Mihai Adrian Mateescu - BlogArticles about AI/ML, finance, FinTech, Rust, Julia, and the intersection of technology and accounting.https://me-mateescu.de/en-usSun, 12 Apr 2026 20:36:42 GMTAI-Ready Finance Data: Why Finance AI Projects Fail on Structure, Not on Modelshttps://me-mateescu.de/blog/ai-ready-finance-data-rag-document-ai/https://me-mateescu.de/blog/ai-ready-finance-data-rag-document-ai/In finance, weak retrieval, fragile document automation, and low trust usually start long before model choice. The real bottleneck is structure, metadata, validation, and traceability.Sun, 12 Apr 2026 00:00:00 GMT2026-04-12T00:00:00.000Zfintechfinanceragdocument-aixrechnunggobddata-qualitymetadatachunkingcompliancelineagekontakt@me-mateescu.de (Mihai Adrian Mateescu)Founder Compass: Designing a Privacy-First Entrepreneurial Profiler for DACH Foundershttps://me-mateescu.de/blog/founder-compass-svelte5-cloudflare-workers/https://me-mateescu.de/blog/founder-compass-svelte5-cloudflare-workers/Most founders fail not from lack of ideas, but from a mismatch between their profile and their business model. Here is how I built a tool to address that.Wed, 25 Feb 2026 00:00:00 GMTfintechfounder-toolsdachsveltecloudflare-workersaisse-streamingprompt-engineeringtypescriptkontakt@me-mateescu.de (Mihai Adrian Mateescu)Building a KoSIT-Valid XRechnung Generator That Runs Entirely in the Browserhttps://me-mateescu.de/blog/xrechnung-generator-local-first-en16931/https://me-mateescu.de/blog/xrechnung-generator-local-first-en16931/How I built a local-first, zero-tracking XRechnung 3.0 tool for DACH founders — compliant with EN 16931 and KoSIT v3.0, with no backend, no database, and no vendor lock-in.Sat, 21 Feb 2026 00:00:00 GMTfintechxrechnungen16931astrosveltelocal-firstcompliancedachtypescriptkontakt@me-mateescu.de (Mihai Adrian Mateescu)Beyond the ATS: Automating Job Fit Assessment with LLMs and Structured Outputshttps://me-mateescu.de/blog/job-fit-ai-architecture/https://me-mateescu.de/blog/job-fit-ai-architecture/A technical deep dive into extracting perfectly typed JSON data from unstructured HR text using OpenAI Structured Outputs, Zod, and Astro to flip the script on recruitment.Sun, 15 Feb 2026 00:00:00 GMTai-mlllmopenaiprompt-engineeringtypescriptastrozodstructured-outputsautomationkontakt@me-mateescu.de (Mihai Adrian Mateescu)A Modern Portfolio Architecture: Research Insights on Astro, Tailwind, and TypeScripthttps://me-mateescu.de/blog/portfolio-tech-stack/https://me-mateescu.de/blog/portfolio-tech-stack/A research-focused breakdown of a performant and maintainable portfolio tech stack, exploring modern frontend patterns, performance strategies, and type-safe development workflows.Thu, 13 Nov 2025 00:00:00 GMTpersonalastrotypescripttailwindfrontend-architectureperformanceweb-developmentkontakt@me-mateescu.de (Mihai Adrian Mateescu)Understanding Rust Lifetimes: Concepts, Patterns, and Safe Practiceshttps://me-mateescu.de/blog/rust-lifetimes-guide/https://me-mateescu.de/blog/rust-lifetimes-guide/A research-driven guide to Rust's lifetime system—clear intuition, compiling examples, and safe alternatives when ownership gets tricky.Thu, 13 Nov 2025 00:00:00 GMTai-mlrustlifetimesmemory-safetyownershipbest-practiceskontakt@me-mateescu.de (Mihai Adrian Mateescu)Bridging Finance and AI: A Rigorous Approach to Machine Learning in German Accountinghttps://me-mateescu.de/blog/bridging-finance-ai/https://me-mateescu.de/blog/bridging-finance-ai/An in-depth guide to ML in German accounting — document AI, anomaly detection, forecasting, and GoBD compliance with reproducible, audit-ready examples.Wed, 12 Nov 2025 00:00:00 GMTfintechaccountingmachine-learninggobdxrechnungzugferdifrsanomaly-detectiondocument-aiexplainabilitykontakt@me-mateescu.de (Mihai Adrian Mateescu)Julia Performance Optimization: Concepts, Pitfalls, and Practical Patternshttps://me-mateescu.de/blog/julia-performance-optimization/https://me-mateescu.de/blog/julia-performance-optimization/A research-driven guide to writing fast, safe, and reproducible Julia code—type stability, allocations, dispatch, and disciplined benchmarking.Wed, 12 Nov 2025 00:00:00 GMTai-mljuliaperformancebenchmarkingscientific-computingbest-practiceskontakt@me-mateescu.de (Mihai Adrian Mateescu)Machine Learning in Accounting: Concepts, Pitfalls, and Practical Pathwayshttps://me-mateescu.de/blog/machine-learning-in-accounting/https://me-mateescu.de/blog/machine-learning-in-accounting/A research-driven exploration of how ML can augment accounting — from invoice intelligence to anomaly screening — with governance, explainability, and audit-ready design.Wed, 12 Nov 2025 00:00:00 GMTfintechmachine-learningaccountingfintechexplainabilitycompliancekontakt@me-mateescu.de (Mihai Adrian Mateescu)