Workshop: Deep Dive into LLM APIs
Mentor - Oleksandr Krakovetsky, AI Expert | CEO at DevRain | CTO at DonorUA | Author of books on generative artificial intelligence
We invite you to a workshop dedicated to working with the language model API!
Most users work with modern language models through ChatGPT or Gemini, but using the API opens up a completely different level of possibilities. You will be able to manage generation parameters, connect external tools, perform fine-tuning of models, build RAG architectures and integrate LLM as an API backend into your own products.
Also important are practical skills in working with the context window, token optimization, understanding the non-determinism of models and ways to achieve stable, controlled system behavior.
At the workshop you will learn in detail:
- how modern language models work "under the hood"
- what mechanisms determine their behavior
- how to apply this knowledge to create reliable, manageable and scalable solutions
A separate block is dedicated to working with benchmarks:
- how to correctly evaluate models
- what characteristics have practical significance
- how to interpret the results of instruction-following, long-term context and other indicators tests
After the workshop you will be able to check models for relevance to specific tasks and make technical decisions based on metrics, not intuition.
Who will be interested?
- Software developers
- Tech leaders
- Architects
- Anyone who wants to understand how language models work under the hood
Format:
Date and time: December 15&16, online, start at 18:30 (Kyiv time, GMT+2)
Duration of each session: ~2.5 hours
Platform: Zoom. You will receive a link to the broadcast the day before the workshop, and it will also be available on this landing page
Recommended tools and subscriptions:
- OpenAI API Playground (Anthropic API Playground, Google AI Studio Playground теж ок)
- Ollama
- Postman або інший API-manager
Language of the event and presentations: Ukrainian
Program
- How modern large language models work
- API parameters for configuring the operation of large language models
- From Prompt Engineering to Context Engineering
- Using LLM-as-API-backend
- Building RAG solutions
- Instrumentalization: function calling, structured responses, reasoning, using external tools
- Context window, token optimization, efficient work with long queries
- Evaluating the quality of models ("instruction following", work with long context, AGI, etc.)
- Token optimization methods
- Practical demo
Mentor: Oleksandr Krakovetskyi
— Co-founder and CEO at DevRain, the Ukrainian IT company, Microsoft Data & AI Partner
— Co-founder and CTO at DonorUA, an intelligent blood donor recruiting system.
— Ph.D. in Computer Science
—Microsoft Regional Director, Microsoft Artificial Intelligence Most Valuable Professional.
—Microsoft Certified: Azure Data Science Associate, Azure Data Engineer Associate.
Event price
Access to online course sessions
Access to course recordings for a year
Presentations
Additional materials from the speaker
Access to a chat where the speaker will answer questions
Workshop participant certificate
10% discount on participation in Fwdays conferences
Available installment payments from Monobank and installment purchases from PrivatbankIf after the first lesson you realize that your expectations do not match, we will refund your money in full.