Inside $180B Co-Founder's AI Agent System

I sit down with Alex Finn to break down how he sets up Moltbot (formally Clawdbot) as a proactive AI employee he treats like a teammate named Henry. We walk through the core workflow: Henry sends a daily morning brief, researches while Alex sleeps, and ships work as pull requests for review. Alex explains the setup that makes this work; feeding the bot deep personal and business context, then setting clear expectations for proactive behavior. We cover model strategy (Opus as “brain,” Codex as “muscle”), a “Mission Control” task tracker Henry built, hardware options, and the security mindset around prompt injection and account access. Timestamps 00:00 – Intro 02:08 – Clawdbot Overview 03:33 – The Morning Brief Workflow 05:01 - Proactive Builds: Trends → Features → Pull Requests 07:27 – The Setup: Context + Expectations For Proactivity 09:38 – The Onboarding Prompt Alex Uses 12:05 – Hunting “Unknown Unknowns” For Real Leverage 12:43 – Using the right Models for cost control 14:18 – Mission Control: A Kanban Tracker Henry Built 17:16 – The future of Human and AI workflow 22:01 – Hardware And Hosting: Cloud vs Local (Mac Mini/Studio) 25:47 – The Productivity Framework 27:10 – The Possible Evolution of Clawdbot 28:53 – Security and Privacy Concerns 33:38 – Closing Thoughts: Tinkering, Opportunity, And Next Steps Key Points I get the most leverage when I treat the agent like a proactive teammate with clear expectations and rich context. Henry delivers compounding value by shipping work for review (pull requests) based on trend monitoring and conversation memory. I separate “brain” and “muscle” by delegating heavy coding to Codex while using Opus for reasoning and direction. I track autonomous work with a dedicated “Mission Control” board so progress stays visible over time. I keep risk contained by controlling environment and account access, especially around email and prompt injection. The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/ FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND ALEX ON SOCIAL Youtube: https://www.youtube.com/@AlexFinnOfficial/videos X/Twitter: https://x.com/AlexFinnX Creator Buddy: https://www.creatorbuddy.io/

I sit down with Furqan Rydhan, a founding team member of Applovin and cofounder Founders Inc, as he walks me through Nebula, a Slack-like workspace where every channel holds an agent that can execute real work across the tools teams already use. We watch Nebula create and edit a Google Slides deck end-to-end, including generating an image and handling failures by retrying until it lands. Furqan shows how Nebula turns one-off work into repeatable “recipes” with scheduled triggers, like adding slides daily or publishing blog posts multiple times per day. We also talk about what “business-in-a-box” looks like in the AI era; where direction, taste, and quality loops become the edge as automation gets widely available. Timestamps: 00:00 – Intro 01:51 –Building useful agents for real work 03:34 – Nebula: a Slack-like agent workspace 05:04 – Demo: Nebula creating a Deck with Google Slides 13:25 – The “business in a box” content dream (newsletters, affiliates, ads) 14:39 – Demo: Automate Blog Posting 15:52 – What stays valuable when everyone automates 21:23 – Agent workforce and Building quality loops 25:38 – Services and agencies: delivering work with fewer humans 28:53 – Final Thoughts Key Points I watch Nebula run like “cloud code for everything else,” automating real work across tools and workflows. Agents turn one-time actions into repeatable systems via triggers and schedules. The interface mirrors Slack because work already lives in channels, threads, and context. Quality becomes the differentiator: critics, scoring, and iteration loops upgrade outputs over time. Service businesses and agencies scale faster when agents handle production-heavy tasks The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/ FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND FURQAN ON SOCIAL Furqan's X: https://x.com/FurqanR Fuqan’s personal website: https://furqan.com Nebula: https://www.nebula.gg

In this episode, I sit down with Boris, the creator of Claude Code and one of the key builders behind Claude Cowork, to unpack what Cowork actually unlocks and how people use it in the real world. He walks through a hands-on demo where Cowork organizes files, extracts receipt data, builds a clean spreadsheet, and even drives the browser to create and share a Google Sheet. We go deep on how “agentic” work feels different when the model takes actions across your computer, your browser, and your tools. Then I shift into Boris’s viral workflow for Claude Code: parallel sessions, plan-first execution, Claude.md as a compounding team memory, and verification loops that dramatically improve output quality. Timestamps: 00:00 – Intro 03:26 – Cowork Overview 05:51 – Demo: Folder Access + Renaming Receipts 08:23 – Demo: Turning Receipts Into A Spreadsheet 10:52 – Demo: Google Sheets + Chrome Control 15:52 – Demo: Emailing The Sheet + Parallel Tasking 22:07 – Best way to start/use with Cowork 24:22 – Where will AI and Agents Go Next 28:44 – Boris’s Claude Code Setup 41:12 – The “Claude” Pronunciation Discussion Key Points I use Cowork as a “doer,” not a chat: it touches files, browsers, and tools directly. I think about productivity as parallelism: multiple tasks running while I steer outcomes. I treat Claude.md as compounding memory: every mistake becomes a durable rule for the team. I run plan-first workflows: once the plan is solid, execution gets dramatically cleaner. I give Claude a way to verify output (browser/tests): verification drives quality. The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/ FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND BORIS ON SOCIAL X/Twitter: https://x.com/bcherny

In this episode, I sit down with Professor Ras Mic for a beginner-friendly crash course on using Claude Code (and AI coding agents in general) without feeling overwhelmed by the terminal. We break down why your output is only as good as your inputs and how thinking in features + tests turns “vague app ideas” into real, shippable products. Was walks me through a better planning workflow using Claude Code’s Ask User Question Tool, which forces clarity on UI/UX decisions, trade-offs, and technical constraints before you build. We also talk about when not to use “Ralph” automation, why context windows matter, and how taste + audacity are the real differentiators in 2026 software. Timestamps 00:00 – Intro 01:22 – Claude Code Best Practices 05:31 – Claude Code Plan Mode 09:30 – The Ask User Question Tool 14:52 – Don’t start with Ralph automation (get reps first) 16:36 – What are “Ralph loops” and why plans and documentation matter most 18:41 – Ras’s Ralph setup: progress tracking + tests + linting 23:48 – Tips & tricks: don’t obsess over MCP/skills/plugins 27:44 – Scroll-stopping software wins Key Points Your results improve fast when you treat AI agents like junior engineers: clear inputs → clean outputs. The biggest unlock is planning in features + tests, not broad product descriptions. Claude Code’s Ask User Question Tool forces real clarity on workflow, UI/UX, costs, and technical decisions. If you haven’t shipped anything, don’t hide behind automation—build manually before using “Ralph.” Context management matters: long sessions can degrade quality, so restart earlier than you think. Numbered Section Summaries The Real Reason People Get “AI Slop” I frame the episode around a simple idea: if you feed agents sloppy instructions, you’ll get sloppy output. Ras explains that models are now good enough that the failure mode is usually unclear inputs, not model quality. How To Think Like A Product Builder (Features First): Ras pushes a practical mindset: don’t describe “the product,” describe the features that make the product real. If you can list the core features clearly, you can actually direct an agent to build them correctly. The Missing Piece: Tests Between Features: We talk about the shift from “generate code” to “build something serious.” The move is writing and running tests after each feature, so you don’t stack feature two on top of a broken feature one. Why Default Planning Mode Isn’t Enough: Ras shows the standard flow: open plan mode, ask Claude to write a PRD, and get a basic roadmap. The issue is it leaves too many assumptions—especially around UI/UX and workflow details. The Ask User Question Tool (The Planning Upgrade): This is the big unlock. Ras demonstrates how the Ask User Question Tool interrogates you with increasingly specific questions (workflow, cost handling, database/hosting, UI style, storage, etc.) so the plan becomes dramatically more precise. Spend Time Upfront Or Pay For It Later: We connect the dots: better planning reduces back-and-forth, reduces token burn, and prevents “I built the app but it’s not what I wanted.” The interview-style planning forces trade-offs early instead of late. Don’t Use Ralph Until You’ve Built Without It: Ras makes a strong case for reps: if you can’t ship something end-to-end yet, automation won’t save you—it’ll just move faster in the wrong direction. Build feature-by-feature manually first, then graduate to loops. Practical Tips: Context Discipline + Taste Wins: Ras shares a few operational habits: don’t obsess over tools like MCP/plugins, keep context usage under control, and restart sessions before quality degrades. We wrap on a bigger point: in 2026, “audacity + taste” is what makes software stand out. The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/ FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND MIC ON SOCIAL X/Twitter: https://x.com/Rasmic Youtube: https://www.youtube.com/@rasmic

Today I’m joined by Samuel Thompson, an internet capitalist who’s launched 100 companies in 10 years, and he walks me through a live, end-to-end build of an info product using AI. We break down how he goes from idea → AI-written book → mockups → Shopify product page → ad creatives in a ridiculously short amount of time. The big takeaway is that this isn’t just “info products,” it’s a repeatable launch system you can apply to e-comm, SaaS, mobile apps, and pretty much anything where customer acquisition matters. We also get into the real game: CAC vs LTV, conversion rates, and how to build what Sam calls a “rigged slot machine” you can scale. Timestamps 00:00 – Intro 02:32 – Choosing the offer 05:36 - Writing ebook with ChatGPT (outline → chapters → upgrade quality) 07:30 – Mockups with Canva & Envato Elements 10:25 – Shopify themes that convert (Solo Drop + Elixir) 12:05 – Finding products to sell 16:28 - Building the Shopify Store 21:16 – Using ChatGPT to generate product-page copy fast 24:13 – What “good” conversion rates look like (3–5% target range) 28:51 – Bonus gifts strategy = perceived value + conversion lift 33:26 – HeyGen for AI photo/video ad assets + voice clone insight 35:37 – Canva static ads + high-performing angles 38:57 – Big picture: one person can build a “real business” with AI Key Points Sam’s launch loop is offer → AI asset creation → Shopify page → Meta ads → iterate on math Start with low-friction products (ebook/info) to validate customer acquisition fast The real framework is CAC vs AOV vs conversion rate, not “brand vibes” 3–5% conversion rate is a strong target on a direct-response product page Use bonus gifts to increase perceived value and lift conversion Static ads + strong angles can outperform everything when the message hits The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/ FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND SAMUEL ON SOCIAL: X/Twitter: https://x.com/samuelthompson

In this episode, I sat down with Chris Koerner and we go through a set of approachable startup ideas that start low-friction but can scale if you get distribution right. We start with a potential “app ecosystem” opportunity around Facebook Marketplace, plus a product-studio framework that combines short-form video, AI, and 3D printing to validate “dumb” products via demand before you invest. We then jump to more grounded, local-first ideas—bike washing/maintenance subscriptions, bar anti-spike stickers, and even vending-machine concepts like “shiny rock” drops at trailheads. We close with a weird Pokémon-card “meme + supply control” play inspired by the Kabuto King, including Chris’s own collecting “big reveal.” From there, I dig into why PSA-style grading feels slow and expensive, and we workshop a more modern grading experience (including a livestream/packaging angle and an AI-from-photo approach). Timestamps 00:00 – Intro 02:28 – Startup Idea 1: Facebook Marketplace App Studio 07:43 – Startup Idea 2: DTC Product Studio 17:05 – Startup Idea 3: Bike Washing/Maintenance Subscription 24:29 – Startup Idea 4: Anti-Drink-Spike Stickers 31:55 – Startup Idea 5: Shiny Rock Vending Machines 36:37 – Startup Idea 6: The Kabuto King and Card Grading Key Points I look for “alpha” where people are already obsessing, but the market structure is still primitive (like collectibles + grading). I treat “distribution” as the multiplier—short-form can make “dumb” products viable if the content loop is strong. I push for starting manually first (prove demand), then upgrading into infrastructure, subscriptions, and scale. I pay attention to marketplaces with huge usage but weak third-party tooling—there’s often a platform-layer opportunity there. I keep coming back to “repackaging” as a business model: same underlying thing, new wrapper, new buyer, new channel. The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/ FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND CHRIS ON SOCIAL: X/Twitter: https://x.com/mhp_guy Instagram: https://www.instagram.com/thekoerneroffice/ Youtube: https://www.youtube.com/@thekoerneroffice

We got Ryan Carson on the pod to break down the “Ralph Wiggum” Agent and why it’s suddenly everywhere. He walks me through a simple workflow that lets an autonomous agent build a full product feature while I sleep: start with a PRD, convert it into small user stories with tight acceptance criteria, then run a looped script that ships work in clean iterations. The big idea is you’re not “vibe coding” one giant prompt—you’re giving the agent testable, bite-sized tickets and letting it execute like an engineering team. By the end, Ryan shows how this becomes repeatable (and safer) with a memory layer—agents.md for long-term notes and progress.txt for iteration-to-iteration context. Timestamps 00:00 – Intro 02:44 – What is the Ralph Wiggum AI Agent 03:40 – Step 1: PRD Generator 06:11 – Step 2: Convert PRD to Json 09:47 – Step 3: Run Ralph 12:05 – Step 4: Ralph Picks a Task 13:14 – Step 5: Ralph Implements Task 14:49 – Tokens + Cost: What It Actually Spends 15:45 – Guardrails: Small Stories + Clear Criteria Keep It Sane 16:19 – Step 6: Ralph commits the change 16:38 – Step 7: Ralph Updates PRD json file 16:55 – Step 8: Ralph Logs to Progress txt 20:08 – Step 9: Ralph Picks another Task 20:48 – Step 10: Ralph Finishes Tasks 21:18 – Example of how Ryan uses Ralph 24:08 – How To Start Today (Ralph Repo) and Tips Links Mentioned: Ralph Wiggum Agent: https://startup-ideas-pod.link/Ralph-agent  AI Agent Skills: https://startup-ideas-pod.link/amp-skills  AMP: https://startup-ideas-pod.link/amp-code  Ryan’s Ralph Step-by-Step Guide: https://startup-ideas-pod.link/Ryans-Ralph-Guide Key Points I can’t expect “sleep-shipping” unless I translate the feature into small, testable user stories with clear acceptance criteria. Ralph works like a Kanban loop: pull one story, implement, commit, mark pass/fail, then grab the next. The real leverage is the reset: each iteration starts fresh with a clean context window, instead of one giant, messy thread. agents.md becomes long-term memory across the repo; progress.txt is short-term memory across iterations. The bottleneck isn’t “coding”—it’s the upfront spec quality: PRD clarity, atomic stories, and verifiable criteria. The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/ FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND RYAN ON SOCIAL: X/Twitter: https://x.com/ryancarson Amp: https://ampcode.com

In this episode, I’m breaking down a guide from Ben Tossel on how you can actually build with AI agents without being technical. I walk through what he’s shipped as a “non-technical” builder, why he lives in the terminal/CLI, and the exact workflow he uses to go from idea → spec → build → iterate. We also talk about the meta-skill here: treating the model like your over-the-shoulder engineer/teacher, and using every bug as a learning checkpoint. The takeaway is simple: pick a tool, ship fast, fail forward, and build your own system as you go. Ben’s Article: https://startup-ideas-pod.link/Ben-Tossell-Article Timestamps 00:00 – Intro 01:04 – What Ben Has Shipped 03:21 – The Workflow: Feed Context → Spec Mode → Let The Agent Rip 07:52 – His Agent Setup 08:56 – Coding On The Go 10:07 – Things to Learn 13:33 – The New Abstraction Layer: Learning To Work With Agents 14:33 – Learning from Others 16:15 – Use The Model As Your Teacher (Ask Everything) 18:13 – Contributing to Real Products 19:13 – Why this is Different 21:31 – Asking Silly Questions 24:00 – Beyond “Vibe Coding”: A New Technical Class 24:43 – Vibe Coding is a game 27:12 – Fail Forward + Permission To Build And Throw Things Away 28:16 – Pick One Tool, Minimize Friction, Keep Shipping Key Points I don’t need to be a traditional engineer to ship—I can learn by watching agent output and iterating. The terminal/CLI is the power move because it’s more capable and I can see what the agent is doing. “Spec mode” works best when I interrogate the plan like a philosopher instead of pretending I understand everything. agents.md becomes my portable instruction manual so every new repo starts clean and consistent. The fastest learning path is building ahead of my capability and treating bugs as checkpoints—fail forward. Numbered Section Summaries The Thesis: Non-Technical Doesn’t Mean Non-Builder I open with Ben’s core claim: you can ship real software by working through a terminal with agents, even if you can’t write the code yourself—because you can read the output and learn the system over time. Proof: What He’s Actually Shipped I run through examples Ben built—custom CLIs, a crypto tracker, “Droidmas” experiments, an AI-directed video demo system, and automations that keep projects moving even when he’s away from his desk. The Workflow: Context → Spec Mode → Autonomy High Ben’s process is straightforward: talk to the model to load context, switch into spec mode to pressure-test the plan, link docs/repos for exploration, then let the model run while he watches and steers when needed. http://agents.md/ The “Readme For Agents” That Follows You Everywhere I explain why agents . md matters—one predictable place to tell your agent how you want repos structured, how to commit, how to test, and what “good” looks like so each session gets smoother. Coding On The Go: PRs, Issues, Phone, Telegram, Slack We get into the real “agent native” behavior: install the GitHub app, work via pull requests and issues, tag the agent to self-fix, and even push changes from your phone—plus using Slack as a one-person “product” with an agent in the loop. Learning The Primitives: Bash, CLIs, VPS, Skills I cover the building blocks Ben’s learning: bash commands and repeatable terminal workflows, preferring CLIs over MCPs to save context, and using a VPS + syncing to keep projects always-on. The Mindset Shift: The Model Is The Teacher The real unlock is treating the model like your patient expert—ask everything you don’t understand, bake “explain simply” into your agent instructions, and close knowledge gaps as they appear. Fail Forward, Pick One, Keep Shipping I end on the playbook: build ahead of your capability, treat it like play, give yourself permission to throw things away, and stop tool-hopping—pick one system and go deep. The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/ FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/

I walk through Alibaba’s new AI agent tool, Accio, and show how it helps you go from “what should I build?” to actual product concepts and supplier options. I demo how it spots rising trends, pulls specific product opportunities (with context like search and sales movement), and even generates early design concepts. Then I test it on a real research task and use that to spin up a “cozy gaming” keyboard concept aimed at Gen-Z women. I close by showing how Accio can vet suppliers and even draft a supplier outreach email so you can start the sourcing process faster. Timestamps 00:00 – Intro 01:55 – Trend Spotting Demo 03:31 – Designing Products Demo 07:04 – Product Opportunity Pain Points Demo 10:10 – Supplier Search Demo 11:06 – Mechanical Keyboard Market Research and Pain Points 16:03 – Cozy Gaming Mechanical Keyboard For Gen Z Women 18:42 – Supplier Vetting + Due Diligence 22:00 – Supplier Outreach Key Points Accio compresses the e-commerce workflow: trends → product ideas → design concepts → supplier shortlists. The real leverage is pairing insights (ratings, negative tags, review pain) with concrete product recommendations. The “agent task” flow feels like a research assistant: it gathers sources, updates a plan, and synthesizes outputs. Accio can move from concept to execution by suggesting suppliers and drafting a structured inquiry email. You still need real diligence: call suppliers, vet claims, and start with small orders. Numbered Section Summaries Accio As An “Unfair Advantage” For E-Commerce I introduce Accio as an AI agent built around e-commerce workflows—idea generation, trend analysis, product concepts, and supplier sourcing. My core point is it reduces the friction that usually keeps me (a software person) from starting e-commerce. Trend Spotting That Goes Beyond Generic Charts Using a baby products example, I show that it’s not just search/sales graphs—it surfaces specific product categories and differentiators (like smart features) plus recommendations you can validate elsewhere. Turning Pop Culture Into Product Concepts (With Caveats) I try a “Squid Game” prompt to generate product directions and visuals. I’m clear this isn’t a “press button, print money” system, but it gets the creative juices flowing and connects ideas to sourcing. Finding Opportunities By Reading What Customers Hate In the senior dog pet supplies example, Accio highlights product opportunities and connects them to the underlying pain (accessibility, cognitive decline, weak ratings). I emphasize that the edge is insight—knowing why current products underperform. Supplier Discovery Without The Usual Alibaba Overwhelm I run a supplier prompt with constraints (OEM, private label, MOQ, certifications, reviews). The key is Accio structures what’s normally chaotic and gives a shortlist you can actually act on. Agent Research: Mechanical Keyboard Pain Points, Ranked I test an agent task to find unmet pain points and cluster them by theme, with “proof” from reviews/forums/Q&A. The point isn’t keyboards—it’s showing how fast you can go from “trend” to “what to build” using structured research. From Pain Points To A Launchable Niche Concept (Cozy Gaming) I pivot from the research into a niche: mechanical keyboards for Gen Z women aligned with “cozy gaming.” Accio proposes brand directions, a flagship product concept, and early roadmap thinking. Reality Check: Sourcing, Verification, And Outreach I ask for trusted suppliers and get a short list plus technical verification prompts (finish, sound profile, color matching). Accio then drafts a supplier email and shows how the workflow can extend to sending inquiries—while I remind you to vet suppliers carefully and start small. The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/ FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/

In this episode, I walk through a beginner-friendly, step-by-step way to set up Claude Skills so you can get more consistent, higher-value output over time. I show where to enable Skills (it’s not on by default), how to create a new skill using Claude’s “create a skill together” flow, and why Skills are different from Projects for ongoing, reusable workflows. Then I demo a real example: building a conversion-focused copywriting review skill for an agency workflow, installing it, and testing it on app store screenshots + website copy. I close with how to level up Skills by iterating them over time, using a 10-step process I reference from a “Boring Marketer” tweet. Timestamps: 00:00 – Intro 00:40 – Enable Skills (Settings → Capabilities → Skills Preview) 01:21 – Creating a new skill 06:34 – Why Skills are important Projects for “always-on” workflows 07:49 – Reviewing the skill 10:34 – Installing the skill (copy to skills / upload in Skills) 11:28 – Testing the Skill 16:14 – How to improve skill over time Key Points Skills make Claude’s output more consistent because you bake in reusable context and workflows. Skills aren’t enabled by default—turn them on in Settings → Capabilities. The easiest path for most people is “Create a skill together,” then answer Claude’s scoping questions. A strong skill includes frameworks, scoring, and an output template—not vague advice. The real power comes from iterating: test on real scenarios, critique, refine, and keep improving the skill over time. Numbered Section Summaries Why Skills Matter For Beginners I open by explaining that Skills help you get more consistent, higher-value output from Claude over time, especially if you’re a beginner and want repeatable results. Turn On Skills First Skills aren’t enabled by default, so I show the exact path: Settings → Capabilities → enable the Skills preview feature. Create A Skill (Three Paths) I walk through the three options: create with Claude, write skill instructions, or upload an existing skill Build A Real Skill: Conversion Copy Review I describe the skill I want: a conversion-focused copywriting reviewer for apps and websites, built like a specialist “employee” that can critique headlines, CTAs, value props, pricing pages, and more. Skills vs Projects (And Why Skills Win For Ongoing Work) I explain why I prefer Skills for ongoing workflows: Projects can be context-specific to a campaign, while Skills are meant to work across day-to-day work regardless of the project timeline. What Claude Generates (And Why Markdown Is Great) I show Claude generating the skill structure and markdown files (like skill md and framework docs), and I call out why markdown is practical and easy for non-technical folks to edit. Install + Test The Skill On A Real Example I install the skill (copy to Skills / upload) and test it on real assets—app store screenshots and website copy—to see if it actually follows the skill workflow. Make The Skill Better Over Time (The Improvement Loop) I share the idea that Skills shouldn’t stay static. I reference a 10-step process (understand the problem, explore failures, research, synthesize, draft, self-critique, iterate, test, finalize) and emphasize ongoing iteration based on real outputs. The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/ FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/