Generative AI has elevated AI into the mainstream and made it the topic of dinner-table conversations everywhere. Large Language Models (LLMs) from companies such as OpenAI, Google, and Anthropic enable software to do things that weren’t possible just a few short years ago. Small Language Models (SLMs) do most of what their LLM counterparts do, can be hosted locally, and do not incur per-token fees for text generation.
Are you looking for an on-ramp into generative AI? Curious to learn how to infuse AI into your apps and business processes and come away with lots of sample code to use in your next project? Bring your laptop and take a deep dive into generative AI in this hands-on masterclass. Learn what LLMs and SLMs are, how they work, how to put them over documents and databases, how to supercharge them using the Model Context Protocol (MCP), how to fine-tune them, and more. More importantly, learn the basics of building AI agents and see first-hand why companies are falling over themselves to embrace agentic AI.
Course contents
Module 1: Language Models Large and Small
Large Language Models (LLMs) are a boon to software development because they permit apps to do things that were impossible just a few short years ago. The number of LLMs is increasing every day. Get up close and personal with LLMs from OpenAI, Google, and others, learn what differentiates one from another, and learn how to leverage these models to write software that’s more intelligent than ever before. Also see some of the industry’s best open-source Small Language Models (SLMs) in action so you can decide whether an LLM or SLM best fits your workload.
Module 2: Making Language Models Smarter
If you’re using Large Language Models in your code and doing nothing to enhance them, you’re not getting everything you can from generative AI. Learn ways to supercharge your LLM usage, including how to extend LLMs with function calling and tool use, how to put LLMs over documents and databases, how to safely generate and execute code, how to use fine-tuning to increase performance while reducing cost and producing higher-quality results, and more. And take home tons of sample code for a head start incorporating these techniques into your next project.
Module 3: AI Agents and the Zen of Agentic AI
Agentic frameworks such as CrewAI, AutoGen, and Agno simplify the process of building AI agents that work alone or as part of a team. Agentic AI can orchestrate complex workflows, freeing users from the tyranny of prescriptive UIs. It’s now entirely possible to build an interface that accepts a command (typed or spoken) such as “Find all the nonstop flights from Atlanta to New York on June 1st that cost less than $800 and identify the three with the most unsold seats in first class” — or just about any other command you could dream up. Learn how to build AI agents and put them to work in your business, and see some jaw-dropping examples of the tasks they can perform. Also learn about the Model Context Protocol (MCP) and see how it augments the capabilities of AI agents.
Target audience and prerequisites
Content level: Advanced
Prerequisites:
Attendees should be comfortable programming in Python. You don’t have to be a Python expert, but most of the code samples and hands-on exercises will utilize Python. The concepts presented are applicable to any programming language, however.
Hands-on exercises:
The masterclass comprises three modules, each accompanied by an immersive hands-on exercise designed to reinforced what’s learned during the lectures and demos. In the final exercise, you’ll build an agentic Web app that exposes a team of AI agents trained to be expert stock analysts. The finished product is commercial-quality and something that you’ll want to share with others to show what you learned and help them understand why agentic AI is getting so much attention.
https://codecamp.ro/masterclasses/a-practical-guide-to-generative-ai-from-concepts-to-code-cluj-2025/
You may also like the following events from Codecamp Romania:
Also check out other
Workshops in Cluj-Napoca.
