From Idea to Build Plan
Vibe coding, prompting, Git and the fundamentals that keep you moving
The first night gives you enough technical footing to build quickly without treating the codebase like a black box. We take one product idea from a vague sentence to a useful brief, scaffold it with an AI coding tool, and save the first clean checkpoint in Git.
Dates TBD — evening workshops followed by a longer capstone hackathon at Workuity Biltmore. Join Discord or follow the Meetup calendar for the next cohort.
Or join the waitlist — the dates come to you.
Venue sponsor: Workuity. Format: the host builds live on screen. Bring a laptop and work along, or just watch — nobody is put on the spot.
Why this session
AI makes clear thinking more valuable, not less. Without a specific outcome, constraints and a safe way back, faster generation only creates a faster mess. This session installs the habits that make every later build recoverable.
What we cover
- 01
Vibe coding to agentic engineering
The four waves of AI-assisted development, where vibe coding works and breaks, and why building a screen is different from building a system.
- 02
Prompt for outcomes
Turn a vague request into what, where, behavior, constraints and a definition of done — enough context to get a useful first pass.
- 03
Read the shape of an app
Files, components, routes, packages and the terminal explained through the project in front of you.
- 04
Git as your safety net
Clone, branch, commit, inspect a diff and recover from a bad turn before the stakes get higher.
- 05
Generate and review the first slice
Ask the agent to plan and generate one visible interface, run it in the browser, inspect the diff and undo one bad change before saving the clean version.
- 06
Secrets and safe defaults
Environment variables, .gitignore and the difference between browser-safe configuration and server-only keys.
You leave with
A scoped product brief, a working project on your laptop, its first clean checkpoint pushed to GitHub and a repeatable prompt pattern for turning intent into small, reviewable changes.
To follow along
A laptop, a GitHub account and access to an AI coding tool such as Codex or Claude Code. No professional coding experience is required, but you should be comfortable using a laptop and completing the setup steps shared before the session. Watching and pairing are welcome.
Afterward
Nothing is required. It compounds if you run the same work on your own product. The suggested output:
01-foundations/ — product brief, project map, prompt recipe and the URL of your first GitHub repository.
Everything is open source. Missed the session? It's archived in Discord.
The session kit
Slides, a follow-along guide and skill files. Free to download, room or no room.
The community online
Recaps, archive links, questions between sessions, everyone else's work in progress.