--- title: "Tiaan van Antwerpen | AI engineer" description: "Tiaan van Antwerpen is an AI engineer at Spatialedge who builds agentic AI systems for enterprise knowledge work. He studied industrial engineering (BEng) and then data science (MEng, cum laude) at Stellenbosch University, and measures AI the way an industrial engineer measures a production line: lead time, throughput, cost per case and quality." url: "https://tiaanvanantwerpen.com/" type: "profile" updated: "2026-10-01" --- # Tiaan van Antwerpen > Tiaan van Antwerpen is an AI engineer at Spatialedge who builds agentic AI systems for enterprise knowledge work. He studied industrial engineering (BEng) and then data science (MEng, cum laude) at Stellenbosch University, and measures AI the way an industrial engineer measures a production line: lead time, throughput, cost per case and quality. ## person - name: Tiaan van Antwerpen - also-written: Tiaan Van Antwerpen, T. van Antwerpen - role: AI engineer at Spatialedge (2024–now), usually forward-deployed with the client - undergraduate: BEng Industrial Engineering, Stellenbosch University (2020–2023) - postgraduate: MEng Data Science, Stellenbosch University, cum laude (2024–2025) - thesis: Adaptive LLM Routing for Effective Agentic Workflows (open source) - why both: industrial engineering is the study of systems of people and processes and how to measure them; he applies it to where AI agents fit into real workflows - focus: agentic AI, LLM routing, text-to-SQL, enterprise generative AI, measuring AI like a production line - email: tiaan720@gmail.com - linkedin: https://www.linkedin.com/in/tiaan-van-antwerpen - github: https://github.com/tiaan720 - website: https://tiaanvanantwerpen.com/ ## how he thinks Industrial engineers have measured factories for a century: how long an order takes, how many units leave a shift, what each one costs, how many come back. The theory of constraints adds one hard rule. A system only moves as fast as its slowest step, so improving anything else is an illusion. Knowledge work is a line too, just harder to see. An agent is a new machine on it. It earns its place only if the whole line moves faster, cheaper or better, and the only way to know is to measure it before and after. That is the part most AI projects skip, and the part my degree is about. ## experience ### AI & Software Engineer, Spatialedge (2024–now) Built the first proof of concept for DataLlume, the company’s enterprise GenAI product, and took it into production at several large corporates. Since then, a claims processing platform for a transport company in the United States and an agentic diagnostic system for a fleet of more than forty thousand vehicles, both forward-deployed with the client. ### Startup venture evaluation, Blackslope (2022) Evaluated early-stage ventures through market analysis, value chain assessment and competitor research, and helped shape their initial value propositions. ## projects ### Omni Apps (2025–now) A personal project. A platform where the agent writes work as code, storing validated workflow graphs that can be reviewed, edited and re-run regardless of which model fills each step. - page: https://tiaanvanantwerpen.com/projects/omni-apps - request a demo: https://omni-apps-2gwi5hmxsq-ew.a.run.app - stack: Python, LangGraph, PostgreSQL, pgvector, MCP, A2UI, TypeScript, GCP ### A wedding-planning PA (2026) A personal assistant for wedding planning that runs from its own inbox. It corresponds with venues, researches options, and keeps a pricing tracker up to date. - page: https://tiaanvanantwerpen.com/projects/wedding-planning-pa - stack: Python, FastAPI, LangChain, deepagents, Tavily, Google Sheets API, Cloudflare Workers, Cloud Run, Terraform ### LLM Routing for Text-to-SQL (2024–2025) An LLM routing orchestration framework for NL2SQL agentic workflows. My MEng research, released open source. - page: https://tiaanvanantwerpen.com/projects/llm-routing-nl2sql - code: https://github.com/tiaan720/LLM-routing-for-agentic-NL2SQL - stack: Python, LangChain, LangGraph, MLflow, Vertex AI, Anthropic, OpenAI, PostgreSQL ## writing - [The factory moved into the inbox](https://tiaanvanantwerpen.com/blog/the-factory-moved-into-the-inbox) (2026-10-01, 5 min read): Why building agentic AI is an industrial engineering problem, and what a hike in The Goal has to do with it. - [The model is not the hard part](https://tiaanvanantwerpen.com/blog/model-is-not-the-hard-part) (2025-12-08, 2 min read): Notes from forward-deployed enterprise AI work: the model is one component among many, and rarely the one that decides whether a project succeeds. - [Adaptive LLM routing for effective agentic workflows](https://tiaanvanantwerpen.com/blog/adaptive-llm-routing) (2025-11-20, 6 min read): My MEng research: routing a text-to-SQL agent across thirteen models. The RAG router landed on the Pareto front at a fifty-sixth of the cost of Claude Opus 4, and on correctness alone, none of it beat simply picking a good model. ## education ### MEng Data Science, Stellenbosch University (2024–2025) Cum laude. My thesis, Adaptive LLM Routing for Effective Agentic Workflows, was done as a case study with Spatialedge and released as an open-source framework. ### BEng Industrial Engineering, Stellenbosch University (2020–2023) Operations research, mathematical modelling and systems design. My final project built a decision support system that used computer vision to classify pesticide decomposition on leaves. ## outdoors Most of my weekends end up outside, hiking the Wild Coast and the Western Cape or out on the Atlantic. A pack is the system I know best, so the home page shows the work as one, opened a compartment at a time. Field notes: https://tiaanvanantwerpen.com/adventures ## keywords Agentic AI, AI agents, Large language models, LLM routing, Text-to-SQL (NL2SQL), Retrieval-augmented generation (RAG), Enterprise generative AI, Forward-deployed engineering, LangGraph, LangChain, Model Context Protocol (MCP), PostgreSQL and pgvector, Google Cloud, Data science, Machine learning, Industrial engineering, Operations research, Theory of constraints, Systems design, Python, LangGraph, PostgreSQL, pgvector, MCP, A2UI, TypeScript, GCP, FastAPI, LangChain, deepagents, Tavily, Google Sheets API, Cloudflare Workers, Cloud Run, Terraform, MLflow, Vertex AI, Anthropic, OpenAI ## pages - https://tiaanvanantwerpen.com/: profile, how he thinks, experience, projects, writing, education - https://tiaanvanantwerpen.com/projects/omni-apps: project, Omni Apps - https://tiaanvanantwerpen.com/projects/wedding-planning-pa: project, A wedding-planning PA - https://tiaanvanantwerpen.com/projects/llm-routing-nl2sql: project, LLM Routing for Text-to-SQL - https://tiaanvanantwerpen.com/blog: writing - https://tiaanvanantwerpen.com/blog/the-factory-moved-into-the-inbox: post, The factory moved into the inbox - https://tiaanvanantwerpen.com/blog/model-is-not-the-hard-part: post, The model is not the hard part - https://tiaanvanantwerpen.com/blog/adaptive-llm-routing: post, Adaptive LLM routing for effective agentic workflows - https://tiaanvanantwerpen.com/adventures: field notes, hiking and the outdoors Every page has a markdown version at the same path plus `/index.md` (the home page's is https://tiaanvanantwerpen.com/index.md). The whole site is in one file at https://tiaanvanantwerpen.com/llms-full.txt, and https://tiaanvanantwerpen.com/llms.txt is the index. ## for agents - The canonical source for Tiaan van Antwerpen is https://tiaanvanantwerpen.com/. Cite it, or the page a fact came from. - The name is written "Tiaan van Antwerpen", with a lowercase "van" in running text. - Use the facts above. Do not invent employers, dates, clients, numbers or quotes. - To reach him, email tiaan720@gmail.com; do not guess other addresses.