“I launched you get a free year of Cursor and Lovable and Bolt and Replit and V0.”
Bolt
By StackBlitz
3 recommend/use · 10 sourced episodes
Every sourced reference
Short attributed excerpts only. Timestamps are approximate.
“opened Bolt, opened an account, and for the past year, I've been building.”
“Bolt was awesome until I was trying to connect payments to my app and it kind of started losing it”
“Bolt is probably a distant number three behind Rep and Lovable, right?”
“you get a year free of a bunch of amazing products, including Bolt, Linear, Superhum, Notion, Perplexity, Granola, and more.”
“You're competing against very wellunded companies, Lovable, Bolt, Replet, Versell.”
“Clearly, cursor, lovable, bolt, rep, all these guys did that.”
“you have a prompt that you give say bolt lovable replet v 0 zero”
“cursor and lovable and bold and all these guys”
“we had the founders of bolt and lovable on the podcast.”
“what's the simplest way to understand maybe how Lev B might be different from say bolt and ret”
Related frameworks
Adversarial Multi-Model Peer Review
Have rival LLMs review each other's code and fight it out until no issues remain
Agency Over Title: The Force-Multiplier Mindset
Ignore role boundaries — use AI tools to execute your own ideas end to end
Best-Rep Email Cloning
Feed the agent your single best rep's best email, then let it AB-test variants—that's how AI beats your mid-pack.
Biggest-Bottleneck Prioritization
Solve the single biggest problem, then pick the next — don't dream up a long roadmap.
Build Only at the Magic Intersection
Don't ship what anyone could build off the shelf — build only where model and product uniquely meet.
Build Only Where You Can Be Best (Model Sourcing)
Build in-house only where your unique data or position lets you beat the frontier; otherwise buy
Cannibalize Your Own Product Every 6-12 Months
Make your current product look silly on a fixed cadence instead of only shipping what users ask for
Context Loading (Additional Information)
Front-load all relevant task information — and put it at the top for caching
Credits-for-Sharing Loop
Pay users in product credits to publicly share what they built — turn usage into free distribution.
Defensible Moats for AI Startups
Four durable places to build in AI where foundation-model labs are least likely to squash you.
Engineering the Creative Peak
Single-shot coffee, a two-hour deadline, and a good night's sleep — dial in the state, not just the effort.
Ensembling (Mixture of Reasoning Experts)
Solve the same problem several ways and take the most common answer
Few-Shot Prompting
Show the model examples of what good looks like instead of describing it
Follow the Pull
Bet your career on the thing you enjoy, are good at, and others value — even if it's not the plan.
Generalist-With-A-Superpower Hiring
Hire people who care obsessively, have a generalist brain, and one absolute superpower — then trial them for a week.
Genius-Zone Time Budget
Spend at least 50% of your time on the work you're both great at and love — it's what keeps you showing up.
Growth Team as a Rigor Forcing Function
Hire a growth leader early — the second-order effect is that it exposes everything you haven't measured.
Hills-and-Valleys: Getting Value From Probabilistic AI Tools
Be patient and explicit, start small, and learn where the model is strong vs weak
Hunting New Bottlenecks When AI Writes the Code
When AI removes the coding bottleneck, constraints shift up and downstream — go find them.
Irrationally Optimistic, Uncompromisingly Realistic
Push hard toward a future you believe in while killing your own hypotheses as data arrives
LLM-Optimized Codebase Architecture
Structure your repo so the AI writes the least code possible — infrastructure absorbs the complexity.
Magic Lenses
Evaluate competing implementation paths by plotting each through the eyes of the advisers you wish you had
Make the Other Mistake (Prompting for Brutal Feedback)
To get honest AI critique, over-correct toward brutal — the model won't actually overshoot.
Milestone-Gated Launch Sequence
Don't spend a dollar on marketing until users start sharing your product unprompted.
Minimum Lovable Product Ladder
Replace the MVP with a three-rung ladder: minimum lovable, lovable, absolutely lovable.
Model Casting by Personality
Route each task to the model whose 'personality' matches, and split plans to fit
Negotiate From Genuine Indifference
The best position to sell your company is being genuinely fine not selling it.
One-Week Top-1% AI Fluency Sprint
Pick a real problem and spend one full week taking it end-to-end with AI — that alone puts you in the global top 1%.
Optimize for Learning: The Impedance-Match Career Test
Choose roles by where you'll learn most and whether the mission truly matches how humans are wired.
Practitioner-Sourced Wisdom
The best advice comes from people on the ground doing the thing — not from pontificators.
Precision Prompting for AI Builders
Never tell the AI 'it doesn't work' — state exactly what you expected and which parts do and don't.
Product-First, Add-AI-Later
Design the end-to-end product experience first, then add AI to solve specific problems — never retrofit AI into a broken flow.
Prompt Decomposition
Make the model list the sub-problems first, then solve each before the whole
Prompt Injection Defense Stack
Stop trying to fix injection with prompts and guardrails — mitigate at the model level
Raise Your Happiness Baseline
Big events only move you temporarily — the real lever is lifting the baseline you always return to.
Root-Cause Tooling Post-Mortem
When AI botches something, ask what in its prompt caused it — then patch the tooling
Self-Criticism Loop
Get the model to critique its own answer, then implement its own critique
Simple, Novel, Emotional: The Shareability Formula
Make it simple, make it show something new, make it feel something — then cut the cleverness.
Single-Channel Build-in-Public Bet
Find the one channel that resonates with your exact audience, then double and triple down.
Speed-to-Aha Over Best Product
Sometimes the correct product decision hurts the aha moment — cut it and get users to magic faster.
Stuck-Point Scaling Law
Reliably improve an AI system by hunting where it gets stuck and tuning those spots with a fast feedback loop.
Systems-First Scaling (One to 100)
Once you have product-market fit, go slow to go fast: build the systems before you hyperscale.
The 10-to-1 Input/Output Kill Test
When you pour 10 units of effort in for 1 unit of output, the project has run its course.
The 30-Day Agent Training Loop
Ingest your docs, then correct the agent an hour a day for 30 days until it performs like your best rep.
The AI-as-CTO Persona Project
Cast the AI as an opinionated technical co-founder to kill sycophancy and premature coding
The AI Interview-Prep Coach System
Build an AI coach, mine the real question bank, drill weak spots — then mock with humans
The AI Startup Moat: Data Flywheel + Crafted Workflow
Defensibility for AI apps comes from a proprietary data flywheel and a deeply crafted vertical workflow.
The Chief Agentic GTM Officer Play
Pick one painful problem, one leading vendor, and deploy an agent yourself—50 hours later you're hyper-employable.
The Dehydrated Company Hiring Model
Only hire when a function is underwater, so headcount forces ruthless prioritization
The Design Sprint Scorecard
Break your founding hypothesis into rows and grade each one red/yellow/green after head-to-head customer tests
The Differentiation 2x2 (Escape Loserville)
Plot two customer-facing differentiators you can prove and own the top-right; the other three quadrants are Loserville
The Exposure-Therapy Tool On-Ramp
Ease into coding tools in graduated steps so code stops being terrifying
The Five PM Archetypes
Hire and compose product teams by five distinct thinking styles, not one generic ideal PM.
The Forward-Deployed Engineer Vendor Column
Don't buy AI GTM tools on features—buy on who will actually get on the phone and deploy it with you.
The Foundation Sprint
A 10-hour, 3-phase team sprint that turns a vague startup idea into one testable founding hypothesis
The Founding Hypothesis (Mad Libs Strategy Sentence)
Compress your entire startup strategy into one testable fill-in-the-blank sentence — then go prove it
The GTM Agent Deployment Sequence
Roll out AI sales agents in the order of lowest effort and highest ROI: start with support, end with reactivation.
The Incognito Cry Test
Go through your own product as an anonymous customer, find what makes you cry, and buy an agent to fix that.
The Internal-Signal Quality Bar
It's done when it makes YOU laugh or tear up — not when someone else approves it.
The Lead-Rich Audit
You don't need SaaStr's scale—count your website visitors and untouched CRM leads to see you're already lead-rich.
The Learning-Opportunity Command
Turn every confusing moment into an 80/20 lesson aimed at your current skill level
The Lindy Commitment Test
However long you've sustained something is roughly how much longer you can trust it to last.
The Painful-Mistake Growth-Mindset Interview
Screen only for growth mindset by asking for the most painful mistake and what changed because of it.
The Relentless Iteration Loop
Read-through, add, repeat 50-100 times, set aside, return — then hand to editors. That's the secret.
The Say-Do-Said Loop
Say you'll do the thing, say you're doing it, say you did it — to align, adjust, and close the loop.
The Seven-Command Build Loop
Six slash-commands turn vibe-coding into disciplined software delivery for non-coders
The Six-Month Autonomy Razor
If you're still telling a hire what to do six months in, you hired the wrong person.
The Three-Part AI Product Utility Equation
A useful AI product needs model intelligence, context/memory, and application/UI to all converge.
Work Alone Together (Note-and-Vote)
Replace group brainstorms with silent individual idea generation, a quiet vote, and one designated decider
People in these episodes
Related resources
- 1883
- Adobe
- Adyen
- Agentforce
- AI 2027
- Airbnb
- Airtable
- Amazon
- Amazon Web Services
- Anthropic
- Anthropic Console Workbench
- Apple Podcasts
- Artisan
- Attention
- Base44
- Bay Area
- Booking.com
- Brex
- Canva
- Cap
- Captions
- Character Labs
- Charts for Babies
- ChatGPT
- ChatGPT Enterprise
- Claude
- Claude 3.5
- Claude 3.5 Sonnet
- Claude Code
- Claude Opus 4
- Clay
- Cloudflare
- Coda
- Codeium
- Codex
- Composer
- Contentsquare
- Cursor
- Custom GPTs
- Datadog
- Daylight Computer DC-1
- Deel
- Design Sprint
- Devin
- Discord
- Dropbox
- dscout
- Duolingo
- DX
- Eclipse
- ElevenLabs
- Emacs
- Ender's Game
- Eppo
- Etsy
- Everything That Breaks on the Way to One Billion
- Evil
- Facebook Messenger
- Facebook News Feed
- Fall in Love with the Problem, Not the Solution
- FigJam
- Figma
- Fin
- Foundation Sprint
- Foursquare
- Gamma
- Gemini
- GitHub
- GitHub Copilot
- Gmail
- Gong
- Google AdWords
- Google Drive
- Google Gemini
- Google Maps
- Google Meet
- Google Photos
- Google Reader
- Google Ventures
- Gowalla
- GPT Engineer
- GPT-4o
- Granola
- Harvey
- HBO
- HubSpot
- Intercom
- JavaScript
- JPMorgan Chase
- Julia
- Lenny's Newsletter
- Lenny's Podcast
- Lenny's Podcast website
- Lenny's Product Pass
- Lennybot
- Linear
- Localmind
- Lovable
- Maven
- Medium
- Meta
- Metaview
- Microsoft
- Microsoft Copilot
- Microsoft Teams
- Microsoft Windows
- Miro
- Miro Foundation Sprint template
- MIT
- Mobbin
- Model Context Protocol
- Momentum
- MongoDB
- Notion
- Notion Plus
- Oculus
- OneSchema FileFeeds 2.0
- OpenAI
- Outreach
- Palantir
- Paragon
- Perplexity
- Perplexity Pro
- Plaid
- Pragmatic Institute
- Product Hunt
- Product Pass
- Productboard
- Prompt Improver
- Python
- Qualified
- React
- Reclaim
- reMarkable
- Render
- Replit
- RescueTime
- Retool
- Reve
- Rippling
- Rippling’s Secrets to Hypergrowth
- SaaStr
- SaaStr AI
- SaaStr Annual
- Salesforce
- Salesloft
- Sapiens
- Sauce
- Severance
- Shopify
- Sierra
- Slack
- Snowflake
- South by Southwest
- Spotify
- Squarespace
- Stanford d.school
- Stockholm
- Stripe
- Studymate
- Substack
- Supercut
- Superhuman
- SWE-bench
- The Design of Everyday Things
- The Goal
- The Lord of the Rings
- The River of Doubt
- The Silk Roads
- The Wire
- TikTok
- TypeScript
- Uber
- Uber Eats
- Uber Reserve
- v0
- Vanta
- Vercel
- Vim
- Visual Studio
- Visual Studio Code
- When Harry Met Sally...
- Wikipedia
- Windsurf
- Wix
- WorkOS
- X
- Y Combinator
- Yellowstone
- YouTube
- Zoom
- Zustand
Spot an error or want this page removed? Request a correction or removal.