Markus Clauss

AI & Data Science Lead · energy sector · since 2026

Dr. Markus Clauss (Abdullah Isa)

I lead AI and data science work in the energy sector, and I build software with AI coding agents: the written spec is the source of truth, the agent writes the code.

Dhahran, Kingdom of Saudi Arabia

See the projects Sira Labs GitHub
  • 21 yearsprofessional experience since 2005
  • 13 yearsdata science, ML and AI since 2013
  • Dr. rer. pol.economist, tax-benefit microsimulation and CGE modelling
  • 3 countriesGermany, Switzerland, now at home in Saudi Arabia

How I work

The documents are the source of truth. The agent writes the code.

Most of what I build today, I build with AI coding agents. Not by asking for snippets, but by writing the system down first and letting the agent implement it, one spec at a time.

Before a line of code exists, the repository holds the documents that define the system:

  • vision
  • architecture
  • ADRs
  • threat model
  • acceptance tests

The vision says why the thing exists. The architecture says how it is shaped. Each architecture decision record keeps a choice and its trade-offs. The threat model says what must never happen. The acceptance tests say what done means. The code is derived from these, and when the agent cannot implement a spec cleanly, the spec is what gets fixed.

I do this for the joy of it, and for real. The same discipline carries into my work with LLM systems on air-gapped GPU infrastructure: evaluation before rollout, governance written down, nothing that phones home.

  1. Write the spec

    Vision, architecture, ADRs, threat model and acceptance tests, in the repo next to the code.

  2. Hand it to the agent

    Claude Code implements one spec at a time. I read the diff the way I would read a colleague's.

  3. Run it for real

    Previews run on our own servers; Thawr's release candidates run on a VPS, a Mac and a phone. The acceptance tests decide, not the demo.

  4. Fold it back

    What the running system teaches goes into the documents first. The spec changes before the code does.

Why the names come from the Sira

The Sira Labs projects take their names from moments in the Sira, the life of the Prophet Muhammad ﷺ. Each name is chosen because that moment explains what the software is for. Thawr is the cave that gave shelter during the Hijra, so Thawr is a network that shelters. Tabayyun is the command to verify a report before acting on it, so Tabayyun verifies data. The names are meaning, not decoration.

I am at home in the Kingdom of Saudi Arabia now, and I am learning Arabic. Suffa exists because of that.

Projects

Sira Labs: software you own, built in the open

My open-source work now lives at Sira Labs. Seven self-hostable projects in three tracks, each written from specs and decision records before any code, built with AI coding agents, and named for a moment of the Sīra that says what it is for.

siralabs.org Sira Labs on GitHub

Learning

Learn together: with your teacher, your class and your own sources.

Preview

Suffa الصُّفَّة

Offline-first Arabic learning for Modern Standard Arabic, with your teacher, your class and an AI tutor around one curriculum.

The platform in the Prophet's ﷺ mosque where people lived and learned.

  • PWA
  • offline-first
  • AI tutor
Open Suffa GitHub

Preview

Arqam أرقم

One connected journey to becoming an AI-native AI engineer, data scientist or AI researcher, built from openly licensed material.

Dār al-Arqam, the house where the first Muslims learned together.

  • curriculum
  • AI engineering
  • learning ledger
Open Arqam About Arqam

Early build

ʿArḍa العَرْضة

Tajwīd learned the way it was always taught: the rule, the sound and your teacher on the same āya. You recite, your sheikh marks the word and answers with his voice. Suffa's sister, offline-first.

Each Ramaḍān Jibrīl reviewed the Qurʾān with the Prophet ﷺ; the student recites, the teacher corrects.

  • tajwīd
  • PWA
  • offline-first
Open ʿArḍa GitHub

Data

Verify data before anyone acts on it, and explain what was found.

Preview

Tabayyun تبيّن

Verifies industrial time series before anyone acts on them: a catalogue of statistical and domain checks, a score per series and an explanation for every finding. Energy first: PV, wind, grid, metering and storage.

To verify a report before acting on it.

  • Rust
  • Python
  • time series
Open Tabayyun GitHub

Preview

Sahifa صحيفة

Assesses whole data stores: profiles every table, scores six quality dimensions mapped to ISO/IEC 25012 with how sure each score is, and explains every finding. It never writes to the data it assesses.

The charter of Medina, which set down in writing what each party could expect of the others.

  • data quality
  • data contracts
  • ISO/IEC 25012
Open Sahifa About Sahifa GitHub

Security

Protect what is yours, and test it the way an attacker would.

Release candidate

Thawr ثور

A self-hosted WireGuard mesh VPN and zero-trust network in one Go binary. Default-deny policy in git, NAT traversal with a built-in relay, phones via QR code. No cloud, and it keeps working offline.

The cave of the Hijra: hidden, protected, reachable only by those who belong.

  • Go
  • WireGuard
  • ZTNA
About Thawr GitHub

Design

Khandaq الخندق

A command post for authorised AI red teaming: the maintained open-source tools under one scope, one tamper-evident chain of evidence, and reports mapped to MITRE ATLAS and the OWASP LLM and Agentic Top 10.

The trench dug around Medina on Salmān al-Fārisī's counsel: attacker thinking in the service of defence.

  • AI red teaming
  • MITRE ATLAS
  • OWASP
Open Khandaq About Khandaq GitHub

Earlier work

  • news-recap-app: agents gather the day's news and turn it into a short video. Second place, Encode Club / SwarmZero AI and Video Hackathon, December 2024.
  • cache-implementation-challenge: Claude, Qwen and GLM-4.5 write the same Rust cache from one specification, benchmarked side by side.
  • apertus-transparency-guide: a transparency dashboard for Apertus, Switzerland's open 8B language model.
  • gradio-medical-image-analyzer: a Gradio component for veterinary medical image analysis with DICOM support.

Background

Economist by training, engineer by practice

Career

  1. AI & Data Science Lead, Dhahran

    Leading AI and data science work in the energy sector: LLM systems and agents on air-gapped GPU infrastructure, evaluation and governance.

  2. Senior Data Scientist, University of Zurich (DIRU)

    Medical imaging AI and computer vision.

  3. Data Scientist / Data Engineer, Volkswagen / Autovision

    Advanced analytics, big data and cloud platforms.

  4. Data Scientist / Data Engineer, Sky Deutschland

    First years in data science and machine learning on production data.

  5. Software Developer, DATEV

    Professional software development.

  6. Researcher, ZEW Mannheim

    Labour markets and social security. Tax-benefit microsimulation, peer-reviewed publications.

Education

  1. Dr. rer. pol., University of Duisburg-Essen

    Tax-benefit microsimulation combined with computable general equilibrium modelling.

  2. Diplom-Volkswirt, University of Regensburg

    Econometrics.

Expertise

AI agents & LLM systems

Multi-agent systems, RAG, tool use, LLMOps, evaluation and governance, air-gapped GPU infrastructure.

ML & deep learning

PyTorch, TensorFlow, scikit-learn, XGBoost. Computer vision, NLP, forecasting.

Data & platform engineering

PySpark, Databricks, Delta Lake, Snowflake, dbt, Kubernetes.

Cloud & operations

AWS, Azure, GCP. Docker, Terraform, MLOps, CI/CD.

Languages

Python, R, SQL, Rust, Go, TypeScript.

Awards

  • Winner, Cudis-RADAR AI Hackathon (October). Shell AI team: a computer-vision ring size fitter built on HandMesh.
  • Second place, Encode Club / SwarmZero AI and Video Hackathon (December), with AI News Recap.
  • ZEW Qualification Award.

Where I come from

German national. I lived and worked in Germany and Switzerland and am now at home in the Kingdom of Saudi Arabia.

Publications

Peer-reviewed articles

  1. Franz, W., Gürtzgen, N., Schubert, S., Clauss, M. (2012). Assessing the Employment Effects of the German Welfare Reform: An Integrated CGE-Microsimulation Approach. Applied Economics, 44(19). doi:10.1080/00036846.2011.564149
  2. Clauss, M., Schnabel, R. (2008). Distributional and Behavioural Effects of the German Labour Market Reform. Journal for Labour Market Research (Zeitschrift für ArbeitsmarktForschung), 41(4). Full text (IAB)

Working papers and reports

  • Horstschräer, J., Clauss, M., Schnabel, R. (2010). An Unconditional Basic Income in the Family Context: Labor Supply and Distributional Effects. ZEW Discussion Paper 10-091.
  • Clauss, M., Schubert, S. (2009). The ZEW Combined Microsimulation-CGE Model: Innovative Tool for Applied Policy Analysis. ZEW Discussion Paper 09-062.
  • Clauss, M., Schnabel, R. (2008). Distributional and Behavioural Effects of the German Labour Market Reform. ZEW Discussion Paper 08-006.
  • Franz, W., Gürtzgen, N., Schubert, S., Clauss, M. (2007). Reformen im Niedriglohnsektor: eine integrierte CGE-Mikrosimulationsstudie der Arbeitsangebots- und Beschäftigungseffekte. ZEW Discussion Paper 07-085.
  • Arntz, M., Clauss, M., Kraus, M., Schnabel, R., Spermann, A., Wiemers, J. (2007). Arbeitsangebotseffekte und Verteilungswirkungen der Hartz-IV-Reform. IAB-Forschungsbericht 10/2007.
  • Contribution to ZEW Wachstums- und Konjunkturanalysen, 2006.

RePEc author page: link to be added

Contact

Get in touch

Interested in AI agents in regulated or air-gapped environments, spec-driven development, or Sira Labs? Write to me.