AI Tools & Resources

Practical tools and guides for effective work with AI assistants. Templates, best practices, integrations.

Tools & Guides

Token Counter

Coming soon

Prompt Builder

Coming soon

What is AI and Why Does It Matter?

AI (Artificial Intelligence) is technology that enables computers to perform tasks requiring human intelligence: understanding text, generating code, analyzing data, answering questions.

Modern AI assistants (ChatGPT, Claude, Gemini) are Large Language Models (LLMs) trained on vast amounts of text that can help with a wide range of tasks: from writing code to creating content.

Popular AI

  • ChatGPT (OpenAI)
  • Claude (Anthropic)
  • Gemini (Google)
  • Copilot (GitHub/Microsoft)
  • Cursor (AI IDE)

How AI is Used

Development

  • Writing and refactoring code
  • Code review and bug hunting
  • Test generation
  • Documentation and comments
  • Learning new technologies

Content

  • Writing articles and posts
  • Editing and proofreading
  • Text translation
  • Document summarization
  • Idea generation

Analysis

  • Data and report analysis
  • Market research
  • Information extraction
  • Content categorization
  • Pattern recognition

How to Integrate AI

Web Interfaces

The easiest way to start - use official web apps:

  • chat.openai.com - ChatGPT
  • claude.ai - Claude
  • gemini.google.com - Gemini

IDEs and Editors

Integration directly into development environment:

  • Cursor - AI-first editor based on VS Code
  • GitHub Copilot - plugin for VS Code, JetBrains
  • Codeium - free Copilot alternative

API

For integration into your applications:

  • OpenAI API - GPT-4, GPT-3.5
  • Anthropic API - Claude
  • Google AI API - Gemini

CLI

For terminal work:

  • Claude Code - official CLI from Anthropic
  • aider - AI pair programming in terminal
  • sgpt - ChatGPT in command line

AI Articles View all

AI Coding Agents: A Practical Workflow Guide for Real Projects

How to work effectively with AI coding agents like Claude Code, Cursor, and Windsurf. Covers the agent loop, when to delegate vs direct, context management, multi-step tasks, and the habits that separate productive agent use from expensive frustration.

11 March

MCP (Model Context Protocol) Explained: How AI Agents Connect to the Real World

A practical breakdown of the Model Context Protocol (MCP): what it is, how the client-server architecture works, why it exists, and what it means for AI tool integration. Includes examples, a comparison with function calling, and an honest assessment of the current state.

9 March

Prompt Engineering Patterns That Actually Work - Beyond the Hype

A practical guide to prompt engineering patterns that produce consistent results: structured output, chain-of-thought, few-shot examples, role framing, and constraint-based prompting. No magic tricks - just techniques that hold up across real tasks.

7 March

AGENTS.md Makes Your AI Coding Agent Worse - and Now There's Research to Prove It

ETH Zurich's research on AGENTS.md files confirms what I discovered the hard way: bloated custom instructions make AI coding agents slower, more expensive, and less effective. A breakdown of the paper's findings, why context files backfire, and what actually works.

3 March

Custom Instructions for AI Assistants: How to Write Them Without Wasting Money

A practical guide to writing effective custom instructions for ChatGPT, Claude, and Cursor. Covers what happens inside every prompt, how instructions inflate token costs, prompt caching, and a comparison of bloated vs lean instruction sets with real token counts.

3 March

RAG Document Assistant: Answer Questions from Your Own Docs with Ollama, ChromaDB and Docker

Build a local RAG document assistant that reads .txt files, indexes them with vector embeddings, and answers questions using a local LLM — all without a cloud API. Includes a FastAPI backend, a minimal browser UI, and a full Docker Compose setup.

26 February

Common Questions

It depends on your workflow. GitHub Copilot is best for inline autocomplete inside VS Code/JetBrains. Cursor and Windsurf are full AI-native editors with multi-file editing. Claude Code is a CLI agent for your terminal - ideal for complex refactors and autonomous tasks. OpenAI Codex is a cloud-based agent that runs tasks in a sandboxed environment from ChatGPT - good for parallel background work. Many developers use 2-3 tools together.

Custom instructions tell an AI assistant how to behave across all conversations - your preferred language, coding style, frameworks, and response format. Set them once and skip repeating context. ChatGPT, Claude, Gemini, and Cursor all support them in different formats.

Both are project-level instruction files that give AI context about your codebase. CLAUDE.md is used by Claude Code (Anthropic's CLI), .cursorrules by Cursor editor. They serve the same purpose - persistent project context - but for different tools. Our Custom Instructions builder can generate both formats.

Paste the diff or describe the change. Ask the AI to look for bugs, security issues, performance problems, and style violations. Be specific about what matters - e.g. "focus on SQL injection risks" works better than "review this code". AI catches things humans miss, especially in large PRs.

Claude excels at reasoning, debugging, and following complex instructions. ChatGPT has the broadest plugin ecosystem and web browsing. Gemini handles massive context (up to 1M tokens) - great for large codebases. For day-to-day coding, try all three and pick based on your specific tasks.

A term coined in 2025 for rapid prototyping with AI - you describe what you want in natural language and let the AI generate the code, iterating through conversation rather than writing everything manually. It's effective for MVPs, scripts, and learning new frameworks, but production code still needs human review.

RAG (Retrieval-Augmented Generation) lets an LLM answer questions using your own data - docs, code, databases - instead of relying only on training data. The system retrieves relevant chunks via vector search, then feeds them to the model as context. It's how you build AI chatbots that know your product, internal wikis that actually answer questions, and code assistants that understand your codebase.

n8n is an open-source workflow automation platform (a self-hostable alternative to Zapier/Make). Developers use it to build AI-powered pipelines - e.g. trigger on a GitHub issue, send it to an LLM for analysis, post a summary to Slack. It has native nodes for OpenAI, Anthropic, and vector databases, making it a popular choice for RAG workflows and AI agent orchestration without writing glue code.