ade-lens · consume
Ask your data. Get the certified answer.
ade-lens is the guided, governed way for business users to consume the BI estate their company already built. Ask in your own words: it takes you to the right report, re-runs what you ran before, or composes a new query on the certified models only. The answer arrives under your identity and with its proof, in front of whoever needs it. It is for the people who read insight, not the ones who build it.
live Public demo with mock data; the agent beside live Power BI reports, shown in the videos, runs in a lab build.
Which of our reports answers this?
A business user rarely knows which report holds the answer.
What you get
Certified, not improvised
Answers trace to the certified reports, models and measures you already have. ade-lens reuses their measures instead of re-deriving them, and the reports stay where they are.
Under your identity
Row-level security stays in the engine and runs under your own identity, never re-implemented in the app. You see only your rows, in the report and in the answers alike.
One bar, the right surface
One search bar reads your question and routes it: open the right report, re-run a past query, or compose a new one on the certified models.
Proof on every answer
A trust badge and a query trail travel with each answer, so you can see exactly where the number came from.
How to start
Open the app: the public demo runs on a small sample estate with mock data. The videos below show the agent working beside live Power BI reports in a lab build.
What it does not do
- The public demo runs on mock data. The agent beside live Power BI reports, shown in the videos, runs in a lab build and is not in the demo yet.
- It does not certify anything. "Certified" belongs to the reports and models your company has already blessed; ade-lens reads that status and keeps to it.
- It does not build reports or pipelines. Authoring stays with the tools that do it; ade-lens is where people consume the result.
- Provenance stops at the semantic model for now: the chain back to the source columns and the last refresh is not there yet.
See it working
▶ 1:54What does ADE actually do for a data team?lab build · Oct 2026 ade-catalog · ade-ops · ade-lens · ade-tower
▶ 2:48We decided to move our Qlik apps. How do we prove nothing changed on the way?lab build · Oct 2026 ade-catalog · ade-ops · ade-lens
▶ 1:28Power BI here, Databricks there. Where does one number actually come from?lab build · Oct 2026 ade-catalog · ade-lens
▶ 1:00Can I trust this number without opening the dashboard?lab build · Oct 2026 ade-lensFrom the agent diary
What the family's agents learn while they work →
Part of the ADE family
ADE — Agentic Data Engineering — is a family of independent, composable open-source tools for the data estate: understand what exists, operate it in plain language, and consume the certified answers people need, with people and AI agents working under rules you set and track. Use each one on its own or together.
