8 posts
Harvey raised $760M. Blue J raised $133M. Neither can answer a question about erfbelasting in Brussels. Here's why that creates an opportunity.
Chat interfaces feel modern but produce ephemeral, indefensible output. Professional tax research needs structured answers you can file, reproduce, and defend.
These aren't trick questions. They're routine queries any tax professional faces. But they expose five architectural blind spots that no general-purpose AI can fix with a better prompt.
AI skepticism in tax is rational. Most tools deserve it. But rejecting the entire category because ChatGPT hallucinated a tax rate is like refusing calculators because the first ones jammed.
Fine-tuning memorizes yesterday's law. RAG looks up today's. For Belgian tax professionals, this architecture choice determines whether your AI tool is current or confidently outdated.
Most firms start by asking 'how accurate is it?' That's question 10 on this list. Here are the nine questions you should ask first — and why they matter more for professional tax work.
How retrieval-augmented generation works, why basic RAG still hallucinates, and what a search-RAG fusion architecture adds for tax professionals.
Why language models invent legal citations, what makes Belgian tax especially vulnerable, and three defenses that actually work.