Assistant Admin — Onboard Workbooks

AI model

The assistant answers with your own LLM API key — Anthropic (sk-ant-…) or OpenAI (sk-…), detected automatically. Stored locally in config.json.

API key

Model

Power BI connection

Register an app (service principal) in your own Entra tenant, add it as a Member of the workspace(s) that hold the reports you want to onboard, then save the details here. Stored locally in config.json.

Tenant ID

Client ID

Client secret

Workspace ID

Onboard a Power BI workbook

Paste a report's URL from powerbi.com (while viewing it). The report is read in place — no upload. The service principal must be a Member of that report's workspace. Reads the model's tables, measures and relationships, extracts and profiles the data, and generates the reference documents with AI.

Onboard even if row-level security roles are defined — I understand per-user filtering will NOT be enforced in the assistant

Assistant knowledge

Give the assistant extra context it can use when answering — business definitions, targets, caveats, anything not visible in the data itself.

ⓘ Overall description (below) applies to all dashboards — e.g. "All amounts are in USD; the fiscal year runs Apr–Mar."
Per-dashboard notes — click Notes & files on a dashboard in the list below for context specific to that dashboard.
You can type text, upload a document, or both. Supported file types: .txt, .md, .docx, .pdf (max 5 MB). The text is extracted and handed to the AI alongside the generated reference documents whenever it answers.

Overall description — applies to every dashboard

Upload file

Onboarded dashboards

Everything the assistant can currently answer questions about. Use Notes & files to add curated context for a specific dashboard (text or a .txt / .md / .docx / .pdf file).

Loading…