Knowledge base
Practical resources and guides on AI tools, technology, and software development.
Obsidian as a knowledge base with which the agent works
The Obsidian repository is a regular folder with markdown files, so it can be read equally by a human, a script, and an AI agent. What to put in frontmatter, how to give the agent access, how to prevent him from littering the database with duplicates, and how to check that the knowledge is there at all.
Data check before loading: staging and dry run
Import either falls in the middle, or is “successful” and a week later is found in prices and reference books. Analysis of mechanics: file profiling, rules as code, intermediate circuit, run without recording, batch_id for rollback.
Claude Code limits: how the limits work and what to do when you get stuck
Three different limiters that confuse with each other what exactly inflates the consumption in a session and which commands show the real picture.
Git for non-developers: the minimum that is enough
Twelve commands cover almost everything that a person without development needs: history of edits, rollback, branch for an option, viewing what the agent has changed. Analysis of the mechanics - index, commit, branch, conflict - and an honest list of what git is not good for.
GitHub Copilot in real work
Addition to the editor, chat with the repository context, agent mode and an agent that opens a draft pull request. Which of this saves time, and which creates work for the reviewer.
II-agent for 1C: how to connect the model with the accounting system
Three layers of binding: how 1C sends data out, how named operations for the model are made from it, and why recording always goes through an extension with an idempotency key.
OpenAI API: what the request consists of
Analysis of the request body and response fields: what determines the form of the result, where money on tokens leaks, why the response breaks off mid-sentence, and when repeating a request makes sense and when not.
Creation of AI agents: constructor, framework or own cycle
Three layers of agent assembly and what each gives and takes away: a visual designer, a code framework, a custom loop on the SDK. Selection criteria, assembly routes for each layer and rules for transition between them.
Claude Code in Russia: what prevents access and payment
Three separate barriers - service region, geocontrol and payment - how they differ, what ends in account blocking and which paths remain working.
AI agents for business: which tasks are closed and which are not
Task suitability filter of five attributes, application map by department with an honest list of what agents do not pull, economics of a unit of work and a pilot’s route with metrics by which decisions are made.
Local models via Ollama
Demon on 11434, models in GGUF, Modelfile, quantization and num_ctx: how to run a model on your hardware, how much memory it will eat, and in which tasks local launch honestly wins over the cloud.
MCP: protocol for connecting tools to the model
One contract instead of an adapter for each client-system pair: the server describes tools, resources and prompts, any supporting client picks them up. Analysis of handshakes, transports, risks and debugging.