Ask Aria: what the assistant can and can't do
Aria drafts, proposes and cites — it never files. One page with five tabs (Inbox, Run, Activity, Ask, Settings), a launcher on every screen, EU-hosted Mistral, and a person approving every change.
Aria is Veritome's built-in assistant. It knows the EU AI Act and the frameworks you have enabled, and it can see the context of the page you are on, so you can ask plain-language questions instead of hunting through 113 articles and 13 annexes. The words beside its mark are the whole rule: drafts, proposes, never files.
Aria runs on Mistral, served from Mistral's EU infrastructure in Paris under a commercial agreement with no training on your data; the application and its database run on a Hetzner server in Nuremberg. Organisation → Data, privacy & residency states the same facts for your own records.
Where you'll find Aria
- The Ask Aria button in the top bar opens a drawer that carries the context of the screen you are on — a system, an obligation, a register — and links to the full page.
- Aria's page has five tabs in one header:
| Tab | What it is |
|---|---|
| Inbox | Every proposal waiting for a person — from a run, from a chat, or from a regulatory signal — with the same three choices: apply, dismiss, or open the record. Tab one, with a count, because an unlooked-at proposal is the most important thing Aria makes. |
| Run | Give Aria a goal. It plans, reads what it needs, and proposes; you approve each change. |
| Activity | What Aria did, with outcomes: Applied · Dismissed · In inbox · No proposals · Failed. A run that produced nothing is never reported as a success. |
| Ask | The conversation. |
| Settings | Behaviour, privacy, knowledge sources and autonomy. |
- The Dashboard shows an Aria found something band when proposals are waiting — drafted, not applied.
- On the classification Review screen, Aria can draft the reasoning for the classification you chose; the answers are yours.
What Aria is good for
- "Does Annex III cover a CV-screening tool?" — interpreting the EU AI Act.
- "What does Article 13 require me to give my deployers?" — explaining an obligation in your situation.
- "Draft the human-oversight section for this system." — a first draft you then review and edit.
- "What applies before 2 December 2027?" — dates, with the provision cited.
Asking a question
Open the Ask tab or the launcher, type your question or pick a suggestion. To ground the answer in your own material, attach a document (PDF, DOCX, TXT, MD or CSV) — Aria reads it and answers against it. Aria replies with clickable citations; citations are always on — it names the provision it relies on or says it cannot. Rate an answer, copy it into your work, or resume an earlier conversation from the rail.
Controlling what Aria sees
Settings governs the context sent with your questions: response style; whether Aria may read obligation status, risk classifications, team member names and document titles; anonymise system names, which replaces real names with generic identifiers; and whether conversation history is kept. The knowledge sources follow Frameworks: binding law (the EU AI Act, GDPR) is always grounded, and each standard is grounded once you enable it on Frameworks — there is no separate list to maintain.
Autonomy: Approve each, or Auto-apply
Each capability Aria has carries an autonomy level. Approve each means nothing applies without sign-off. Auto-apply lets low-stakes changes apply and be logged for review; the header pill reads Auto-apply · partial so nobody mistakes the posture. Some capabilities carry a floor — needs approval, sign-off required · always, or manual only — that cannot be lowered.
The guardrail
Aria is a drafting and research aid, not a legal sign-off. Every suggestion — a proposed risk tier, a drafted control, a reprioritised due date, an agent action — is a proposal for a human to confirm. Regulator-facing actions (incident notifications, EU database registration, dossier submissions) are never automated; Aria will not even propose them. Veritome records who confirmed what, so the human decision, not Aria's suggestion, is the one in your audit trail.