From ChatGPT to Your Own AI Solutions
ChatGPT, Claude, and other generative AI tools can be used as standalone assistants. However, we unlock significantly more possibilities when we integrate their capabilities directly into our own applications, internal processes, or customer-facing services.
In this hands-on workshop, you'll discover step by step how to use various large language models via APIs and how to build a simple, working AI solution from them.
What will you be doing?
- Using different models such as OpenAI, Claude, and DeepSeek
- Building your own chatbot with the Gradio tool
- Developing a multimodal chatbot that understands not only text but also images and audio
- Testing local language models with Ollama
What does this mean in practice?
Your own chatbot for customers or employees
In just a few hours, you'll have a working chatbot up and running for customer support, internal queries, or FAQs — without building an entire web application from scratch.
Choosing the right AI model
You'll compare different models based on their capabilities, costs, and data privacy requirements, and see how to swap out a model when needed.
AI that understands images and audio too
You'll try out use cases such as invoice and document analysis, processing photos of defects, transcription, and voice input.
AI without sending data to the cloud
You'll explore the option of running a local model on your own infrastructure — particularly valuable when working with sensitive or internal data.
Who is this workshop for?
The workshop is aimed at micro, small, and medium-sized businesses and employees who are already familiar with the basics of generative AI and want to take the next step by integrating AI into their processes, applications, or services.
Speaker: Andrej Duh
