
Sign up to save your podcasts
Or


What happens when a non-technical couple locks themselves into a 48-hour hackathon with an engagement ring and an idea?
Most people think building an AI product requires months of learning or a technical co-founder. Christina spent weeks scrolling through Bridebook and WedStay — generic catalogs, no personalization, nothing that understood her taste. Then one shower conversation turned frustration into a product vision: what if you could talk to a wedding planner that actually gets you?
This is the full behind-the-scenes breakdown of every product decision and tech choice — from picking next-forge over a simple template, to the moment fal.ai generated a visualization of our dream wedding and Christina was astonished. Ten product needs, ten tech decisions, each explained from both the non-technical and technical perspective.
Honest disclaimer: we didn't follow our own Pirate Launch Plan. We set up Stripe and auth too early. The visualization feature worked 30 minutes before the deadline. And production deployment almost broke everything on Saturday night.
But we made it: https://www.bridesmaid.love/de is live.
WHO THIS IS FOR
- A founder who's stuck between "I use AI tools" and "I shipped a product with AI"
- A non-technical builder wondering what it actually takes to go from idea to live product
- A vibe coder preparing for a hackathon who wants to see what's realistic in 48 hours
- A couple or team where one person has the domain knowledge and the other has the tech instinct
IN THIS EPISODE
00:00:00 – How we built an AI startup in 48 hours
00:00:34 – Scratch your own itch: Christina's wedding app frustration
00:03:15 – The product we wanted to use: chat-first wedding planning
00:05:54 – 10 product decisions, 10 tech choices
00:07:15 – AI SDK + AI Gateway: a conversation that does things
00:09:57 – Real-Time Scribe: talk, don't type
00:10:39 – fal.ai: show me my dream wedding
00:12:08 – Clerk, Stripe, Claude Code: the rest of the stack
00:14:54 – Christina's hackathon experience (in her own words)
00:17:12 – The honest weekend recap: what went wrong
00:19:46 – What's next: events, Builder Forge, and your turn
DEEP DIVE LINKS
📖 Full Article + All 10 Tech Decision Cards: https://pirateskills.com/insights/startup-in-48-hours
🏗️ Builder Forge Q2 April 1st — Build your own AI product with guided support: https://pirateskills.com/build/forge
🎧 Spotify: https://open.spotify.com/show/7kFl0BJiOYih8yqQTRR9SN
🍎 Apple Podcasts: https://podcasts.apple.com/us/podcast/build-grow-repeat/id1870561487
🗓️ All upcoming events: https://pirateskills.com/events
💬 Connect with me on LinkedIn: https://www.linkedin.com/in/bensufiani/
Everyone's using AI. Nobody knows where they actually stand.
There's no shortage of AI tools, tutorials, and hype. But there's no map. No way to know: am I a beginner who thinks they're advanced, or someone further along than I realize? And what should I actually learn next?
I couldn't find a clear progression path, so I built my own. The AI Skill Path is a 6-level framework — from Landlubber to Admiral — that shows you where you are, what you already unlock at that level, and what it takes to reach the next one. Each level covers both the Build track and the Grow track.
This isn't about collecting tools. It's about knowing which capabilities matter at your stage — and ignoring everything else until you get there.
WHO THIS IS FOR
A founder who uses ChatGPT daily but isn't sure what the next level looks like
A vibe coder who ships apps but hasn't touched AI marketing yet
A marketer experimenting with AI content but not building anything technical
Someone drowning in AI FOMO who wants a clear, honest progression path
IN THIS EPISODE
00:00:00 – The problem: there is no map
00:01:11 – The principle underneath every level: relationship to initiation
00:02:39 – The 6 levels overview
00:02:52 – Level 1: Landlubber — the ChatGPT user
00:04:36 – Level 2: Deckhand — persistent context and better prompting
00:07:19 – Level 3: Navigator — vibe coding simple tools and automations
00:09:30 – Level 4: Corsair — owning your stack and building real SaaS
00:13:43 – Level 5: Captain — proactive agents working for you
00:17:29 – Level 6: Admiral — orchestrating multi-agent systems
00:20:36 – Do you really need to go all the way?
00:24:48 – Find your level and start from there
DEEP DIVE LINKS
What would you do if you only had 48 hours to build and launch a startup from scratch?
The old playbook said: build a landing page, run a survey, do customer development interviews, then build. But vibe coding changed that — it's now faster to build a working MVP than to set up a survey campaign. That changes the order of operations completely.
The Pirate Launch Plan is a 6-stage operating system for going from zero to shipped and launched in a single sprint. It alternates between building and growing from hour one — so you never build in a vacuum. Whether you're at a hackathon or doing a weekend sprint, you follow the same stages in the same order.
Honest context: this comes from someone who ran 150 landing pages and built 6 apps (two with over a million users) using the old validation playbook. That experience still applies — but the execution has fundamentally changed.
WHO THIS IS FOR
A vibe coder who wants a clear, repeatable plan for launching new projects
A founder who builds first and markets later (and wants to stop doing that)
Someone preparing for a hackathon and wants to maximize their 48 hours
A non-technical builder who needs an AI-native stack that won't create security surprises
IN THIS EPISODE
00:00:00 – What if you only had 48 hours?
00:00:30 – The old validation playbook vs. vibe coding
00:02:09 – Y Combinator: 25% using AI for 95% of coding
00:03:05 – Stage 1: Lock the idea — problem, audience, solution
00:06:06 – Stage 2: Build the magic interaction
00:09:40 – Stage 3: Make first contact
00:13:11 – Stage 4: Build the MVP — database, auth, payments
00:17:00 – First do it, then do it right, then do it better
00:17:53 – Stage 5: Grow — organic, paid, or outreach
00:23:00 – Stage 6: The Build-Grow-Repeat loop
00:27:07 – Now it's your turn
TOOLS & RESOURCES MENTIONED
🖥️ Cursor / Claude Code (AI code editors): https://cursor.com / https://anthropic.com
⚡ Next.js + Vercel (framework + hosting): https://vercel.com
🔐 Clerk (authentication): https://clerk.com
🗄️ Supabase (database): https://supabase.com
💳 Stripe (payments): https://stripe.com
📊 PostHog (analytics): https://posthog.com
DEEP DIVE LINKS
📖 Full Article + Ship Plan Checklist: https://pirateskills.com/insights/pirate-launch-plan
🔧 The Vibe Coding Stack (referenced in video): https://pirateskills.com/insights/vibe-coding-stack
🏴☠️ Vibe Hackathon Cologne — Mar 20th: https://pirateskills.com/vibe-hackathon-cologne
🗓️ All upcoming events (free): https://pirateskills.com/events
What would it look like to run a full customer acquisition engine — content, ads, website, data, analytics, emails, and sales — without an agency, without a team, and without losing your mind?
Turns out it's possible. Vibe marketing applies the same principle as vibe coding: AI does the heavy lifting, you steer with intent. After 12 weeks of building and running this system, every layer is connected, agent-driven, and working day and night.
There's a live look at the full weekly content cascade, real attribution data from the Supabase user table, PostHog dashboards and A/B tests set up entirely by an AI agent, the Attio CRM pipeline reviewed daily by Christina (an OpenClaw assistant), and the stack configurator in the article that generates an AI discussion prompt for your own setup.
This is not theory. It's a working system.
WHO THIS IS FOR
IN THIS EPISODE
TOOLS & RESOURCES MENTIONED
DEEP DIVE LINKS
Most founders use AI to build products.
In this Captain’s Insight article, we show a different application: using vibe coding to automate the operational work behind your product — the repetitive setup, coordination, and admin that quietly consumes hours every week.
The episode walks through how we at Pirate Skills rebuilt its internal event system:
- 84 events planned for the year
- Google Calendar + Zoom connected via API
- Automated invitations, reminders, and follow-ups
- A custom Event Prep dashboard showing what’s done and what’s missing
What used to require ongoing manual coordination was reduced to half a day of setup — and will take roughly an hour next quarter.
This isn’t about building a bigger product.
It’s about removing friction from real work and letting internal tools compound.
WHO THIS IS FOR
- Founders who say: “I don’t have time to build with AI.”
- Builders who picked their stack but still feel overwhelmed
- Operators drowning in repetitive admin work
- Anyone curious how to start vibe coding without going fully public
IN THIS EPISODE
00:00:00 – Intro: vibe coding your real work
00:01:11 – “Where am I supposed to get the time?”
00:02:03 – The first internal tool that became a SaaS (Captain)
00:02:58 – The events problem (Christina + operational dependencies)
00:03:52 – The Event Prep dashboard concept
00:04:56 – “84 events” → why tooling beats doing it manually
00:05:46 – Why helper tools are insanely practical (the advantages)
00:09:15 – Giving AI access to Google Calendar + Zoom (API keys)
00:12:48 – The 3 questions to choose what to automate
00:14:59 – Build vs buy: “build for the gap” rule
00:22:21 – Compounding tools → your own operating system (“Ironman suit”)
DEEP DIVE LINKS
📖 Read the full article (with Ship Plan & prompts):
https://pirateskills.com/insights/vibe-code-your-real-work
🧪 Builder Lab — Monthly vibe coding workshop (next: March 18)
https://pirateskills.com/build/lab
📈 Growth Lab — Monthly vibe marketing workshop (next: March 11)
https://pirateskills.com/grow/lab
🏴☠️ Builder Forge — 6-week cohort (next: April 1st)
https://pirateskills.com/build/forge
🎧 Spotify
https://open.spotify.com/show/7kFl0BJiOYih8yqQTRR9SN?si=vS7cYQ3MTL6L2tFBlWZghw
🍎 Apple Podcasts
https://podcasts.apple.com/de/podcast/build-grow-repeat/id1870561487
🗓️ All upcoming events
https://pirateskills.com/events
💬 Connect with me
https://www.linkedin.com/in/bensufiani/
What happens when you move your business strategy, OKRs, and project management into your codebase — and let AI run it?
The counterintuitive discovery that kept me organized, productive, and sane as a solo founder: your codebase is a better home for business context than Notion, Asana, or Google Docs. Once AI can read your strategy, goals, and bottlenecks without you re-explaining them, planning and execution merge into the same conversation.
WHO THIS IS FOR
IN THIS EPISODE
TOOLS & RESOURCES MENTIONED
DEEP DIVE LINKS
What does AI change about message testing and marketing decisions?
In this episode, I walk you through how I use AI to turn message testing from a “nice-to-have” into a repeatable, data-driven system.
As a growth marketer, I’ve always believed in testing — but like most teams, it often slipped to a B-priority because it took too long. AI changes that completely. What used to take weeks of creative work, coordination, and iteration can now be done in hours — if you structure it correctly.
I break down my full end-to-end workflow, using a real campaign for Vibe Coding Cologne, including positioning, angle generation, AI creatives, Meta Ads experiments, and how to interpret the data without fooling yourself.
This is not theory. It’s real spend, real numbers, and a few uncomfortable lessons where my own assumptions lost.
We talk about:
- Why most marketers get stuck on a “local maximum” in their messaging
- How AI collapses the cost and speed of message testing
- Using positioning frameworks (April Dunford) to generate better angles
- Letting AI create options — and humans curate decisions
- Image vs. video ads: what actually converted better
- CTR vs. conversions and why deeper funnel signals matter more
- Why your favorite message is often not the best one
- How to kill losing messages early and double down on winners
This episode is especially relevant if you’re:
- A founder or operator doing your own growth
- A marketer tired of guessing what should work
- Running B2B or community-driven campaigns
- Using AI and want leverage — not noise
Timestamps
00:00:00 – Why message testing matters (and why we avoid it)
00:02:00 – The “local maximum” problem in marketing
00:05:10 – How AI changes the economics of testing
00:07:20 – Positioning before creatives (April Dunford framework)
00:11:10 – Adding pain points to strengthen AI outputs
00:13:30 – Defining the campaign and ideal customer profile
00:15:40 – Generating strong message angles with AI
00:18:50 – Creating AI image creatives fast
00:23:10 – Turning static images into video ads
00:26:20 – Building a reusable prompt & style library
00:30:00 – Structuring Meta Ads for message testing
00:34:30 – Budgets, ad sets, and what’s “enough” data
00:38:30 – CTR vs. conversion tracking
00:42:40 – Reading the first real results
00:47:20 – The surprising winner: community beats autonomy
00:52:30 – Images vs. videos: what actually converted
00:56:50 – Why Meta attribution is not the source of truth
01:01:40 – Verifying results in your own database
01:05:20 – What this taught me about my audience
01:08:50 – How to scale winners and kill losers
01:11:40 – Final advice: stop guessing, start testing
LINKS
📖 Full Article: https://pirateskills.com/insights/message-testing
🧪 Join a free Growth or Builder Lab: https://pirateskills.com/events
💬 Follow on LinkedIn: https://www.linkedin.com/in/bensufiani/
What does AI actually change for non-technical operators?
In this conversation, I’m joined by Anna Nadeina, Head of Growth at saas.group and host of the SaaS Unbound podcast. Anna has spent years working with founders and SaaS teams — without a technical background — and now sits front-row as AI reshapes how modern companies operate.
We talk about:
- How non-technical marketers and operators can really use AI
- The moment AI stopped being a gimmick and became a daily work tool
- Practical AI workflows in content, growth, and podcasting
- Why tools like ChatGPT, Riverside, and Descript change leverage — not just speed
- Where human judgment still matters (and always will)
- What founders and operators should focus on now instead of chasing tools
This episode is especially relevant if you’re:
- A non-technical founder or operator
- A growth marketer navigating AI tools
- Building or operating SaaS products
- Curious how AI fits into real workflows — not demos
00:00:00 – Intro & why this conversation matters
00:02:10 – Anna’s background: marketer, operator, non-technical by choice
00:05:00 – Working in a founder-heavy, technical SaaS world
00:08:10 – First real exposure to AI in everyday work
00:11:30 – When AI stopped being hype and became useful
00:15:00 – How non-technical operators actually learn AI
00:18:40 – AI workflows in growth, content, and marketing teams
00:22:30 – Podcasting with AI: tools, leverage, and quality
00:26:10 – What AI is good at vs. where humans still win
00:30:20 – Decision-making, taste, and judgment in an AI world
00:34:20 – How SaaS teams adopt AI without breaking workflows
00:38:10 – Advice for founders and operators right now
00:42:10 – What the next 1–2 years will demand from operators
00:44:30 – Final thoughts & wrap-up
LINKS:
📖 Full Article: https://pirateskills.com/insights
🧪 Join a free Growth or Builder Lab: https://pirateskills.com/events
💬 Follow on LinkedIn: https://www.linkedin.com/in/bensufiani/
Follow Anna on LinkedIn: https://www.linkedin.com/in/anna-nadeina/