Your hiring data should answer questions, not export CSVs

A quiet shift is happening in how people use their software. Instead of opening five dashboards and exporting spreadsheets, they connect an AI assistant to the system that holds the data and ask questions in plain language. Which stage loses the most applicants. How long screening takes on average. Whether this quarter's pools are stronger than last quarter's. The assistant reads the data and answers.

Why this beats dashboards

A dashboard answers the questions someone predicted you would ask, months ago, when it was built. Real questions do not arrive on schedule. They arrive mid-meeting, when a hiring manager asks why the pipeline stalled, and the honest answer is that the chart for that does not exist. An assistant connected to your data answers the question you actually have, in the shape you asked it, and the follow-up question too.

How it works in notanATS

We built this in rather than waiting for you to duct-tape it. In settings, you generate a read-only API key and point Claude, or any assistant that can call an API, at your own hiring data. Then you talk to it the way you look at data: your funnel, your roles, your screening outcomes, questioned directly.

Two properties of that key matter more than the feature itself. It can look, not touch: nothing connected through it can change a record, move an applicant, or act on your pipeline. And it sees your organisation only. The boundary is enforced where the data lives, not by politeness.

What recruiters actually ask

Where does my funnel leak between invitation and completed screening. Which roles pull the strongest pools. What did the last five hires have in common at screening time. How long does an applicant actually spend in a screening conversation. These are the questions that used to mean an afternoon of exports, and now mean typing the question.

The larger point: your hiring data is only as useful as your access to it. Systems that trap it behind fixed reports are making a decision for you about which questions you get to ask. We would rather you ask anything.

The fastest way to judge any of this is to run it on a real role. Run a live test. Two postings, no card.