ade-ops · operate
Operate your data platform in plain language.
ade-ops takes a data platform, or the slice of it you own, from design to deploy, run and evolve. People and AI agents drive every operation conversationally, under the rules you set and track: fast where it is safe, gated where it counts. It is built for the teams that build and run data products, and for the AI coding agents working alongside them.
live Public preview, v0.2.0 (pre-1.0).
What you get
Whole-lifecycle orchestration
One operating model from build to deploy to run to change. Today across Databricks, Power BI and Fabric, with more platforms being added.
People and agents, one team
Humans and AI coding agents drive the same governed operations. AI-agnostic: Claude Code, Copilot or Codex, no lock-in to one assistant.
Rules you set, and track
Encode naming, environments, guardrails and deploy gates once. Every operation is checked against them and logged, so you always know what ran, by whom, and why.
Governance you dial in
Choose, per team and per environment, where you sit between flexibility and approval with role gates: a live change can flow freely, or be shown as a diff and held for review.
How to start
ade-ops is open source under Apache-2.0. Start from the repository and the docs, on a single project from your own machine, then grow it into how your whole team operates. The app shows the operating console on synthetic demo data.
What it does not do
- It is a public preview, v0.2.0, before 1.0: expect the surface to change between releases.
- It operates the platforms it has connectors for, today Databricks, Power BI and Fabric. Anything else is out of its reach until a connector exists.
- It does not replace your platform's own security. It runs with the credentials you give it, and its gates add to your permissions; they do not stand in for them.
- It works on one data product's lifecycle at a time, not on your whole landscape. Mapping the landscape is what ade-catalog is for.
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
▶ 1:18We decided to move a Power BI report to Qlik. How do we prove nothing changed on the way?lab build · Oct 2026 ade-opsFrom 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.