Effective Vibe Coding for Beginners
About This Course
Vibe coding means describing what you want in plain language and steering an agent, rather than writing every line yourself. It is fast and genuinely useful, and the result is only as good as your steering. This one-day workshop teaches the steering: how to get a coding agent to build the thing you actually wanted, and how to tell whether it did.
You work in VS Code with OpenAI's Codex agent, building a small Streamlit application from scratch across the day. The point of the example is the order you build it in, and you can run the exercises against your own data instead if you would rather practise on your own work.
The aim is competent prototypes, not production systems. Most of the day goes on the part that decides whether a prototype is worth keeping: reading what the agent gave you and proving it does what you asked. You finish with a written review checklist, a set of project rules, and habits that transfer directly to Claude Code, OpenCode, Aider and whatever replaces them.
Who This Course Is For
This workshop is for scientific researchers and other technical professionals who are not full-time software developers but need to build small applications, scripts and reports for their work. It also suits developers who are new to agentic coding tools and want a disciplined workflow rather than trial and error.
The room is mixed by design. Every chapter has a core path everyone follows and an extended exercise for people who already write code.
Prerequisites
No software engineering experience is required. You do not need to have used Codex, Claude Code, or any other agent before.
Familiarity with the command line helps but is not assumed. The workshop
introduces the small set of terminal and git commands you need on the day.
What You'll Learn
- Drive a coding agent through a spec-first workflow instead of vague "build me an app" prompts.
- Write a short implementation spec, and plan a small Streamlit application so that its core logic can be tested.
- Work safely with an agent, using sandbox and approval settings deliberately
and keeping rollback cheap with
git. - Apply test-driven development with an agent for the parts of a project where behaviour actually matters.
- Review AI-generated code against a specification, and recognise the failure patterns that recur.
- Encode project rules and reusable prompts so the agent applies them in every session.
Course Syllabus
AI-assisted coding with VS Code and Codex
- How coding agents work, and why output is plausible rather than correct
- Managing context, and working spec first
- Version control as a safety net
Working safely with coding agents
- Sandboxing, approvals and practical guardrails
- Data governance for local and cloud tasks
Reviewing AI-generated code
- A repeatable review loop, run against the spec
- Recognising "AI slop" and recurring failure patterns
Test-driven development with AI coding agents
- Writing and running tests alongside an agent
- Making tests the default for new logic
Configuring coding agents
- Project rules, reusable prompts and helper scripts
Beyond Codex: other tools and next steps
- Choosing between Codex, Claude Code and the other agentic coding tools