Practical playbooks for engineers — free to download and share.
Prompt Engineering Playbook
How to structure prompts, apply prompt engineering patterns, and build reliable LLM-powered workflows — especially in regulated domains like payments and POS.
Based on concepts from Building Agentic AI and refined for engineering teams building AI into production systems.
BeviaLLM Playbook — Building a Language Model From Scratch
A comprehensive guide to understanding and building a GPT-like language model from the ground up using Python and NumPy. No frameworks, no abstractions — every component implemented manually: embeddings, self-attention, layer normalization, backpropagation, and AdamW optimization.
Covers the full Transformer architecture, the mathematics behind attention, a complete implementation deep dive, and hands-on experiments you can run on a laptop.
Source code: github.com/Bevia/BeviaLLM
If you find these useful, I’d love to hear from you — contact@corebaseit.com.