AI CaseQuery
From installation to answers your firm can rely on

Getting Started

Version 2.1 · September 2026

AI CaseQuery answers questions about your firm's database in plain English. It does not know on day one what your firm means by its own words — which files count as active, what referred means, how you count a sale. Getting started is mostly teaching it that, and then proving that it learned.

The short versionYour IT connects it read-only and hides anything sensitive. It studies how your database is built, on your own network, and comes back with a short list of words it needs you to define. Your leads settle those and check a set of standard questions. Then you test it against figures from reports you already trust — so you have proof, not our word. After that, anyone who spots a wrong number sends it to a lead with one click.
1. Connect and protect Read-only, hide sensitive columns Your IT or administrator Day one 2. Prepare the database Runs on your own network Automatic Produces the list of words to define 3. Teach it your language Settle terms, check baseline questions Your operations leads The first weeks 4. Prove it with ground truth Figures from reports you trust Administrator, with your reports Once the main terms are settled 5. Keep it honest Users flag, leads settle Everyone Ongoing; re-check every quarter Grey: IT · Purple: automatic · Green: your firm's people

Where to go next

Administrators and your DBA: Admin / DBA Guide. Operations leads: Lead Guide: Fine-tuning. Everyone who asks questions: User Guide, and Working with Casey if your firm offers the assistant.

The five stages

StageWhat happensWhat you do
1. Connect and protectAI CaseQuery is connected to your database read-only. It can never change your data.Connect under Database, then hide any column nobody should see under Schema rules. Do this before stage 2, so preparation never reads those columns.
2. Prepare the databaseIt studies how your database is built — its tables, counts and coded values — on your own network. Your table data is not sent to the AI. It writes a note for each coded column and lists the words your firm needs to define.Press Prepare Database under Settings › DB Tuning. Optionally add a data dictionary first.
3. Teach it your languageYour leads decide what your words mean, and check a set of standard questions your firm already knows the answers to.On Fine-tuning: settle each item in Definitions to settle, then mark answers in Baseline questions as Right or Wrong. A wrong answer goes back on the list to settle; a right one can become a verified query that answers the same way every time.
4. Prove it with ground truthIt answers questions you already have trusted figures for, and shows which figures it reproduced exactly. The figures are never changed to match an answer — a disagreement is the finding.Enter a handful of figures from reports your firm trusts under Settings › DB Tuning › Ground truth, then check the answers.
5. Keep it honestEvery wrong number anyone reports reaches a lead with their name on it, and settling it improves every later answer that depends on it.Users press Not right? under an answer. Re-run baseline questions and ground truth every quarter, and after large rule changes.

Two things people mix up

What these steps usePreparation runs on your own network. Checking baseline questions and ground truth asks each question of your AI provider exactly as if someone had typed it, so it is billed to your provider account. Each screen tells you how many questions it will ask before you confirm.