Ask a CRM for one customer's open pipeline when that customer is stored under four spellings, and a retrieval-based agent answers with a confident wrong number at every setting: $120,000 if it reads a few records, $1,345,000 if it reads a hundred, never the real $275,000. The model did nothing wrong. The customer's identity was never resolved in the data, and no amount of orchestration recovers it. That example is a runnable demo; the wrong total reproduces at every retrieval cutoff.
That is the shape of the most expensive surprise in AI agent projects, and it is a data problem wearing an agent costume. A team scopes the agent and budgets the model: tokens, a vector store, some orchestration. The agent demos well on three clean documents, then meets the real data, and six weeks later the project is behind, not on the model, on the data nobody put on the plan. This is the data-prep tax. Here is what it is, why it recurs instead of ending, and how to scope it before you commit to building an agent at all.
TL;DR
The model is the commodity; the data is the system. What decides whether an agent works in production is the state of your data, not the choice of model.
There are two data problems, not one. Knowledge data (policies, docs, FAQs) fails on format and terminology. Operational data (records, access, source-of-truth) fails on identity resolution and authority. They are estimated separately or not at all.
