai/how-intercom-doubled-engineering-output-brian-scanlan-ai-workflows-for-claude-code
• Design an Agent-Friendly CLI to Automate SaaS Product Onboarding: https://www.chatprd.ai/how-i-ai/workflows/design-an-agent-friendly-cli-to-automate-saas-product-onboarding
• Build a Self-Improving AI Agent to Automatically Fix Flaky Tests: https://www.chatprd.ai/how-i-ai/workflows/build-a-self-improving-ai-agent-to-automatically-fix-flaky-tests
• Automate High-Quality Pull Request Descriptions with a Custom AI Skill: https://www.chatprd.ai/how-i-ai/workflows/automate-high-quality-pull-request-descriptions-with-a-custom-ai-skill
—
Tools referenced:
• Claude Code: https://claude.ai/code
• Cursor: https://cursor.com/
• Honeycomb: https://www.honeycomb.io/
• Snowflake: https://www.snowflake.com/
• Fin AI: https://www.intercom.com/fin
• Vercel: https://vercel.com/
—
Other references:
• Intercom GitHub Repo: https://github.com/intercom
• Google API Go Client Repo: https://github.com/googleapis/google-api-go-client
—
Where to find Brian Scanlan:
X: https://x.com/brian_scanlan
LinkedIn: https://www.linkedin.com/in/scanlanb/
Company: https://www.intercom.com
—
Where to find Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].

JJ Englert leads community enablement at Tenex. In this episode, JJ provides a complete zero-to-one tutorial on Claude Cowork, Anthropic’s desktop tool that sits between simple chat and full terminal-based coding.

What you’ll learn:
How to create your first Claude Cowork project by connecting a folder on your computer and building context over time
The “brain” file strategy: how to create a preferences document that Claude reads every time to understand who you are and how you work
Why one-click connectors to Gmail, Slack, Notion, and Google Calendar unlock AI that actually does work instead of just suggesting it
How to analyze your sent emails to build a writing skill that perfectly matches your tone and style
The sub-advisory-board technique: spinning up three AI agents with different personas to review your work from multiple perspectives
How to set permissions for each connector so Claude only drafts (never sends) or always asks before taking action
The scheduled-task workflow that creates a morning debrief by reading your email, Slack, and calendar every day at 7:30 a.m.
Why projects with shared memory beat individual chat threads for consistent, high-quality AI outputs
—
Brought to you by:
Tines—Start building intelligent workflows today
Cursor—The best way to code with AI
—
In this episode, we cover:
(00:00) Introduction to JJ Englert
(02:48) What Cowork is and who it’s for
(05:49) Getting started: Opening the Cowork tab in Claude Desktop
(07:04) Understanding projects as folders on your computer
(07:54) Creating your “brain” file, with working preferences and context
(10:24) Demo: Building a daily operating system project from scratch
(12:18) How to prompt Cowork when starting a new project
(14:54) Understanding the project interface and shared memory
(18:37) Setting up connectors to Gmail, Slack, Google Calendar, and other tools
(21:00) Using connectors to analyze your emails and build personalized writing skills
(24:21) Creating a thinking-partner skill for decision support
(26:18) Cowork vs. OpenClaw
(27:18) Building a sub-advisory skill with multiple AI personas for feedback
(34:03) Advanced skill example: Multi-step newsletter creation with research and evaluation
(36:08) Setting up scheduled tasks for morning debriefs
(37:57) Going beyond one-off tasks with AI
(41:00) Progressive trust and the tradeoff of information for productivity
(44:08) Different use cases beyond work productivity
(46:08) Lightning round
—
Tools referenced:
• Claude Code: https://claude.ai/code
• Wispr Flow: https://whisperflow.ai/
• Monologue: https://www.monologue.to/
• Domo: https://www.domo.com/
• Pencil.dev: https://pencil.dev/
• Remotion: https://www.remotion.dev/
• Obsidian: https://obsidian.md/
• OpenClaw: https://openclaw.com/
• Notion: https://notion.so/
—
Other references:
• Get Started with Claude Cowork: https://support.claude.com/en/articles/13345190-get-started-with-cowork
—
Where to find JJ Englert:
YouTube: https://www.youtube.com/channel/UCv2ovDhYVtlJw4QMidLFP8Q
X: https://twitter.com/jjenglert
LinkedIn: https://www.linkedin.com/in/jj-englert-a08836a6/
—
Where to find Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].

Yash Tekriwal is the head of education at Clay. A self-described hyper-optimizer, Yash has built multiple custom productivity applications using Perplexity Computer and OpenClaw to manage his overwhelming daily workflow—including a Slack digest system that categorizes over 150 daily notifications into actionable priorities, and a consolidated news/email/Slack dashboard that serves as his personal command center.

What you’ll learn:
How Yash built a custom Slack digest that categorizes 150+ daily notifications into action-required, need-to-read, and FYI buckets
Why Perplexity Computer beats Claude Code and Codex for building personal productivity apps
His “anti-to-do list” framework: spending an hour daily automating tasks you never want to do again
How to use AI for deterministic tasks (APIs, structured data) vs. subjective tasks (categorization, summarization)
Why the SaaS apocalypse narrative is wrong—and why we’re about to see an explosion of micro-software
How his team uses Perplexity Computer to prototype design systems and communicate with cross-functional partners
—
Brought to you by:
Guru—The AI layer of truth
ThoughtSpot—Build AI-powered analytics into your product
—
In this episode, we cover:
(00:00) Introduction to Yash
(02:38) The burden of 150 daily Slack notifications
(05:45) When to use AI for tasks vs. building deterministic code
(06:38) Building the Slack digest with OpenClaw
(11:33) Introducing Perplexity Computer and the visual dashboard
(14:28) Three reasons Perplexity Computer beats Claude Code
(16:14) Using connectors to automate meeting follow-ups across Notion and Asana
(18:21) The Kanban-style Slack dashboard
(20:15) The long tail of customer requests and the future of micro-software
(24:09) The anti-to-do list framework
(26:21) Building a consolidated news, email, and Slack digest
(29:48) How Perplexity Computer handles authentication and deployment
(31:46) Team use case: Prototyping persona-based learning journeys for Clay University
(35:49) Lightning round and final thoughts
—
Tools referenced:
• Perplexity Computer: https://www.perplexity.ai/computer/new
• OpenClaw: https://openclaw.ai/
• Discord: https://discord.com/
• Claude Code: https://claude.ai/code
• Codex: https://openai.com/codex/
• Asana: https://asana.com/
• Airtable: https://airtable.com/
• Figma: https://www.figma.com/
• Vercel: https://vercel.com/
• ChatGPT: https://chat.openai.com/
—
Other references:
• Slack: https://slack.com/
• Notion: https://www.notion.so/
• Superhuman: https://superhuman.com/
• Clay University: https://www.clay.com/university
• Kanban boards: https://en.wikipedia.org/wiki/Kanban_board
—
Where to find Yash Tekriwal:
LinkedIn: https://www.linkedin.com/in/yashtekriwal/
X: https://x.com/yash_tek
Company: https://www.clay.com/
—
Where to find Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].