Ask: answer questions in plain English
Let end-users query their own data conversationally — no reports to build.
What Ask is #
Ask is a built-in data agent your end-users talk to in plain English. They type a question — "which customers are overdue and not in the Q3 deal?" — and Ask plans a query, runs it against your Tadabase data, and renders the answer. No report builder, no filters, no training.
How answers come back #
Ask picks the clearest shape for each question and renders it natively:
| Render | When Ask uses it |
|---|---|
| Table | A list of matching records — "show me open tickets by owner." |
| Chart | A comparison or trend — "revenue by month this year." |
| Number | A single metric — "how many invoices are overdue?" |
| Sentence | A written answer when prose reads better than a grid. |
Every answer is permission-scoped #
Ask runs every query under the signed-in user's own Tadabase session. The same row-level security you already wrote applies — a user can never use Ask to see a record they couldn't already see in the app.
Turning Ask on #
Ask is enabled per interface, so you can offer it on a customer portal but keep it off an admin-only screen. Flip it on in the app's AI settings, and it appears for users with access to that interface.