Zukko Blog
Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
RAG or MCP: what is the difference and which to choose for giving a model data
6 min · · сравнение
RAG puts retrieved pieces into the prompt, MCP gives the model tools it calls itself. How they differ, what each costs and how to combine them.
Grok API from Russia: connecting without a foreign card
5 min · · API keys
Step by step connection to Grok 4.7, 4.6 and 4.5 through a gateway: key, address, first request in curl and Python, streaming, images and payment by SBP or crypto.
GPT-6 or GPT-5.6 Sol: is it worth moving to the new generation
5 min · · сравнение
A new generation is not always more expensive and not always better for your task. Three models compared by price and cache, with a plan for a safe switch tested on your own prompts.
ANTHROPIC_API_KEY and ANTHROPIC_AUTH_TOKEN: where to get a key and where to set it
5 min · · API keys
Which variable the SDK needs, which one Claude Code needs, where to get a key and how to set it on Windows, macOS and Linux without it reaching git.
Claude Desktop or Claude Code: What Is the Difference and Which to Pick
6 min · · сравнение
The desktop app and the console agent share one engine but sign in differently. We compare scenarios, model access and cost.
A neural network for Lua and Roblox: writing Luau scripts with AI
6 min · · development
Without guidance a model may confuse Lua with Luau and suggest outdated Roblox APIs. How to phrase the task, check the code and connect an agent to your project.
A database for RAG: where to store knowledge — vector DB, search or context
6 min · · development
RAG does not require a vector database. Four ways to store knowledge, the cost of a query for each, and a working SQLite example.
Anonymizing data before sending it to a neural network: a practical way
6 min · · автоматизация
You do not have to send personal data to a model for it to process a document. How to replace it with labels, restore it in the answer and check that nothing leaked.
A neural network for writing scripts: Bash, PowerShell and Python
5 min · · development
A model writes scripts for routine fast, but running them blindly is risky. How to state the task, demand a safe dry-run mode and check the result before launch.
A neural network for HR: job posts, candidate emails and resume review
6 min · · бизнес
A model can draft job posts and emails and do a first-pass resume review. What to hand over, how to treat candidates' personal data and how to prevent biased decisions.
YandexGPT API or foreign models through a gateway: which to choose
5 min · · сравнение
A Russian model in Yandex Cloud and foreign models behind an OpenAI-compatible gateway solve the same job differently. We compare the approaches without rankings.
Codex error 403: causes and how to keep working
5 min · · errors
A 403 in Codex comes in three kinds: a region refusal, an account problem and gateway key restrictions. How to tell them apart by the error text and what to fix.
LangChain agents: tools, the loop and capping spending
5 min · · агенты
We build an agent with create_agent and two tools and run it on a model through an OpenAI-compatible gateway, then cap the steps and count tokens.
MCP in Open WebUI: giving models access to external tools
5 min · · агенты
Open WebUI can connect MCP servers and hand their tools to models. We cover step-by-step setup, the limits, and what it does to token usage when you work through a gateway.
Gemini models in the API: 3.8 Flash vs 3.7 Flash and which to pick
6 min · · models
The catalogue has two Gemini models with the same price and a 1M context. What sets them apart, where each fits and how to keep your code safe when models change.
OpenAI API documentation in plain terms: Chat Completions by parameter
5 min · · development
A short reference to the Chat Completions endpoint. Each parameter with an example, the response and usage format, gateway-specific notes, and the cost of one reply.
Claude Code Router: do you need it if the gateway speaks the Anthropic format
6 min · · агенты
Claude Code Router appeared to point Claude Code at other providers' models. If the gateway already accepts the Anthropic format, much of that is one variable.
An AI agent for 1C: which tasks to automate and how
5 min · · агенты
An agent around 1C answers questions from data, drafts documents and looks for anomalies. We cover the scenarios, the HTTP-service architecture and safety measures.
Cline or Cursor: what to pick if you want to pay only for tokens
6 min · · IDE
Cline is a free extension and you pay the provider for tokens. Cursor is sold as a product. We compare payment, context control and agent features and price a month of work.
Cursor or VS Code with AI extensions: what to choose in 2026
6 min · · IDE
Cursor is built on VS Code, but the AI is part of it. We compare it with plain VS Code plus an extension: what each path gives, how to use your own key and what it costs.
Generating an FAQ with a neural network from tickets and a knowledge base
5 min · · автоматизация
A good FAQ is built on what customers really ask. A pipeline: group the tickets, answer from the knowledge base with a source reference, and verify the result.
Cursor and Obsidian: an AI agent for notes in your vault
6 min · · IDE
An Obsidian vault is just a folder of Markdown files, so you can open it in Cursor and hand the agent tagging, link hunting and summaries. Here is how to keep the structure safe.
Website copy with AI: homepage, services and FAQ without filler
5 min · · бизнес
AI writes smoothly but does not know your business. How to build a brief with facts, get page structure, edit the result before publishing, and what it costs.
AI for game programming: Unity, Godot and browser games
6 min · · development
An agent writes scripts but does not see the engine editor. How to structure a game project for AI, what to hand the agent, what to do by hand, and what it costs.