Thinking & Writing
Notes on building products, AI systems, and shipping software as a solo developer.
Featured insight
Building Anruvo: Why an AI Phone Agent Needs Deterministic Business Logic
A transparent build case study on turning German customer calls into structured, rule-validated operational cases with voice AI, deterministic decision logic, and human handoff.
Read articleMore writing
From AI Prototype to Production: The Architecture Checklist Most Teams Skip
A production-oriented guide to acceptance gates, structured outputs, security boundaries, evaluation, observability, human review, and operational ownership for AI systems.
On-Premise RAG for Manufacturing: Architecture, Hardware, and Cost
An auditable FastAPI, vLLM, and pgvector reference architecture covering security, GPU sizing, evaluation, and realistic project costs for technical documents.
RFQ Automation: How Machine Builders Evaluate 200-Page Specs with On-Premise AI in Minutes
Accelerate technical RFQs and specification documents in B2B sales. How local, GDPR-compliant AI workflows free engineers and protect IP.
Why German Mittelstand Avoids Public-Cloud AI – and How Sovereign AI Saves Document Workflows
How German B2B companies automate manual document processes with local, GDPR-compliant on-premise LLMs—without sending data to the public cloud.
AI Should Explain Engineering Validation, Not Invent It
How separating deterministic logic from LLM reasoning builds trust, manages unknown data states, and mitigates hallucinations in BIM validation.
Page 1 of 3