Rethinking how we build software in the era of AI
Agents optimise for code that works, and the tests that gate the merge cannot see what happens to the structure. Studies of agent-written code show duplication, coupling and complexity growing while pass rates stay flat. For systems that have to live for years, intent has to be machine-readable, enforced by executable checks, measured on three levels, and reviewed at the level of structure instead of lines.
Spec-Kit artifacts are packages and dependencies: catalogs publish what is available, bundles pin what a project installs, and the repository keeps only project intent and project-owned customization.
Document Analysis & Agentic Assistant
AI-powered letter analysis that helps you understand bureaucratic correspondence from authorities, digitizes documents, and delivers clear action recommendations: fast, secure, and simple.
Visit BriefCheckSpec Kit Workflow Terminal
A terminal cockpit for Spec Kit workflows: own, observe, and review one workflow run, follow execution, and decide what happens next without leaving the terminal.
Agentic Engineering Pipeline
Extends GitHub's Spec-Kit with QA review loops, automatic documentation reconciliation, and issue-to-PR automation. Ships three composable flows — Feature, Bugfix, and Quick — so every change is reviewed against its spec and documented in sync with the code.
Software Engineering Pipeline
Orchestrates a full PM → Architect → Code → Review pipeline across Claude, Codex, and Gemini, injected via tmux, not the API. Reuses your existing subscriptions. No per-token costs.
Software engineering enthusiast with a clear mission: making life easier for developers and producing good-quality software.
After studying computer science, I spent 9 years in consulting before becoming a Domain Architect at a major German bank, supporting their digital transformation.
Currently deep in agentic coding and the toolchain around it: exploring how these tools integrate into software development and reshape the industry.