# Technische Autorenschaft

Alle Wissenshub-Artikel in Technische Autorenschaft.

URL: https://dylanengelbrecht.dev/de/insights/category-authorship.html

- [Warum Mirror für Unity-Multiplayer](https://dylanengelbrecht.dev/de/insights/mirror-multiplayer-unity.html): Mirror is a pragmatic default when Unity teams need a complete networking architecture.
- [Progressive Disclosure beim Lernen: Karten statt Auswendiglernen](https://dylanengelbrecht.dev/de/insights/progressive-disclosure-learning-with-agents.html): Orchestrate agents across a navigable map — learn foundations deeply, index everything else, verify with the environment.
- [Erste Schritte mit Cursor: die Schleife automatisieren](https://dylanengelbrecht.dev/de/insights/getting-started-with-cursor.html): Treat Cursor as an automation surface — rules, tests, MCP, and agents run the boring parts so you keep one thread for judgment.
- [Der AGENTS.md-Standard für KI-Coding-Agenten](https://dylanengelbrecht.dev/de/insights/agents-md-standard.html): One open Markdown file per repo — closest AGENTS.md wins; user prompts override.
- [Wissen für KI-Agenten organisieren](https://dylanengelbrecht.dev/de/insights/organizing-knowledge-for-ai-agents.html): Pair a public site with a private brain — progressive disclosure, lifespans, verification metadata.
- [MCP-Server mit Search und Execute bauen](https://dylanengelbrecht.dev/de/insights/mcp-search-execute-codemode.html): Two MCP tools — search and execute — beat hundreds of per-operation tool definitions.
- [Reinforcement Learning für Tool-Aufrufe in Agentenmodellen](https://dylanengelbrecht.dev/de/insights/rl-tool-calling-composer.html): RL specializes models for the tool loop — Composer is the public case study.
- [Keep the thread: why plan–critique–build pipelines fail modern coding agents](https://dylanengelbrecht.dev/de/insights/single-agent-coding-loops.html): One agent, one thread, small units — verify with tests, not lossy handoffs.