audit-grade-rag
A compliance-grade RAG console. Bone-paper aesthetic, branch-protected mainline, bracketed citation pills auditors can read out loud.
Marius Jauernik · Litzendorf, Bavaria · 2026
Electrical engineer · AI agents · Self-taught fullstack
Dipl.-Ing. electrical engineer (TU Dresden, 2018). Self-employed since 2022 in cloud operations and full-stack development, now building AI agents and automations.
Selected work
Anchors from the 30 public repositories at github.com/mj-deving. Each one is a system that runs.
A compliance-grade RAG console. Bone-paper aesthetic, branch-protected mainline, bracketed citation pills auditors can read out loud.
AI phone agent for medical practices. Appointment booking, emergency detection, call routing. 156 tests, deployed on Fly.io. Python and Vapi.
Self-healing n8n workflow. Learns from failures so the fourth identical error heals at zero LLM tokens. Claude, Slack, n8nac code-first.
Five progressive agent demos from single-agent to multi-agent with plan and reflect loops. Claude Agent SDK, 42 tests, per-run cost numbers.
Security-first OpenClaw deployment. Hardened config, monitoring scripts, and a fifteen-phase guide that explains every decision.
CLI plus MCP server for code-mode. Execute TypeScript code chains in an isolated sandbox. Published on npm as code-mode-tools.
Curated, sanitized export of 21 agent-skill packages for Claude Code and Codex. Gated by an automated publication audit. No secrets, no local paths.
SIEM alert triage with parallel threat intel from VirusTotal, AbuseIPDB, Shodan, MITRE ATT&CK. 86 percent fewer tokens, 3.3x faster, 7 seconds end-to-end.