Build a working application by describing what you want, then keep it honest. This workshop runs periodically, tailored each time to the group in the room, and needs no coding background.
What it covers
- What an AI agent is, and how it differs from a chatbot
- The agent loop: plan, act, observe, repeat
- Prompting that survives a long working session
- Building in layers, and debugging when the model is confidently wrong
- Data security — treat every prompt as a postcard, and what that rules out
- Hands-on: build something of your own, start to finish
Tools we work with
- Google Gemini / AI Studio
- Command-line coding agents
- Git and a deployment target
The exact tools change as the landscape does; the session is built around whatever is currently worth learning.
Details
- Audience: Students, staff, and faculty — no prior experience assumed
- Presented by: Utku Ege Tuluk, RITS
If you want this session run for your group, or have a project you want help starting, write to [email protected]. See also AI.