Reference

Assistant (AI)

The Assistant is the first X7 Insight platform module: a context-aware AI helper over your study data. Permissions and audit are the same as for human users. The inference perimeter is set at deployment time: it can be fully local (the model is deployed with you — then data never leaves the system) or external, if so decided during rollout.

What it can (and cannot) do

It can:

explain — what is left to fill in a form, why a check fired, what an open query means, how a version’s design is built (read-only, within your own permissions);
prepare drafts — prefill a form from an uploaded source document (OCR), draft a query/answer text, assemble a study skeleton from a protocol;
execute with confirmation — on your explicit command, open a query or build a draft design version (only where level 2 is enabled).

It cannot (and never will — these are red lines):

enter, change, auto-verify (SDV) or sign clinical data;
work with unblinded data (it sees the ***BLINDED*** mask, just as you do without the permission);
advise on managing a specific subject (diagnosis, dose, treatment) — that is outside an EDC;
fabricate data “to pass a check” — with no source it stops.

Autonomy levels

What the Assistant may do in your study is set by the administrator (level + feature toggles). The level cannot be “jumped” from the UI — it is part of change control.

Level 0 — Explain. Read-only chat: it answers from data you can see (the intersection of your permissions and the module’s).
Level 1 — Prepare. Drafts are added: OCR form prefill, query text drafts, parsing a protocol into a design structure. You review and confirm every draft.
Level 2 — Execute with confirmation. On your explicit confirmation button the Assistant performs a prepared action (open a query, build a draft design version). Without confirmation nothing happens.

Where you meet it

Surface	What you ask	What you get
Chat dock (Assistant button)	a question about the study, subject, form	an answer from data you can see; fields, queries, forms, subjects and visits as link chips
Form panel	“ask about this form”	what is left to fill in, why a check fired, what an open query means
Form panel	“fill from a document” (scan/photo/PDF)	a suggestion card for every value: confidence and the source snippet; you can correct the value right in the card
Design builder panel	explain the design; an edit check in words	an explanation of the current design version
Design builder panel	a draft version from a protocol	a structure on a preview with warnings → assembled as an ordinary version draft
Settings (Admin)	—	autonomy level, enabled features, inference health, quality dashboard (for the module administrator)

Details worth knowing:

Chat dock: the conversation survives a page reload; the History button lists your earlier conversations, “+” starts a new one.
Form panel: a value corrected right in the card is recorded as “edited”; accepted values are saved by your action (marked as AI-assisted in the audit); “Reject all” is a decision too — and it is journalled.
Design builder: the order is — upload the protocol → the Assistant extracts the structure → you review and adjust it → preview with warnings → build. The result is an ordinary draft that goes through the normal route: submit → review → approve by another person → publish.

AI literacy: working with AI responsibly

AI speeds up routine, but responsibility for the data stays with the human. Remember:

Verify against the source. A suggestion is a hypothesis, not a fact. Check the value against the source document, especially for critical fields.
Beware automation bias. The temptation to accept everything without looking is the main risk. Open the evidence; read drafts before sending.
AI can make mistakes. The model is deterministic and works from the source, but recognition and extraction are not flawless; low legibility → lower confidence.
It is AI, not a person. All AI surfaces are labelled; every interaction is logged (which model, which prompt) — part of the audit trail.

Your responsibilities by activity

Data entry (CRC): accept prefill suggestions deliberately, checking against the source; open evidence for critical fields; the final record is yours.
Monitoring (CRA): source-vs-data discrepancy hints are candidates only; SDV remains your manual act.
Design (Builder): a generated design is a draft; you review forms/fields/visits and checks on the preview; the version is approved by another person (separation of duties).
Data management (DM): you edit query-text drafts and send them under your own name; opening a query by the Assistant requires your confirmation.

Privacy and confidentiality

Your conversations, uploaded documents and suggestions are visible only to you — even to colleagues who use the Assistant on the same study. An inspector reconstructs the document → suggestion → your decisions chain from the audit trail, not from someone’s chat.
Uploaded documents may contain personal data — only upload sources you are authorised to process; they are retained per policy and then deleted.
The Assistant does not see blinded data (***BLINDED*** mask), just like you without the permission.
The model does not train on your data under the recommended (local) deployment; with an external inference provider this is guaranteed by the contract with that provider.

Permissions

The module’s separate permissions separate its surfaces:

Assistant access — the button and the chat;
Document upload and OCR — “fill from a document”;
Design generation and edits — the panel in the design builder;
Level 2 action confirmation — the button that executes a prepared action;
Settings and the quality dashboard — for the module administrator.

What’s next

What modules areHow modules are enabled and configured.

Roles and accessHow grants and scope define what you and the Assistant can see.