Name: Ultimate Private AI: Full-Day Hands-On Workshop
Start: 2026-04-23T08:30:00+02:00
End: 2026-04-23T17:30:00+02:00
Location: Clubco CZ

Ultimate Private AI: Full-Day Hands-On Workshop

**Hands-on Workshop: Private AI in Go — Run Open-Source Models Locally**
This full-day, hands-on workshop takes you from zero to running open-source models directly inside your Go applications — without cloud APIs, without external servers, and without any data leaving your machine.
## Getting Started
You’ll begin with the fundamentals:
* Loading a model
* Running your first inference using the Kronk SDK
## Configuring for Performance
Next, you’ll learn how to tune models for your specific hardware:
* GPU layers
* KV cache placement
* Batch sizes
* Context windows
The goal is simple: extract maximum performance from whatever machine you are running on.
## Controlling Model Output
With the model properly configured, you’ll take precise control over its output using sampling parameters:
* Temperature
* Top-k
* Top-p
* Repetition penalties
* Grammar constraints that guarantee structured JSON responses
## High-Performance Caching
You’ll explore how Kronk’s caching systems work:
* System Prompt Cache (SPC)
* Incremental Message Cache (IMC)
These mechanisms eliminate redundant computation and dramatically accelerate multi-turn conversations. You’ll see a live progression from full prefill on every request to processing only the newest message.
## Building Real Applications
With the foundation in place, you’ll build practical, production-relevant systems:
### Retrieval-Augmented Generation (RAG)
Create a RAG pipeline that grounds model responses in your own documents using embeddings and vector search.
### Natural Language → SQL
Implement a system that generates database queries from plain English — with grammar constraints ensuring valid, executable SQL every time.
## End-to-End Progression
Each section builds on the previous one.
By the end of the day, you won’t just understand how private AI works — you will have built applications that:
* Load models
* Cache intelligently
* Retrieve contextual data
* Generate structured outputs and code
* Run entirely locally on your own hardware
---
## Workshop Leader
The workshop is led by **William Kennedy**, Managing Partner at Ardan Labs (Miami, Florida).
William travels from the United States to deliver this workshop, following the strong reception of his previous session.
He is the author of *Go in Action* and *The Ultimate Go Notebook*, has written more than 100 technical articles on Go, and is a founding member of GoBridge and the Go Developer Network (GDN), organizations dedicated to expanding Go adoption.
With years of experience teaching and building production-grade Go systems, William brings deep technical expertise and practical insight to this immersive workshop.