First the process, then the system
We start with the manual work causing friction today: verifying documents, retyping data, preparing quotes, or identifying risks. Only then do we determine the required architecture.
Jack van der Vall
Founder of Opusmatic & AI Engineer with a hands-on foundation in technical work preparation, building automation, and Applied Data Science & AI.
Background
With a hands-on background in technical work preparation, building automation, and smart technology (including Klip B.V. and Lomans), I understand the operational reality of technical firms from the inside out — from AutoCAD isometric piping drawings and cost calculations to parts lists and ERP workflows.
Combining that domain foundation with Applied Data Science & AI, I developed autonomous data-mining agents at the Erasmus Centre for Data Analytics (ECDA) and engineered an AI platform for automated contract risk analysis.
Through Opusmatic, I combine technical domain expertise with resilient, version-controlled software architecture (Python, PostgreSQL, PydanticAI, and n8n) to replace manual administrative toil with reliable systems.
Architecture you can understand, govern, and scale
We build systems designed to last for years. With clear ownership, visible controls, and integrations tailored to your existing operations.
Robust code over brittle workflows
Critical business logic does not belong in fragile no-code chains. We engineer version-controlled Python and n8n systems with type-safe validation, logging, and explicit error handling.
Human-in-the-loop where it counts
Automation removes repetition, not your team's professional judgment. For financial, legal, or operational risks, decision-makers remain visible in the loop.
Client Testimonials
“Where we previously spent many hours per contract on manual verification, we now do it in a matter of minutes and, more importantly: the platform automatically flags deviations without missing anything.”
Ivo Alblas
Operations Office Manager, Industrial Contractor
“He is reliable, enthusiastic, and motivated. Brings us valuable insights and innovates company processes in seamless collaboration — over the last 1.5 years leveraging AI techniques. Jack is an asset and a great sparring partner.”
Ruud De Groot
Financial Controller, Industrial Contractor
“Jack placed strong emphasis on governance and human-in-the-loop review on critical steps to prevent hallucination risks, working very independently from problem scoping to a working platform. [...] Jack was an asset to our team.”
Jos van Dongen
Director, Erasmus Data Collaboratory | House of AI
Full recommendations can be viewed on LinkedIn.
Practical proof
A selection of production deployments where AI, data engineering, and technical workflows intersect.
Projects
contract-analysis-platform
Production deployment for industrial contractor
Multi-agent system for automated analysis of commercial documents. Flags deviations in delivery terms, payment schedules, and scope creep to mitigate operational and financial risk.
data-mining-platform
Research for ECDA
AI agents automating data mining based on the CRISP-DM framework. From problem formulation and data extraction to model selection and insight generation at scale. Actively used by ECDA.
social-ai-chatbot
Community project for Pauluskerk
AI-driven triage and information chatbot for volunteers in homeless shelter facilities. Built with PydanticAI agents and Supabase pgvector memory.
Open source & research
agentic-archive
Collection of n8n architectures for multi-model orchestration and RAG-to-SQL.
file-to-vector
Streamlit interface for document ingestion into Supabase pgvector databases.
resume-job-matcher
Semantic matching between resumes and job profiles using sentence transformers.
air-quality-prediction
PM2.5 prediction model using Random Forest and PCA on Dutch RIVM station datasets.
Schedule a discovery call
In a 30-minute introductory call, we analyze your workflow bottlenecks and identify the highest ROI automation roadmap for your operations.