Start from zero, finish with production-safe skills. The core curriculum teaches you to supervise AI agents, catch their mistakes, and ship secure software. If you need a concrete first move right now, start with a copy-paste prompt, then use the curriculum to understand why it works. Start free with Explorer, then unlock the full Guild Member library when you need the deeper systems work.
The fastest useful on-ramp is usually one safe prompt, one reviewable change, and one matching lesson.
Need the public curriculum in one machine-readable document? Open the plain-text learn catalog.
If you are not a software developer, this is the fastest useful on-ramp: copy one safe sample prompt, scope the job, protect secrets, review the diff, and make the agent stop after one clear change you can inspect.
Want every starter prompt in one paste? Copy the full bundle here or open the plain-text export for the exact machine-readable version.
Use this before implementation work when you want the agent to set one goal, explain the plan, verify the result, and stop after one reviewable change.
"I want to work in a safe beginner loop.
Please do only this one task: [describe one tiny change].
Goal:
- outcome: [what should be true]
- scope: [files, pages, or systems in scope]Use this when your current request feels vague and you want the agent to help shape a safer, sharper implementation prompt before files change.
**Use this with Cursor or Claude Code before you ask for implementation work:**
"Help me tighten this coding prompt before any files are changed.
Project context: [stack, app purpose, relevant data model]
Goal: [the feature or fix I want]
Rough prompt: [paste your current prompt]Use this after an AI-generated change lands so the reviewer focuses on correctness, security, edge cases, and misleading tests.
"Review the diff between my branch and `main`.
For every finding:
1. label it as must-fix, should-fix, consider, or optional
2. explain why it matters
3. point to the relevant file or code sectionRun this before you paste configs, screenshots, or terminal output into an AI tool so you do not leak API keys, connection strings, or internal URLs.
"I am about to share this small app with another person for the first time.
Please give me a beginner-safe pre-share review.
Context:
- project: [describe project]
- who will see it: [friend/coworker/client/internal team]Curated prompt packs
If you do not want to browse prompt-by-prompt, open a pack built around one concrete job: getting through your first agent session, tightening prompts, protecting your work, reviewing a diff, getting a demo ready for production, or thinking in systems before the agent writes itself into a corner.
Prompts for a first Claude Code, Codex, or Cursor session so the agent sets a goal, explains scope, justifies tools or loops, verifies the result, and stops after one safe first move.
Featured prompt
Safe Agent Loop
Use this before implementation work when you want the agent to set one goal, explain the plan, verify the result, and stop after one reviewable change.
Prompts for scoping work, protecting secrets, and making the agent stop after one reviewable step.
Featured prompt
Pre-Flight Secrets Check
Run this before you paste configs, screenshots, or terminal output into an AI tool so you do not leak API keys, connection strings, or internal URLs.
Prompts for turning a promising AI-built demo into something you can share, test, deploy, sell, and improve without pretending it is production-ready too early.
Featured prompt
The First Production Stack — Domains, Auth, Data, Logs, and Payments
The practical baseline for turning an AI-built demo into a real software product: DNS, hosting, database, auth, observability, GitHub, durable notes, subscriptions, and security sweeps.
Prompts for tightening requests, reviewing diffs, verifying fixes, and debugging without letting the agent thrash or loop blindly.
Featured prompt
Review The Diff
Use this after an AI-generated change lands so the reviewer focuses on correctness, security, edge cases, and misleading tests.
Prompts for tightening vague requests, decomposing big ideas, using reasoning plans, teaching patterns with examples, and avoiding prompting anti-patterns.
Featured prompt
The Anti-Patterns — Prompts That Produce Bad Code
Recognize and avoid the most common prompting mistakes that lead to buggy, bloated, or wrong code.
Prompts that push the agent toward architecture, tradeoffs, and production-safe structure instead of surface fixes.
Featured prompt
Choosing Your Tech Stack — A Decision Framework
A practical framework for choosing the right tools and technologies for your project — with sensible defaults for AI-assisted builders.
Prompts for Git, checkpoints, backups, and version-control habits before you let the agent touch more files.
Featured prompt
Don't Lose Your Work — Folders, Git, and Checkpoints
The minimum safe setup for total beginners: a real project folder, a Git repo, a remote backup, and repeatable checkpoints.
Need more than the safest first prompt?
Browse the full public prompt library or jump straight into the Start Here path that explains how to use those prompts without losing control.
If you are not a professional developer, this page should reduce fear instead of creating more of it. These are the practical answers behind the learning-path promise.
Yes. The learning paths are written for people who can already get output from AI tools but do not yet trust their technical judgment. The goal is not to turn you into a career software engineer. The goal is to help you supervise the agent, spot risk, and ship changes you can defend.
Start with the Explorer on-ramp and the Start Safely prompt pack. Use one prompt, one tiny change, and one matching lesson. That combination gives you an immediate move you can copy and paste, plus the reasoning that explains why the prompt is safe.
The public side gives you the blog, the prompt library, the prompt packs, and the Explorer on-ramp paths. Guild Member unlocks the deeper path library, the production systems work, and the structured curriculum that helps you move beyond isolated tips into repeatable judgment.
The prompts are the immediate operating moves. The lessons teach the mental model behind those moves so you can review the output, catch failure modes, and adapt the pattern to your own project instead of copying prompts blindly.
The curriculum keeps returning to the same loop: set one goal, constrain scope, protect secrets, inspect the diff, run the right tests or browser checks, checkpoint the result, and stop before the blast radius grows. That is the core skill non-software developers need if they want AI agents to be useful without becoming dangerous.
Want the fastest safe start instead of more browsing?
Open the copy-paste starter prompt pack, then move into the matching free lessons that explain how to supervise the agent.
3 paths. 59 lessons. The free starting sequence. Learn the workflow, the mental model, and the AI-tool habits that keep new builders from shipping preventable mistakes.
A zero-to-one on-ramp for people who have never built software with AI before. Learn the safe workflow before you touch a real project.
The next stage after Start Here: software mental models, vocabulary, and tool context for builders who have already shipped one tiny thing with AI. Free for everyone.
How to get the best results from AI coding assistants, from Cursor to Claude Code.
4 paths. 88 lessons. The paid core curriculum. Move from safe fundamentals into source control, security, your first deployed product, and the operational pieces real software needs.
Git is your safety net. Master it before your AI agents make a mess of your repo.
The critical security knowledge every AI-assisted builder needs before shipping anything to real users.
A step-by-step guide to building and deploying your first web application from scratch.
The essential features every real product needs — auth, payments, email, analytics, and legal.
14 paths. 276 lessons. The deeper library for production systems. Go beyond the core workflow into databases, APIs, DevOps, architecture, cloud infrastructure, identity, compliance, mobile, and agent orchestration.
Go beyond basics into real data architecture — SQL mastery, database design, and data patterns.
Understand, build, and integrate with APIs — the bridges between software systems.
CI/CD pipelines, infrastructure, monitoring, and DNS — everything between code and production.
React patterns, Next.js deep dives, modern styling, and testing strategies.
Design systems that scale — from monolith to microservices, caching to CQRS.
OWASP, supply chain attacks, infrastructure security, and AI-specific risks.
Build mobile apps with React Native and Expo — from foundations to App Store submission.
Understand where your code actually runs — from shared hosting to global cloud platforms.
Nothing matters except the data. Your app is disposable — your data is forever.
Go beyond prompting single tools. Orchestrate AI agents, build with agent SDKs, set up the MCP ecosystem.
OAuth flows, JWTs, federated identity, and the identity providers that power modern apps.
CRM, ERP, WMS, CMS, WordPress — the enterprise ecosystem AI-assisted builders will inevitably encounter.
Turn raw data into business decisions. Power BI, data warehousing, and the BI stack.
PCI DSS, HIPAA, pen testing, and ethical hacking. The compliance knowledge that separates amateurs from professionals.