# Coding for Non-Coders — learn to build with AI | Envisioning

Source: https://www.envisioning.com/coding-for-non-coders

---

# Coding for Non-Coders

Building software by describing what you want. No CS degree, no syntax memorization, just you and an AI and an idea. This open guide shows you the path from beginner to builder, the concepts, tools, and workflows that take you from your first prompt to shipping real projects.

## Want to run this with your team?

This page is our open guide. For organizations, we deliver it as Build Sessions: hands-on workshops that take non-technical teams from idea to working prototype in a half day, using a version of this guide calibrated to your group.

[Explore Build Sessions](/services/build-sessions)

## What is vibe coding?

Vibe coding is writing software by talking to AI instead of writing code character by character. You describe what you want (“build me a dashboard that shows my sales data”) and the AI writes the code. You review, refine, and iterate until it works.

The term was [coined by Andrej Karpathy](https://x.com/karpathy/status/1886192184808149383) in early 2025:

[![](/_next/image?url=%2Fimages%2Fkarpathy-avatar.jpg&w=96&q=75)

Andrej Karpathy

@karpathy

There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. …

00:17 · Feb 3, 2025 · View on X](https://x.com/karpathy/status/1886192184808149383)

It caught on because it describes what millions of people were already doing: building real things with AI, without traditional programming skills.

This isn't a toy. People are shipping production apps, automating their businesses, and building tools that previously required a development team. The barrier to entry for software has dropped to near zero.

Since then the idea has grown into a spectrum. At one end you accept whatever the AI hands back, which is perfect for quick experiments. At the other, you surround its output with structure and checks so you can trust it in the real world. The real skill isn't picking a side; it's knowing how much structure each project deserves.

## Today is the worst AI will ever be.

Every model release makes vibe coding more capable. The skills you learn today, prompting and debugging and iterating, only become more powerful as the tools improve.

## Who is this for?

Vibe coding isn't just for tech people. Anyone with an idea and a willingness to iterate can build software now.

### Designers

Interactive prototypes, design tools, portfolio sites

Turn a Figma mockup into a working app in an afternoon

### Marketers

Landing pages, dashboards, lead gen tools, SEO analyzers

Build a campaign performance dashboard from your ad data

### Founders

MVPs, internal tools, customer portals, billing systems

Ship a working product before hiring a dev team

### Researchers

Data visualizations, survey tools, analysis scripts

Turn a dataset into an interactive explorer in minutes

### Educators

Quiz apps, curriculum tools, student dashboards

Create an interactive lesson with instant student feedback

### Operations

Workflow automations, reporting tools, inventory trackers

Replace a manual spreadsheet process with a real app

## What you need to get started

Less than you think. You probably have everything already.

### You need

-   A laptop or desktop
    
    Mac, Windows, or Linux, any will do
    
-   A web browser
    
    Chrome, Safari, Firefox, or Edge
    
-   An AI tool
    
    ChatGPT, Claude, or any chat-based AI (free tiers work)
    
-   Curiosity and patience
    
    The willingness to iterate when things don't work
    

### You don't need

-   Programming experience
-   A CS degree
-   Math skills
-   Money

Helpful but not required. You'll learn as you go.

AI gets you roughly 80% of the way to almost any app astonishingly fast. The last 20% is where things stay hard: security, authentication, storage, scale, and the edge cases nobody thought of. These skills can be learned, they're very well documented, and AI can help you in any dimension. Just ask. At the vibe coder level it's about fast prototyping, but it can be much more.

## Levels of Learning

Below is an interactive map of the AI development stack. It's organized into three levels that mirror how people actually learn to code with AI:

L1

### Vibe Coder

Prompt it, ship it. Write prompts, get code, see it run. Start here if you're brand new.

L2

### Project Builder

Plan, build, iterate. Debug, connect pieces, and learn the tools developers actually use.

L3

### Agentic Engineer

Full pipeline with AI agents. Deploy, monitor, and scale secure, multi-feature applications.

Click any concept to see what it is, why it matters, and which tools to try. Mark cards as “known” to track your progress.

L1Vibe CoderL2Project BuilderL3Agentic Engineer

Go from idea to working prototype in minutes

Prompt it, ship it

Prompt

Generate

Iterate

Preview

Publish

FilterL1L2L3ClearSortA–ZLevel

## Concepts (17)

▼

Ask for questions→ Prompt

Let the AI clarify before building

L1

Build me a…→ Prompt

Describe what you want built

L1

Export→ Publish

Export or copy the output

L1

Generate

AI writes the code

L1L2L3

Iterate

Refine with follow-up prompts

L1L2

Keep it simple→ Prompt

Start minimal, add complexity later

L1

Localhost→ Preview

Run the app on your machine

L1L2

Markdown→ Prompt

The lingua franca of AI prompting

L1

Natural language→ Prompt

Instructions in your own language

L1

Preview

See it live instantly

L1L2

Prompt

Describe what you want to build

L1L2L3

Prototype→ Generate

Quick working proof of concept

L1

Publish

Ship to the world

L1L2L3

Refinement→ Iterate

Don't give up, keep chatting

L1

Share link→ Publish

Share your prototype with others

L1

Single prompt→ Generate

One-shot code generation

L1

Start over→ Iterate

No sunk cost: drop and rebuild

L1

## Tools (6)

▼

![](/api/favicon?domain=bolt.new)

Bolt→ Generate

Rapid full-stack generation

L1[bolt.new](https://bolt.new)

![](/api/favicon?domain=chat.openai.com)

ChatGPT Canvas→ Generate

Visual canvas for building and iterating

L1[chat.openai.com](https://chat.openai.com)

![](/api/favicon?domain=www.anthropic.com)

Claude Artifacts→ Generate

Instant browser-based apps

L1[anthropic.com](https://www.anthropic.com)

![](/api/favicon?domain=aistudio.google.com)

Google AI Studio→ Generate

Build and test AI models and apps

L1L2[aistudio.google.com](https://aistudio.google.com)

![](/api/favicon?domain=lovable.dev)

Lovable→ Generate

AI-powered web app builder

L1[lovable.dev](https://lovable.dev)

![](/api/favicon?domain=v0.dev)

V0→ Generate

Vercel's generative UI tool

L1[v0.dev](https://v0.dev)

## Code is languageC(o0de3 i!s$ l1a@ng9ua@g9e3

LLMs are good at language, of course. What makes them exceptional at coding is verifiability. It either compiles or it doesn't. That binary feedback is exactly what models need to self-correct and ship working code.

That same idea becomes your most important skill. Anyone can get code that runs. The people who build things worth keeping have a way to check it's actually _right_, not just that it didn't crash. “It seems to work” versus “I've verified it works” is the real line between a throwaway demo and something you can rely on.

## Skills still matter

While traditional code is created by characters and lines, AI programming is about asking the assistant to implement "chunks": a feature, a fix, or a flow. This doesn't absolve you from the responsibility of having correct code.

### The more you build, the more you'll appreciate the code

You might abstract it away, but the computer doesn't. Having a programmer's perspective on user flows, authentication, and databases will help you build better apps.

### AI fills in blanks, but can't make judgment calls

Language models often can't decide which questions to ask. The ROI for having a fundamental understanding of all areas you're involved with is immense.

### Software breaks in unexpected places

Most people interact with code only through the UX. But bugs happen in authentication flows, database queries, API calls, and edge cases. Understanding these layers helps you debug faster and build more reliable apps.

### AI fills in blanks, but can't make judgment calls

Language models often can't decide which questions to ask. The ROI for having a fundamental understanding of all areas you're involved with is immense.

### Software breaks in unexpected places

Most people interact with code only through the UX. But bugs happen in authentication flows, database queries, API calls, and edge cases. Understanding these layers helps you debug faster and build more reliable apps.

## Your first 10 minutes

The best way to understand vibe coding is to try it. Here's a step-by-step walkthrough you can do right now.

1

### Open an AI tool

Go to any of these. Free accounts work fine. No install needed.

[![](/api/favicon?domain=claude.ai)Claude](https://claude.ai)[![](/api/favicon?domain=chatgpt.com)ChatGPT](https://chatgpt.com)[![](/api/favicon?domain=aistudio.google.com)Google AI Studio](https://aistudio.google.com)

All three have free tiers. Pick whichever feels right.

2

### Describe what you want

Type a prompt that describes a small app. Be specific about what it should do, not how to code it.

CopyShuffle

The more specific your description, the better the result. Think about what you'd want to see on screen.

3

### See it run

The AI will generate code and show you a preview. Click through it. Does it work? Does it look right?

Claude shows an interactive Artifact. ChatGPT shows a Canvas. Both let you see the result immediately.

4

### Iterate

Now change it. Ask for improvements. This is where vibe coding really happens, in the back-and-forth conversation.

CopyShuffle

Don't try to get everything perfect in one prompt. Small, focused requests work better.

5

### You just vibe coded

That's it. You described what you wanted, refined it through conversation, and ended up with a working app. No syntax, no setup, no boilerplate. From here, you can keep going: add features, learn about deployment, or start a new project entirely.

## Publish your v0 project to the web

The simplest path is: build in [v0](https://v0.app), save to [GitHub](https://github.com), deploy with [Vercel](https://vercel.com). If you can click buttons, you can ship a website.

[GitHub](https://github.com)

Where your project code lives (a “repository”).

[Vercel](https://vercel.com)

One-click hosting that publishes your site to a live URL.

[v0](https://v0.app)

Your project hub: build, publish, and manage settings.

### Workshop walkthrough (v0 → GitHub → Vercel)

1.  ### Create accounts (10 minutes)
    
    Sign up on [vercel.com](https://vercel.com) first. Then go to [v0.app](https://v0.app) and log in with **Continue with Vercel**. Finally, create a [GitHub.com](https://github.com) account, so v0 can create a repository for you.
    
2.  ### Build something in v0
    
    Open v0 and prompt: **“Build a website for a bakery that fits the vibe of (city, country).”** Select model: **Auto**.
    
    ![v0 prompt and model selector](/_next/image?url=%2Fimages%2Fvibe-coding-v0%2Fv0a.webp&w=3840&q=75)
    
3.  ### Publish (create a GitHub repo)
    
    Top-right in v0, click **Publish**.
    
    ![v0 publish button](/_next/image?url=%2Fimages%2Fvibe-coding-v0%2Fv0b.webp&w=3840&q=75)
    
4.  ### Create the repository
    
    Click **Create repository**. Connect GitHub in the popup, then click **Create repository** again.
    
    ![v0 create repository dialog connected to GitHub](/_next/image?url=%2Fimages%2Fvibe-coding-v0%2Fv0c.webp&w=3840&q=75)
    
5.  ### Publish to production (Vercel deploy)
    
    Click **Publish** again, top-right, then click **Publish to production**. Done. Your site is live.
    

### Change the random domain to your own

Vercel gives you a random URL at first. You can rename it (or connect a custom domain) from the v0 project settings.

1.  ### Open your v0 projects
    
    Go to [v0.app/projects](https://v0.app/projects). Find your project and click its name.
    
2.  ### Open settings
    
    Click the **3 dots** menu, then click **Settings**.
    
3.  ### Set the domain
    
    Click **Domain**, write the new domain, and click **Save**.
    
    ![v0 domain settings](/_next/image?url=%2Fimages%2Fvibe-coding-v0%2Fv0f.webp&w=3840&q=75)
    

If you are using your own domain (like **yourname.com**), Vercel may ask you to add a DNS record. That is normal.

## Common stumbling blocks

Everyone hits these. Knowing they're normal makes them easier to push through.

### "It worked, then I changed one thing and everything broke"

This is normal. AI sometimes makes cascading changes you didn't ask for. The fix is version control. Commit when things work, so you can always go back.

Learn to use Git early. Commit often. Branches are free.

### "The AI keeps going in circles"

When the AI fixes one thing and breaks another repeatedly, the conversation has gone stale. The model is working from accumulated confusion.

Start a new chat. Summarize what you have, what works, and what's broken. Fresh context usually breaks the loop.

### "I don't understand the code it wrote"

You don't need to understand every line. But you should understand what each file does and how the pieces connect. Ask the AI to explain.

Paste the code back and say "Explain this to me like I've never coded before." Do this regularly.

### "My app looks ugly"

AI defaults are functional but generic. Design takes iteration, just like code. You need to be specific about what you want things to look like.

Share screenshots of designs you like. Say "make it look like this" or use UI generators like V0 for the visual layer.

### "I can't get it to deploy"

The gap between "works on my machine" and "works on the internet" trips up everyone. Build errors, environment variables, and hosting config are common blockers.

Start with one-click deploy platforms (Vercel, Netlify). Paste the entire error message to the AI, never a summary.

### "It looks right but does the wrong thing"

AI's mistakes have changed. They used to be obvious crashes; now the code often looks clean, runs fine, and is quietly wrong: a miscalculated total, a missed case, the wrong record updated. It can even pass a quick test.

Check behavior, not just that it ran. Try real and weird inputs, and confirm it does the right thing. "It didn't error" is not "it's correct."

### "I'm spending more time debugging than building"

Welcome to software development. Even experienced developers spend 30-50% of their time debugging. This ratio improves with experience but never goes to zero.

This is the job. Get comfortable with DevTools (F12), learn to read error messages, and always paste the full error to the AI.

## Managing Expectations

Progression from Prototype to ProductImplementationIdeaPartsWholePrototypePilotProductWhat you canexpect toachieve on yourown with AI.

Click a stage to learn more.

## Practical techniques

Show more (shuffle)

## What people have built

Real projects built by non-programmers using AI tools. From internal tools to public products.

### Sales Dashboard

Built by a Marketing director

Connected to their CRM API and built a real-time dashboard showing pipeline metrics, conversion rates, and team performance.

[![](/api/favicon?domain=claude.ai)Claude](https://claude.ai)[![](/api/favicon?domain=cursor.com)Cursor](https://cursor.com)[![](/api/favicon?domain=vercel.com)Vercel](https://vercel.com)

### Company Website

Built by a Startup founder

Full marketing site with blog, pricing page, contact form, and CMS integration. Launched in a weekend instead of waiting weeks.

[![](/api/favicon?domain=v0.dev)V0](https://v0.dev)[![](/api/favicon?domain=nextjs.org)Next.js](https://nextjs.org)[![](/api/favicon?domain=vercel.com)Vercel](https://vercel.com)

### Customer Support Bot

Built by a Operations manager

An AI chatbot trained on the company's docs and FAQ. Handles 60% of support tickets automatically and routes the rest.

[![](/api/favicon?domain=openai.com)ChatGPT API](https://openai.com)[![](/api/favicon?domain=supabase.com)Supabase](https://supabase.com)

### Pricing Calculator

Built by a Freelance consultant

An interactive tool that prospects use to estimate project costs. Captures leads and sends quotes automatically.

[![](/api/favicon?domain=claude.ai)Claude Artifacts](https://claude.ai)[![](/api/favicon?domain=react.dev)React](https://react.dev)

### Research Analysis Tool

Built by a PhD researcher

Uploads PDFs, extracts key findings, and generates structured literature reviews. Saves hours per paper.

[![](/api/favicon?domain=python.org)Python](https://python.org)[![](/api/favicon?domain=www.anthropic.com)Claude API](https://www.anthropic.com)

### Inventory Tracker

Built by a Small business owner

Tracks stock levels, sends low-stock alerts, and generates purchase orders. Replaced a spreadsheet that was failing.

[![](/api/favicon?domain=bolt.new)Bolt](https://bolt.new)[![](/api/favicon?domain=supabase.com)Supabase](https://supabase.com)

### Workflow Automation

Built by a Project manager

Connects Slack, email, and project tracker. Automatically creates tasks from client emails and posts standup summaries.

[![](/api/favicon?domain=www.anthropic.com)Claude Code](https://www.anthropic.com)[![](/api/favicon?domain=nodejs.org)Node.js](https://nodejs.org)

### Educational Quiz App

Built by a High school teacher

Students answer questions, get instant feedback, and see progress over time. Generates new questions from lesson materials.

[![](/api/favicon?domain=lovable.dev)Lovable](https://lovable.dev)[![](/api/favicon?domain=supabase.com)Supabase](https://supabase.com)

## What to do next

The best way to learn is to build something small. So, what do you want to make? If you're not sure yet, take a moment to think about it, or try the little exercise below.

Not sure what to build? Get three ready-to-use project prompts you can copy and paste into your AI assistant.

Get three ideas

## How much will it cost you?

Cost is independent of skill level. You can be L3 at €20/month. The difference is how much you use the tools, not how good you are.

### Free

…

Enough to learn and prototype

-   —ChatGPT / Claude free tiers
-   —VS Code + GitHub Copilot free tier
-   —Vercel / Netlify free hosting
-   —GitHub for version control
-   —Supabase free tier (database + auth)

You can reach L3 on free tools alone, just with usage limits.

### Builder

…/mo

Remove the friction

-   —Cursor Pro or GitHub Copilot Pro
-   —Claude Pro / ChatGPT Plus
-   —Faster models, longer context
-   —Priority access during peak hours
-   —Enough for most real projects

The sweet spot. Most builders never need more than this.

### Power User

…/mo

For very specific needs

-   —Multiple AI subscriptions (Cursor + Claude + ChatGPT)
-   —Max-tier plans with highest rate limits
-   —Dedicated API access for custom workflows
-   —Premium hosting & database scaling
-   —Running many projects simultaneously

Only if you're shipping production apps at scale or running a business on AI tools.

## Want to run this with your team?

This page is our open guide. For organizations, we deliver it as Build Sessions: hands-on workshops that take non-technical teams from idea to working prototype in a half day, using a version of this guide calibrated to your group.

[Explore Build Sessions](/services/build-sessions)

## Links (18)

▼

-   [![](/api/favicon?domain=prototypr.io)https://prototypr.io/note/vibe-coding-cursor-windsurf-slot-machine· Apr 29, 2025](https://prototypr.io/note/vibe-coding-cursor-windsurf-slot-machine)
-   [![](/api/favicon?domain=www.bensbites.com)https://www.bensbites.com/p/coding-with-ai-a-community-members-workflow· Feb 7, 2025](https://www.bensbites.com/p/coding-with-ai-a-community-members-workflow)
-   [![](/api/favicon?domain=dubroy.com)https://dubroy.com/blog/five-coding-hats/· Feb 3, 2025](https://dubroy.com/blog/five-coding-hats/)
-   [![](/api/favicon?domain=qntm.org)https://qntm.org/devphilo· Feb 3, 2025](https://qntm.org/devphilo)
-   [![](/api/favicon?domain=pgaleone.eu)https://pgaleone.eu/ai/coding/2025/01/26/using-ai-for-coding-my-experience/· Jan 26, 2025](https://pgaleone.eu/ai/coding/2025/01/26/using-ai-for-coding-my-experience/)
-   [![](/api/favicon?domain=nsavage.substack.com)https://nsavage.substack.com/p/when-ai-promises-speed-but-delivers· Jan 26, 2025](https://nsavage.substack.com/p/when-ai-promises-speed-but-delivers)
-   [![](/api/favicon?domain=blog.yfzhou.fyi)https://blog.yfzhou.fyi/posts/tdd-llm/· Jan 16, 2025](https://blog.yfzhou.fyi/posts/tdd-llm/)
-   [![](/api/favicon?domain=www.answer.ai)https://www.answer.ai/posts/2025-01-08-devin.html· Jan 8, 2025](https://www.answer.ai/posts/2025-01-08-devin.html)
-   [![](/api/favicon?domain=shekhargulati.com)https://shekhargulati.com/2025/01/07/chat-first-development-a-better-way-to-use-llms-for-coding/· Jan 7, 2025](https://shekhargulati.com/2025/01/07/chat-first-development-a-better-way-to-use-llms-for-coding/)
-   [![](/api/favicon?domain=huyenchip.com)https://huyenchip.com/2025/01/07/agents.html· Jan 7, 2025](https://huyenchip.com/2025/01/07/agents.html)
-   [![](/api/favicon?domain=crawshaw.io)https://crawshaw.io/blog/programming-with-llms· Jan 6, 2025](https://crawshaw.io/blog/programming-with-llms)
-   [![](/api/favicon?domain=anthropic.skilljar.com)https://anthropic.skilljar.com/claude-code-in-action· Jan 1, 2025](https://anthropic.skilljar.com/claude-code-in-action)
-   [![](/api/favicon?domain=www.anthropic.com)https://www.anthropic.com/engineering/building-effective-agents· Dec 19, 2024](https://www.anthropic.com/engineering/building-effective-agents)
-   [![](/api/favicon?domain=addyo.substack.com)https://addyo.substack.com/p/the-70-problem-hard-truths-about· Dec 4, 2024](https://addyo.substack.com/p/the-70-problem-hard-truths-about)
-   [![](/api/favicon?domain=xcancel.com)https://xcancel.com/bcherny/status/2007179832300581177· Dec 1, 2024](https://xcancel.com/bcherny/status/2007179832300581177)
-   [![](/api/favicon?domain=news.ycombinator.com)https://news.ycombinator.com/item?id=45642527· Nov 15, 2024](https://news.ycombinator.com/item?id=45642527)
-   [![](/api/favicon?domain=johnsalvatier.org)http://johnsalvatier.org/blog/2017/reality-has-a-surprising-amount-of-detail· May 13, 2017](http://johnsalvatier.org/blog/2017/reality-has-a-surprising-amount-of-detail)
-   [![](/api/favicon?domain=www.paulgraham.com)https://www.paulgraham.com/makersschedule.html· Jul 1, 2009](https://www.paulgraham.com/makersschedule.html)

## Videos (10)

▼

-   ![](https://img.youtube.com/vi/YG459bD8qmw/hqdefault.jpg)
    
    ### How Cursor AI Works (No Experience Needed)
    
    15:00
    
-   ![](https://img.youtube.com/vi/bEU15KXIAVk/hqdefault.jpg)
    
    ### Cursor AI Tutorial for Beginners
    
    21:40
    
-   ![](https://img.youtube.com/vi/gqUQbjsYZLQ/hqdefault.jpg)
    
    ### How to Use Cursor AI Like a Pro — Full Stack Tips
    
    40:30
    
-   ![](https://img.youtube.com/vi/HBMjnDAqKkE/hqdefault.jpg)
    
    ### Claude Code: The Terminal-Based AI Coding Agent
    
    25:15
    
-   ![](https://img.youtube.com/vi/sKxUEnylsQg/hqdefault.jpg)
    
    ### Discover Cursor: The AI-Powered Code Editor
    
    31:10
    
-   ![](https://img.youtube.com/vi/1CC88QGQiEA/hqdefault.jpg)
    
    ### Live Coding with AI — Full Session
    
    3:11:30
    
-   ![](https://img.youtube.com/vi/V9_RzjqCXP8/hqdefault.jpg)
    
    ### Cursor Composer: Multi-File AI Coding
    
    24:10
    
-   ![](https://img.youtube.com/vi/nUTR11D8q08/hqdefault.jpg)
    
    ### Build a Web Directory: Cursor + V0 Tutorial
    
    45:20
    
-   ![](https://img.youtube.com/vi/oBDdcVaRhUk/hqdefault.jpg)
    
    ### Adding AI to Your Project with Workers AI
    
    26:40
    
-   ![](https://img.youtube.com/vi/u3wPImWBz7c/hqdefault.jpg)
    
    ### Cursor AI Productivity Tips
    
    8:50
    

## Events

Join us at upcoming events and workshops.

![Oct 23, 2026, 10:00](https://res.cloudinary.com/envisioning/image/upload/f_auto,q_auto:best/v1790598348/events/c3b5953c-c656-41d7-829a-98f5d4b36345-9gl47x.jpg)

Oct 23, 2026, 10:00

IA para Foresight: prototipe sua ferramenta de sinais

Oficina prática de prototipagem com IA para pesquisa de futuros: introdução a sinais de mudança, demonstração do Signals e construção de protótipos com ChatGPT, Claude e v0. Sem conhecimento prévio de programação necessário.

With Casa FirjanRio de Janeiro, BR

[https://futurospossiveis.casafirjan.com.br](https://futurospossiveis.casafirjan.com.br)

![Nov 5, 2026, 12:00](https://res.cloudinary.com/envisioning/image/upload/f_auto,q_auto:best/v1785160411/seosuxxdtejrae7dfput.png)

Nov 5, 2026, 12:00

Programe sem saber programar

Criar sites e aplicativos ficou possível, de repente, para quem não é da área técnica.

Online

![Nov 12, 2026, 16:00](https://res.cloudinary.com/envisioning/image/upload/f_auto,q_auto:best/v1783254884/signals/events/2026-2027/04-future-of-retail-crm-wide.png)

Nov 12, 2026, 16:00

The Future of Retail

A live STEEP scan on returns, resale, and reverse logistics flipping from cost center to strategic lever.

Online

[https://luma.com/envisi-wxb9](https://luma.com/envisi-wxb9)

[View all events](/events)

## Advanced Mode

For people who build with AI and now have to maintain what they built.

This page covers getting started. Advanced Mode is what comes after: six monthly sessions on maintenance, tech debt, architecture you can't undo, and reviewing code you didn't write.

-   ### Bring something that is live
    
    One thing that is running, or will be during the cohort, that someone other than you depends on. That is the whole admission bar.
    
-   ### Twelve peers, not a lecture
    
    Six monthly sessions of 90 minutes, online, capped at twelve. Same structure every time: one deep case, one theme, then blockers round the room.
    
-   ### You set the running order
    
    Applicants rank the six themes (stacks, decisions you can't undo, reviewing code you didn't write), and the ranking is what we follow.
    

[See Advanced Mode](/advanced-mode)

## Interested in our work?

Reach out to learn how we can help you with your foresight needs.

Contact Envisioning

1 / 24

---

On this page

-   01Intro
-   02What is vibe coding?
-   03Today is the worst AI will ever be
-   04Meme break
-   05Who is this for?
-   06What you need
-   07Hard things
-   08Levels of Learning
-   09Interactive Graph
-   10Concepts & Tools
-   11Code is language
-   12Skills still matter
-   13Your first 10 minutes
-   14Publish to the web
-   15Common stumbling blocks
-   16Managing Expectations
-   17Practical techniques
-   18What people have built
-   19What to do next
-   20How much will it cost you?
-   21Links
-   22Videos
-   23Upcoming events
-   24Advanced Mode

Related guide

[Git for non-coders](/learn/git)

---