Expertise
I build the tooling that lets AI agents work inside real codebases, ticket systems and CI – and tests, static analysis and human review still decide what ships.
Open for new projects
Agent skills that reproduce a production bug from synced data, prove the root cause, create the Jira ticket, fix it with unit and Playwright tests and open the pull request.
LLM features wired into existing products: embeddings and vector search, tool calling and structured outputs – with evals and guardrails instead of black boxes.
This site talks to AI agents: WebMCP tools in the browser, llms.txt and every page as Markdown – generated from the same build as the HTML.
Real projects, real numbers – the full list is on the references page.
Messerle Shop
Agent skills that take a bug from report to pull request: reproduce it from synced data, prove the root cause, create the Jira ticket, fix it with unit + Playwright E2E tests and pass the PHPUnit/PHPStan gate.
balazscsorba.com
This site talks to AI agents: WebMCP tools in the browser, llms.txt and llms-full.txt, and every page as Markdown via content negotiation – all generated from the same build.
Claude in OpenCode: the Claude Agent provider, API keys and the other routes
Claude Code Review is generally available: how the multi-agent review works and costs
Claude pricing explained: Free, Pro, Max, Team and the API, and how usage limits work
Claude skills: how to write a SKILL.md that loads at the right moment
Claude Haiku 5.5: pricing, effort levels and the jobs it takes over from Sonnet
DeepSeek V4.1 Flash 1017: 890 bytes of KV cache per token, and what that buys an agentThe Model Context Protocol (MCP) is an open standard that lets AI assistants and coding agents use tools and data from other systems. An MCP server wraps a system – Jira, for example – in well-described tools, so an agent can search issues or log test runs without custom glue code.
Yes, if the guardrails are real. In my pipelines unit and end-to-end tests, static analysis and CI gates decide what ships – and every change still goes through human review.
Claude Code and agent skills, OpenCode and Codex day to day, and the Anthropic and OpenAI APIs for LLM features inside products.
In Voitsberg, west of Graz in Styria, Austria. Remote across Europe and the UK, or hybrid in Styria.
Open for new projects. The quickest way to reach me is e-mail or LinkedIn.
English and Hungarian. Project communication, tickets, documentation and code are in English – I don’t work in German.
Tell me about your project or role – I’d love to hear from you.
