Our workshop day is held on the 11th August, and is a fully catered full day experience.
This is a hands-on, full-day workshop where you'll go from zero to running open-source models directly inside your Go applications — no cloud APIs, no external servers, no data leaving your machine.
You'll start by loading a model and running your first inference with the Kronk SDK. Then you'll learn how to configure models for your hardware — GPU layers, KV cache placement, batch sizes, and context windows — so you get the best performance out of whatever machine you're running on. With the model tuned, you'll take control of its output through sampling parameters: temperature, top-k, top-p, repetition penalties, and grammar constraints that guarantee structured JSON responses.
Next you'll see how Kronk's caching systems — System Prompt Cache (SPC) and Incremental Message Cache (IMC) — eliminate redundant computation and make multi-turn conversations fast. You'll watch a conversation go from full prefill on every request to only processing the newest message.
With the foundation solid, you'll build real applications: a Retrieval-Augmented Generation (RAG) pipeline that grounds model responses in your own documents using embeddings and vector search, and a natural-language-to-SQL system where the model generates database queries from plain English — with grammar constraints ensuring the output is always valid, executable SQL.
Each part builds on the last.
By the end of the day, you won't just understand how private AI works — you'll have built applications that load models, cache intelligently, retrieve context, and generate code, all running locally on your own hardware.
By the end of this workshop, you'll leave with working code, a deep understanding of local model inference in Go, and hands-on experience across the full stack: model configuration, performance tuning, intelligent caching, retrieval-augmented generation, and structured code generation. 🚀
It's expected that you will have been coding in Go for several months.
A working Go environment running on the device you will be bringing to class.
Don't worry if you don't have the full hardware required for this. The instructor will provide everything you need to follow along and be able to run the examples.
Mac M1 series with at least 16 GB RAM (pref 32GB+).
Any Linux/Windows laptop with a dedicated GPU with at least 8GB VRAM (not system RAM) (pref 16GB).
Access to a cloud-based instance with a dedicated GPU with at least 8GB VRAM (pref 16GB).
Please clone the main repo (https://github.com/ardanlabs/kronk) for the class.
Please read the notes in the makefile for installing all the tooling and testing the code before class.
Please email the instructor, Bill Kennedy, for assistance.
This is a hands-on, full-day workshop where you'll build a complete AI-powered application in Go — from first prompt to production-ready system.
You'll start by connecting your Go application to a language model and grounding its responses in real data using Retrieval-Augmented Generation (RAG). Then you'll give it the ability to act on the world through Tool Calling, Function Execution, and the Model Context Protocol (MCP). With the core system working, you'll learn the advanced optimization techniques that separate prototypes from production — speculative decoding, semantic caching, and intelligent model routing.
Finally, you'll harden everything against the security threats unique to LLM-powered systems, from prompt injection to data exfiltration.
Each part builds on the last.
By the end of the day, you won't just understand these concepts — you'll have built, optimized, and secured a working system that retrieves, reasons, and acts.
By the end of this workshop, you'll leave with working code, a production-ready mindset for AI-powered Go applications, and hands-on experience across the full stack: retrieval, action, performance, and security. 🚀