home / use cases / data, spreadsheets and reporting / ask-your-database

Ask your database in plain language

Staff ask questions in the chat widget — how many open orders over 30 days? which products sat unsold last month? — and an Aivell writes the query, runs it read-only against your database, and answers in plain words with the numbers. No report request, no waiting for the one colleague who knows SQL.

Watch the demo

starts when: You type a question into the chat widget

The problem

In most companies, the data is plentiful and the answers are scarce. Between a question — “how many open orders are older than 30 days?” — and its answer stands the one colleague who knows SQL, a ticket queue, and a delay measured in days. So people don’t ask. They estimate, they reuse last quarter’s number, or they decide on gut feeling while the truth sits three tables away.

The irony is that the questions are almost always simple. They don’t need a data team; they need someone patient who knows the schema and has ten seconds. That colleague just never existed — until now.

How your Aivell does it

  1. The question arrives in chat. The widget sits where your team already works; a guardrail limits it to signed-in staff on your network.
  2. The query is written for you. The Aivell knows your schema and your quirks — which status means “open”, where returns hide — writes the SQL, and runs it over a read-only connection.
  3. The answer comes in plain words. “42 open orders older than 30 days, €187,000 in total — 28 of them from two customers.” The query itself is shown underneath, so anyone can verify or reuse it.
  4. Follow-ups just work. “And by region?” continues the same thread, the way a conversation with a colleague would.
  5. The edges are handled by rules, not luck. Ambiguity gets a clarifying question, not a guess. Salary and personal-data questions are declined and routed to Sofia. Every query is in the audit trail.

The guardrails make this safe enough to hand to everyone: the connection cannot write, the sensitive schemas aren’t connected at all, and the log shows who asked what. Your database finally answers the phone — without ever leaving the building.

The chore, as you'd write it.

No flowcharts, no code — a chore is just a message to your Aivell, in your own words. It shapes it into a solid, guarded procedure and follows it to the letter. This one:

Giulia Aivell · answer data questions ● active

when a question arrives in the chat, work out which tables answer it

write the query, run it read-only, sanity-check the result

answer in plain words, with the query shown underneath for the curious

round numbers sensibly; give exact figures on request

questions touching salaries or personal data — decline, point to Sofia

ambiguous question? ask back instead of guessing

keep the thread open for follow-ups like "and by region?"

every question and query goes in the audit trail

You
Got it — I'll start right away, and check with you whenever something needs a human.
Giulia Aivell

The tools it uses.

Connected with single-click passkeys — no copied tokens, no OAuth hell.

Chat widget where questions arrive and answers land
Database runs the queries, read-only

Sensible guardrails.

Every tool can be limited to exactly what this chore needs. For this one, you might set:

Database Read-only by construction — anything that writes is blocked at the tool, no matter how the question is phrased.
Database The payroll and HR schemas are not connected at all. No query can reach them.
Chat widget Answers only signed-in staff on the office network; visitors get nothing.

Questions, answered.

Do people need to know table names or how the data is structured? +

No. They ask the way they'd ask a colleague — "which customers went quiet this quarter?" — and the Aivell finds the tables. It learned your schema once, at setup, and keeps a note of your quirks, like which status codes mean "open".

Could a cleverly worded question change or delete data? +

No. Read-only is a guardrail enforced on the database tool itself, not a polite instruction. However a question is phrased, a write physically cannot run — and every query lands in the audit trail regardless.

Is our database exposed to a cloud AI to make this work? +

No. The question, the schema, the query and the result all stay on the box. The model that writes the SQL runs onboard, inside your network — your data structure is as private as your data.

What if the question is vague? +

It asks back. "Sales this year — orders placed, or orders shipped?" One clarifying question beats a confidently wrong number, and the chore says so explicitly.

Related.

What is an Aivell?

An Aivell is an on-premise AI colleague: a small box that plugs into your network, runs its own AI onboard and takes the repetitive work off your desk. Prompts, documents, data — nothing ever leaves your office. Unplug the internet: it keeps working.

You describe each task as a chore, in plain language. Your Aivell turns it into a solid, guarded procedure and runs it in the background — with guardrails on every tool, a complete audit trail, and approvals in your hand when you want them. One-time setup, fixed monthly fee. No tokens, no overages.

Watch the demo

onboard inference · air-gapped · fixed monthly fee