Business guide · Updated June 2026

What AI can't do

The most useful page nobody writes. Knowing the genuine limits is what separates a business that gets value from AI from one that gets burned by it.

The core limit: a language model predicts plausible text, not verified truth. Everything below flows from that. None of it means AI is useless — it means you design around the gaps with retrieval, tools and human review.

The seven real limits

1. It can't reliably cite real sources without RAG

Ask a bare model for references and it will often invent plausible-looking ones. Real citations require retrieval-augmented generation — connecting the model to an actual document store. Without that, treat every citation as unverified.

2. It can't do reliable maths

Models approximate arithmetic from patterns, not calculation. For anything beyond trivial sums, they need a calculator or code tool wired in. Never trust an unaided model with figures that matter.

3. It can't make legal or medical decisions safely

Hallucination rates in legal queries run 58–88% and in medical summaries 43–64% without mitigation (see the Truth Score). AI can draft and summarise in these fields, but a qualified human must make and own the decision.

4. It can't replace domain expertise

AI lacks accountability and real-world judgment. It is a powerful assistant to an expert, not a substitute for one. The expert knows when the confident answer is wrong — the model often doesn't.

5. It can't remember between sessions

By default a model only sees the current context window. Persistent memory needs an explicit memory architecture built around it. Without one, every conversation starts from zero.

6. It can't hold a consistent persona without a system prompt

Tone and behaviour drift unless you anchor them with a system prompt. For brand-consistent customer-facing use, the system prompt is mandatory, not optional — see AI personality.

7. It can't know that it's right

A model has no internal sense of certainty. It can state a fabrication with exactly the same confidence as a fact. This is the "confident liar" problem — and the reason a human review step is non-negotiable for anything important.

What this means for deployment

The limitThe workaround
Invents sourcesAdd RAG against your verified documents
Unreliable mathsWire in a calculator/code tool
Unsafe for high-stakes decisionsHuman makes and owns the decision
No memoryAdd a memory layer if continuity matters
Persona driftAnchor with a system prompt
Can't self-verifyHuman review on anything that matters

What changed in June 2026

Building responsibly? Pair this with the starter guide, governance basics and the data privacy checklist.