AI & ML Foundations 6 guides
Machine learning theory, deep learning architectures, NLP fundamentals, AI ethics and the 2026 skills roadmap — the ground floor before you touch an API.
Machine Learning Basics: Supervised, Unsupervised and Reinforcement Learning Explained
Deep Learning Guide: CNNs, RNNs, Transformers and Attention Mechanisms
NLP Tutorial: Tokenisation, Embeddings, BERT and Modern Language Models
AI Ethics: Bias, Fairness, Explainability and Responsible AI Principles
AI Skills Roadmap 2026: What to Learn, in What Order, to Get Hired
10 AI Skills Every Developer Must Have in 2025–2026
LLMs & Prompt Engineering 7 guides
Prompt engineering techniques, OpenAI and Claude APIs, function calling, embeddings and fine-tuning LLMs with LoRA — use models like a power user.
Prompt Engineering Guide: Zero-Shot, Few-Shot, Chain-of-Thought and Advanced Techniques
Practical Prompt Engineering: Templates, Variables and Production Patterns
OpenAI API Guide: Chat, Completions, Vision and Assistants API
Claude API Guide: Messages, Tool Use and Extended Thinking with Anthropic
LLM Function Calling and Tool Use: Building Real-World AI Actions
AI Embeddings Guide: Semantic Search, Similarity and Vector Representations
LLM Fine-Tuning with LoRA and QLoRA: Adapt Any Model to Your Domain
AI Agents & Frameworks 7 guides
LangChain, LangGraph, AutoGen, LlamaIndex, CrewAI — build single-agent and multi-agent systems that actually work in production.
AI Agent Frameworks Compared: LangChain, LangGraph, AutoGen, CrewAI and LlamaIndex
LangGraph: Build Stateful AI Agent Workflows with Cycles and Branching
AutoGen Multi-Agent: Build Conversations Between AI Agents
LlamaIndex Document QA: Index Any Data Source and Query it with LLMs
AI Agent Memory: Short-Term, Long-Term and Episodic Memory Architectures
LangChain vs CrewAI vs AutoGen vs LlamaIndex: Which Should You Use?
AI System Architecture: Patterns for Scalable, Reliable LLM Applications
Multimodal & Local AI 6 guides
Stable Diffusion, Whisper, multimodal vision models, Ollama for local LLMs and HuggingFace — run AI on your own hardware.
Ollama: Run Llama 3, Mistral and Phi-3 Locally — Complete Setup Guide
Multimodal AI Vision Guide: GPT-4o, Claude Vision and Gemini Image Analysis
Stable Diffusion Guide: Prompts, ControlNet, LoRA and ComfyUI Workflows
Whisper Speech Recognition: Transcribe, Translate and Diarise Audio
HuggingFace Guide: Transformers, Datasets, PEFT and Inference Endpoints
Spring Boot + Angular + AI: Build an Image Description App End to End
Production AI 7 guides
RAG pipelines, vector databases, MLOps, AI security, guardrails, testing and deployment — ship AI that doesn't break in production.
RAG Complete Guide: Retrieval-Augmented Generation from Chunking to Production
Vector Databases Compared: Pinecone, Weaviate, Qdrant, Milvus and pgvector
MLOps Guide: Model Versioning, CI/CD for ML and Production Monitoring
AI Security: Prompt Injection, Data Poisoning and LLM Attack Vectors
AI Guardrails and Safety: Input Validation, Output Filtering and Content Moderation
AI Testing: Evaluating LLM Outputs, Regression Testing and Evals Frameworks
AI Deployment: Containerising Models, Serving at Scale and Cost Optimisation
📬 Free AI Engineering Newsletter
LLM updates, new agent patterns, RAG tips — free every week, zero spam.