Build custom GPTs
Turn prompts into reusable custom GPTs and AI assistants tailored to a job or business.
What you'll build
Real skills, real projects — not another slide deck.
Run models your way
Understand model selection across ChatGPT, Claude and Gemini, and run local LLMs with Ollama.
Master advanced techniques
Context engineering, token optimisation, structured JSON outputs and reliable multi-step prompting.
Write prompts that work
Structured, repeatable prompts for real tasks — not lucky one-offs that break next time.
- Structured JSON-output prompts for automation-ready results
- A context-engineered workflow that stays reliable at scale
- A custom GPT / AI assistant tuned to a specific use case
- A reusable prompt library for real business and content tasks
- A local LLM setup you control end to end
Who it's for
The skill under every AI workflow
Prompt engineering is the foundational skill behind every serious AI workflow — agents, automations, RAG systems and content engines all depend on prompts that are structured and reliable. This course goes well past 'write a good prompt' into context engineering, structured outputs and building reusable assistants, so your AI work is repeatable instead of hit-or-miss.
It suits anyone who uses AI at work — professionals, marketers, founders, students — and it's the natural first step before automation and agents. ONROL is project-first, so you finish with a prompt library, custom GPTs and assistants in a portfolio you keep and reuse.
The build-first idea
You'll have receipts, not just notes.
Most courses hand you slides; ONROL hands you a track record. You ship real AI — automations, agents, apps — throughout, and keep every piece. The result is demonstrable capability: things you made that work, not a list of topics you sat through.
Where to take this
Turn this into a program.
AI Career Accelerator
A 21-day career-focused entry — practical AI skills, real projects and job readiness.
Explore program →AI Generalist
The 3-month flagship — build 5+ real AI systems and a portfolio, no coding required.
Explore program →AI Architect
The advanced track — AI architecture, agents, RAG and production-grade systems.
Explore program →Good to know
The honest answers.
What will I build?
A reusable prompt library, custom GPTs and AI assistants, structured JSON workflows, and a local LLM setup — all kept in a portfolio you can reuse in your work or freelance projects.
Which AI models does it cover?
ChatGPT, Claude and Gemini for model selection, plus running local models with Ollama — so you understand strengths and trade-offs rather than relying on one tool.
Do I need to code?
No. Prompt engineering is done in natural language. The course is built for non-coders — professionals, marketers, founders and students who want dependable results from AI.
Is prompt engineering still a useful skill?
Yes — more than ever. As AI moves into automations, agents and RAG systems, the ability to write structured, reliable prompts and engineer context is the foundation everything else is built on.
Reserve your seat
Ready when you are. Register in 20 seconds.
Tell us a little about you and we'll follow up with the upcoming batch, the schedule, and how the program works.
Request received.
Thank you — our team will reach out shortly with the next cohort details.