In-depth guides.
Practical, step-by-step guides that go beyond a single term — system prompt cookbook, MCP server catalog, token-reduction techniques, model selection and more.
-
🧭
MCP, A2A, AP2 and Friends: A Map of Agent Protocols
A layer-by-layer map of agent protocols: MCP (agent ↔ tools/data), A2A (agent ↔ agent, Agent Cards), and the payment and commerce protocols (AP2, x402, ACP, UCP, Visa Trusted Agent Protocol); who maintains each, current version and status, how they stack in a real shopping flow, the security and consent model with mandates and signed cards, when you need which, and an FAQ.
MCP A2A AP2 -
🏛️
AI Governance for Companies: A Practical Starter Playbook
A workable AI governance setup for small and mid-sized companies starting with LLMs and agents: the October 2026 map of the EU AI Act, GDPR, KVKK, NIST AI RMF and ISO/IEC 42001, an AI inventory template, risk classification, policies, technical controls, a vendor checklist, a RACI table and a 30/60/90-day plan.
Governance EU AI Act Compliance -
🧰
Anatomy of an AI Harness: What Surrounds the Model
The layer around the model in tools like Claude Code, Codex CLI, Cursor and Gemini CLI: agent loop, tools, context management, subagents, skills, hooks, permissions, sandboxing, memory, and a sub-70-line harness you can build yourself.
Agents Claude Code Context Engineering -
🧭
Do you need AI, ML, or just an LLM?
How to decide between AI, classical machine learning, and a large language model for a new feature — a decision flow with real scenarios.
Decision AI ML -
🛠️
Build Your Own MCP Server
Write an MCP server from scratch that adds capabilities to your AI assistant: what changed in the 2026-07-28 spec, a local task manager tested with TypeScript SDK v2 and Python SDK 2.x, testing with the Inspector, wiring it into Claude Desktop and Claude Code, and publishing to the MCP Registry.
MCP Server SDK -
⚡
Claude Skills Guide
Install, explore, and write Claude Code skills — modular instruction packs that change behavior with one slash command.
Claude Code Skills Productivity -
🤖
Coding Agents Compared (October 2026): Claude Code, Codex, Cursor, Copilot and More
Claude Code, OpenAI Codex, Cursor, GitHub Copilot, Google Antigravity, OpenCode and Cline side by side: CLI vs IDE vs cloud agents, pricing models, models, sandboxing and permissions, MCP/skills/hooks support, choosing by scenario, security and cost control.
Coding Agents Claude Code Codex -
🖱️
Computer Use and Browser Agents: How Screen-Reading AI Works and When It's Safe to Use
How computer use agents work: the screenshot → model → mouse/keyboard loop, pixels vs the accessibility tree; the API tools and in-browser agents from Anthropic, OpenAI and Google as of November 2026; choosing between API and GUI automation; what OSWorld and WebArena measure; prompt injection, VM isolation and confirmation gates; where it works well and badly; and a minimal safe setup.
Computer Use Browser Agents OSWorld -
🏷️
EU AI Act Article 50: A Guide to AI Content Labeling, Watermarking and Chatbot Disclosure
The AI Act's transparency obligations as of October 2026: provider vs deployer, the four Article 50 duties and their exceptions, the 2 August and 2 December 2026 dates, fines, how it relates to GPAI rules, technical implementation with C2PA and watermarks, checklists for chatbots, image generation and marketing teams, and notes for Turkish companies selling into the EU.
EU AI Act Transparency Watermarking -
📈
Practical Forecasting Guide
ARIMA, Prophet, LightGBM, or deep learning? A practical guide to choosing the right approach for a forecasting problem.
Forecasting Time Series Practical -
🔎
GEO and llms.txt: What Actually Has Evidence for Visibility in AI Answer Engines?
How ChatGPT search, Perplexity, Google AI Overviews/AI Mode, Claude and Copilot find and cite pages; GEO vs classic SEO; what the GEO paper and newer studies say; the llms.txt spec with a full example; AI crawlers and robots.txt; structured data; content patterns that get cited; measuring AI traffic; and a checklist.
GEO llms.txt AI Search -
🧪
LLM Evals and Observability: Eval Sets from Real Cases, LLM Judges and Tracing with OpenTelemetry
Building an eval set from real cases; code-based checks, LLM-as-a-judge and human review; judge biases (position, verbosity, self-preference) and calibrating a judge against human labels; offline evals in CI and sampled online evals; nondeterminism and regression testing; agent and trajectory evals; tracing with the OpenTelemetry GenAI semantic conventions; what to log per call; a tool overview and a starter checklist.
Evals LLM-as-a-Judge Observability -
🔌
MCP Server Catalog
A categorized list of MCP servers that are maintained as of November 2026: what replaced the archived packages, local (stdio) and remote (Streamable HTTP) setup, Claude Code and Claude Desktop configuration, and safe use.
MCP Tools Catalog -
🖥️
How to Run an LLM Locally (2026): Hardware, Runtimes, Models and Setup
An end-to-end guide to running an LLM on your own computer or server: VRAM math, Apple Silicon vs NVIDIA, choosing between Ollama, llama.cpp, LM Studio, vLLM and MLX, current open-weight models, the OpenAI-compatible API, Open WebUI, secure server setup, performance tuning and troubleshooting.
Local LLM Self-hosting Ollama -
📱
Small Language Models (SLMs): What They Are, Which to Pick, and When to Use Them Instead of an LLM
Why small language models are on everyone's radar in 2026: what SLM actually means, the Gemma 4, Qwen3.5, Ministral 3, Granite 4.2, Phi-4-mini, SmolLM3 and LFM2.5 families, an SLM vs LLM decision table, distillation, quantization, LoRA, on-device runtimes, LLM+SLM routing, and how to evaluate for your own task.
SLM On-Device Edge AI -
⚡
System One Models: Jev, Clef and Laya — What They Do and Where to Use Them
The new class of models that make decisions in a single pass with calibrated probabilities instead of generating text: how they work, how Jev, Clef/Clef-flash and Laya differ, use cases, pairing them with an LLM, running locally, and pitfalls.
System One Jev Clef -
📝
System Prompt Guide
Ten real-world system prompts for different personas, why each is written that way, and how to avoid the most common pitfalls.
System Prompt Prompting Examples -
✂️
Token Reduction Techniques
Practical ways to cut token cost when using LLMs — prompt compression, caching, structured output, smart RAG, and more.
Tokens Cost Optimization
From token cost to GPU sizing — practical answers to the questions you face when shipping AI.