Learn Generative AI by Building Real Systems

IdeaWeaver AI Labs is a hands-on learning platform built for Software Engineers and DevOps Engineers who want to transition into Generative AI by understanding how real systems work.


How You’ll Learn

Our programs are cohort-based and focused on learning by building. Instead of relying on prompt-only workflows, students work on practical exercises and mini-projects that reflect how Generative AI systems are designed, trained, evaluated, and deployed in real-world environments.


What You’ll Work On

You’ll gain hands-on experience with:

  • Modern Generative AI tools and architectures
  • Retrieval-Augmented Generation (RAG)
  • Fine-tuning and model evaluation
  • AI agents and workflows
  • Tokenization, attention, and model internals
  • Training small language models from scratch

Built for Engineers

All programs emphasize practical implementation, clear mental models, and engineering depth. Students also get access to real GPU resources for hands-on experimentation and model training.

If you’re an engineer looking to move beyond surface-level AI usage and build Generative AI systems with confidence, IdeaWeaver AI Labs is designed for you.


Most Generative AI courses focus on tools and prompts.
IdeaWeaver AI Labs focuses on systems.

Here, you learn how Generative AI actually works, how models are trained, evaluated, and used in real-world systems.

We start from first principles and don’t assume prior GenAI or ML knowledge.
A working knowledge of Python is the only prerequisite.

You’ll work on real-world patterns and get hands-on access to real GPU resources.

Built by engineers, for engineers.


Learn by Building

Weekly live classes and hands-on exercises and mini-projects focused on real-world Generative AI systems, not slides.

Real GPU Access

Train, fine-tune, build and evaluate models using real GPU resources, not simulated environments.

From Basics to Models

Start from first principles and progress all the way to building and understanding small language models.

Hi, I’m Prashant


With 20+ years of experience across Software Engineering, DevOps, Cloud, Kubernetes, and Large-Scale Distributed Systems.

Over the years, I’ve worked on systems used by millions of users, built and operated production-grade cloud platforms, and helped teams debug, scale, and secure complex infrastructure. More recently, my focus has been on Generative AI, specifically how LLMs actually work under the hood and how to build reliable, real-world GenAI systems.

I’m the author of multiple technical books, a CNCF Kubestronaut, RHCA, and an AWS Community Builder. I actively teach and write about topics like LLM internals, fine-tuning, RAG, agents, and building small language models from scratch.

I created IdeaWeaver AI Labs to help engineers transition into Generative AI the right way, by building systems, understanding fundamentals, and learning through hands-on work, not hype.