Zukko Blog
Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
AI for code analysis: how to understand someone else's project faster
5 min · · development
How to get a map of an unfamiliar codebase in an evening: prompts for modules and entry points, checking answers against file references, and cost with and without cache.
AI for fixing code: how to hand over an error and get a working fix
5 min · · development
Fix quality depends on what you show the model. The data to include about the error, a prompt template, asking for a minimal diff, and verifying with a test.
MCP servers for Codex CLI: config.toml setup step by step
5 min · · development
Codex connects MCP servers through the codex mcp add command or tables in config.toml. Both ways, how to verify, and how many tokens tool descriptions use.
Regular expressions with AI: how to get a working regex and test it
5 min · · development
A model writes regex fast but errs confidently on edge cases. A request with examples, an auto-check loop and protection against hangs.
Analyzing logs with AI: from thousands of lines to a clear cause of failure
4 min · · автоматизация
Do not send gigabytes of logs to a model. Filter, group by templates, ask for hypotheses tied to lines and verify them. Code and price estimate inside.
AI for DevOps: configs, scripts and incident analysis
5 min · · автоматизация
A model drafts configs and reads logs well, but must not hold production rights. Tasks, safe boundaries and a sample script.
LangChain.js: connect to an OpenAI-compatible API in Node.js
4 min · · development
How to point ChatOpenAI from LangChain.js at the Zukko gateway: one baseURL setting, streaming, tool calls and a spend check.
How to connect Qwen to VS Code: Companion, Cline and Continue
5 min · · IDE
Two ways to get Qwen in your editor: the official Companion for Qwen Code, or the Cline, Kilo Code and Continue extensions with an OpenAI-compatible key.
Claude Code in JetBrains: IntelliJ IDEA and PyCharm on Your Own Key
6 min · · IDE
The plugin does not bundle Claude Code. It launches the console agent in the IDE terminal. Install, gateway key, diffs and common failures explained.
Porting code to another language with AI: migration plan and checks
5 min · · development
AI translates code between languages quickly, but it will not preserve behaviour on its own. A module migration plan with reference tests and comparison.
LangChain text splitters: how to cut text into chunks correctly
5 min · · development
How to choose chunk size and overlap in RecursiveCharacterTextSplitter, why you should count in tokens and how to check the count against an exact token number.
LangChain and MCP: connecting MCP tools to a LangGraph agent
5 min · · агенты
MCP servers give an agent ready-made tools, and adapters turn them into LangChain tools. The current approach, running on models through an OpenAI-compatible gateway.
Agentic coding: what it is and how it differs from autocomplete
5 min · · агенты
An agent does not suggest the next line, it runs a task in a loop: read, edit, run, check. How it works, which tools exist and what an hour costs via API.
How to use Claude Code: a working loop on a real task
5 min · · development
One full pass with Claude Code, from writing the task to the commit. How to read the diff, undo edits and keep token spend under control.
LangChain RAG: a working example with a model via a gateway
5 min · · development
We build a simple RAG with LangChain: documents, chunks, vector search and a model answer via a gateway. We count what a question costs and trim wasted tokens.
LangChain Deep Agents: what it is and how to run it on your own model
5 min · · агенты
Deep Agents is a ready-made harness on top of LangChain: files, subagents, context summarization. What is inside, how to run it via a gateway and what it costs.
AI for translating scientific papers: terms, formulas and references
5 min · · автоматизация
Scientific text breaks where ordinary translation goes smoothly: formulas, terms, references. A pipeline with formula protection, a glossary and checks, and what it costs.
LangChain Ollama or a cloud model: one codebase, two models
4 min · · сравнение
ChatOllama runs a model on your machine, ChatOpenAI with a gateway base_url calls a cloud one. We write the code once and switch with environment variables.
The best AI for C# programming: choosing a model and setting up an agent
5 min · · development
We give no ranking of the best model for C#, but we show how to compare options by price and index, set up an agent for .NET and verify the result with builds and tests.
AI for Java code: agent, tests and Spring without extra edits
5 min · · development
In a Java project an agent is valuable while it leaves your architecture and dependencies alone. Rules, build commands, test generation and a cost estimate.
Claude Opus 4.6: what it is and how to move to Opus 5.5 safely
5 min · · models
Opus 4.6, 4.7 and 4.8 are the previous generation, and the catalogue now has Opus 5 and 5.5. A four-step migration plan: model id, your own prompts, cost comparison, rollback.
AI for C++ code: CMake builds, compiler errors and sanitizers
5 min · · development
C++ forgives a model a lot at compile time and punishes it later. How to build a build, test and sanitizer loop for an agent and what it costs on different models.
Claude Code in Russian: replies, comments and commit messages
6 min · · агенты
Claude Code understands Russian but answers in whatever language your instructions set. Where to put the language rule, what not to translate and what it costs in tokens.
AI for SQL: how to write and optimize queries with a model
6 min · · development
Schema, sample data and a query plan in the request to the model, an EXPLAIN check and read-only access. Working Python code and a cost estimate.