The AI Factory
That Never Sleeps

Speaker

Martin Mueller

🇵🇹 → 🇩🇪 Moved back to Germany · February 2026

Freelancer · DevOps · AI agents

• AWS Community Builder — Serverless · 5 years
• Member of
• Board member of

linkedin.com/in/martinmueller88 · martinmueller.dev

LinkedIn

Family · Christmas 2025

Context

Clients + cloud work I manage

Until July 2026

Air Canada

Enterprise AI chatbot · customer service · conversational AI in production

·

Current · Cyquins

HDI Versicherung

Cyber insurance assessments · multi-cloud scans (AWS, Azure, GCP, Microsoft 365) · Prowler Cloud as scan backend

Own project · AWS

HalloCasa

CDK · CodePipeline · prod SSO — real estate platform

Own project · AWS

ai-secure.dev

AgentCore · MCP scans · compliance reports (ISO, SOC 2, NIST)

Own project · AWS

qr-plakat.de

OpenNext · Lambda · CloudFront — hosted landing pages with metadata preview

Freelance

Open for work

AWS · DevOps · AI agents — book 15 min if you need help

Calendly

calendly.com/martinmueller_dev

Honest architecture

AI Factory — cool concept, skeptical for code

• AI Factory — issues in, PRs out, 24/7. Great buzzword · I'm not trusting full autonomy on production code yet
• Telegram — talk to the agent from your phone, anywhere
• Hostinger VPS — OpenClaw in Docker, ~€10/mo, always on. Any other VM — or a serverless setup — works too
• Watches GitHub issues, plans, codes, opens PRs · AWS targets (HalloCasa, ai-secure, qr-plakat)
• Human in the loop — review diff, SSO approve, kill runaway jobs. Non-negotiable when code matters — at least for now

Factory runs overnight · you own the merge. Telegram on the go — or pair deeply in Cursor IDE.

In practice

How I use OpenClaw — Telegram Topics

• Two groups — work vs personal; same OpenClaw gateway, different Telegram allowlists
• Forum topics — one thread per project (HalloCasa, prowler, meetups, travel, car…) so context stays scoped
• Phone-first: ping the agent from Milan, approve AWS SSO, review PR links — without opening the laptop
• Slack mirror on HalloCasa work channel — team sees what the agent does; Telegram stays my cockpit

Overview

Pipeline flow (HalloCasa-style)

Learnings

What actually moved the needle

• CI/CD owns deterministic work — typecheck, lint, deploys, integration tests: not in the agent loop (too slow, too costly). Agent opens PR · GitHub Actions proves it.
• LLM subscriptions — Cursor Pro etc. instead of raw API keys where possible. ~95% of spend is tokens anyway.
• Cheap models are enough — Composer, Grok for implementation; reserve Opus for planning. Good enough, much cheaper.
• OAuth2 / SSO where you can — AWS SSO device-code, Google/GitHub OAuth for APIs; fewer long-lived keys in TOOLS.md and env files.
• Dual track — ship from Telegram (async, mobile) and from Cursor IDE (deep focus). Same repos, same PR workflow.
• Self-update — configure OpenClaw to upgrade itself + skills (gateway, clawhub, npx skills update) so the agent stays current without SSH babysitting.
• Share the agent — give co-founders / colleagues access (Telegram group, Slack channel). Non-technical teammates get the benefit too — and it saves you being the bottleneck.