The most useful answer a RAG system can give is sometimes 'that is not in this document.' However, when asked a question, a model tends to answer anyway, so the honest 'not found' has to be built in, not hoped for. Getting the system to say no, and to be right when it does, is harder than getting it to say yes. This article is a bonus in Enterprise Document Intelligence, a series that builds an enterprise RAG system from four bricks.

It justifies the 'I don't know': a confident wrong answer is a bug, a bare no-answer is almost as bad, and each of the four bricks has one piece of evidence to show. New to the series? Every article in this series sits on our two Towards Data Science author pages, Angela Shi and Kezhan Shi. The public companion-code repo at doc-intel/notebooks-vol1 walks each row in order, then ties them together on the CMO / AI electricity-consumption case.

The series argued that structured output makes 'yes' answers verifiable, by forcing the model to cite its evidence: a quote, a page number, a confidence. The same logic applies to 'no' answers, and the same four bricks contribute, one piece of evidence each. This article walks the four bricks once more, on a question whose right output is no, and shows what each brick has to produce so the no-answer is defensible.

The document it runs on is the World Bank's Commodity Markets Outlook (April 2025 issue; CC BY 3.0 IGO). Ask the corporate chatbot 'How much electricity does AI consume globally?' and it returns 'I cannot find an answer in this document.' The system was not lying, but the user did not learn anything useful.