AI / ML
MCP and WebMCP: how AI assistants act on websites and shop in online stores
How an AI assistant acts on a website: an MCP server and WebMCP tools with code examples, connecting to ChatGPT, Claude and Gemini, the protocols for AI purchases, and what an online store needs.
GEO: how ChatGPT, Claude and Gemini find and read websites
GEO in practice: how AI assistants find and read a site, which robots to let in, what to set up in robots.txt, Cloudflare and other CDNs, how to prepare text and markup, and how to measure the result.
LLM inference engines: vLLM, llama.cpp, LiteRT-LM and others — speed, hardware, scaling
What to run language models with in late 2026: the engines vLLM, SGLang, TensorRT-LLM, llama.cpp, MLX, LiteRT-LM and ExecuTorch, and programs built on them such as Ollama and LM Studio — what makes the engines fast, what hardware they run on and how they scale, with measurements on a laptop.
Comparison of 41 AI harnesses — from Claude Code to OpenClaw
Coding agents and general-purpose agents compared: Claude Code, Codex, Cursor, Copilot, OpenCode, OpenClaw, Hermes — licenses, models, configuration, sandboxing, benchmarks, training on your code and leaks.
Claude Code — commands, settings, flags
A Claude Code reference: every slash command with its arguments broken down and examples, settings.json keys, permission rules, terminal subcommands, flags and environment variables. Current as of August 2026.
Claude Code — Best Practices
How to organize work with Claude Code: project instructions, rules and skills, a task and bug tracker in the repository, planning before code, subagents, context, permissions and budget.
Claude Code Hooks
A walkthrough of Claude Code hooks: every event, exit codes and JSON decisions, matcher and if, the five handler types, and three working hooks — sound, subscription limits and a work log.
LangChain and LangGraph — agents, graphs and the infrastructure around them
How the LangChain 1.x and LangGraph 1.x stack fits together: models and messages, tools, create_agent and middleware, StateGraph with reducers, checkpointers and store, streaming, human-in-the-loop, LangSmith, Agent Server and the langgraph CLI, plus the 0.x migration.
Prompt engineering techniques for Large Language Models
The effort knob on reasoning models, strict output schemas, agent prompts, delimiters, XML tags and few-shot — how to write prompts for ChatGPT, Claude or Gemini and get predictable output.
DSPy — Automatic Prompt Generation
DSPy 3.4 through a support agent: signatures instead of prompt text, tools, a metric, the MIPROv2 and GEPA optimizers, saving the result, and what changes in DSPy 3.5.
RAG (Retrieval-Augmented Generation), Function / Tools Calling, CAG (Cache-Augmented Generation) for LLM models
RAG, function calling and CAG for local LLMs: how vector search works, with working examples in Kotlin, Dspy, LangChain, LangChain4j and llama.cpp.
Vector databases
How vector databases work: embeddings, HNSW indexing and similarity search, plus a comparison of Milvus, Qdrant and Weaviate with Milvus code.
Offline AI Launcher — launch AI LLM neural networks on smartphone
Offline AI Launcher runs LLMs like Gemma, DeepSeek, Llama and Qwen straight on your Android phone from .gguf files, with no internet or subscription.
LoRA — Fine-Tuning AI LLM Models
Fine-tuning an LLM with LoRA: when it beats RAG and when it does not, how the adapters work, and two complete examples for Gemma 4 E2B on Unsloth and PEFT with export to GGUF.
llama.cpp AI LLM Engine — How It Works
How inference works inside llama.cpp: loading a GGUF model, tokenization, building the compute graph, the KV-cache, and token sampling.
Running LLMs locally on an Android smartphone
What can run a language model right on Android: LiteRT-LM, llama.cpp, MediaPipe, MLC LLM and ONNX Runtime GenAI — which to choose, how to prepare a model, and Kotlin code that stops generation correctly.
Neural networks in simple terms
How an LLM actually works: tokenization, embeddings, transformer attention, quantization, and the samplers that pick each next token.