For software engineers
Real Python and SQL, with runs you can inspect.
Describe the data work you need. Ordiva writes readable scripts on each node, runs them in isolated sandboxes, and keeps every artifact inspectable.
What you keep
01
Scripts, not black boxes
Every node runs Python you can read, with SQL where SQL is clearer.
02
Isolated execution
Nodes run in sandboxes, so a bad step fails on its own instead of taking the pipeline with it.
03
Test before you run
Dry-run nodes against sample data without writing downstream artifacts.
04
Artifacts you can read
Each run writes an output, a row count, and a column list per node.
05
An API and API keys
Create API keys in the workspace and use the API reference in the app.
06
Approval where it matters
Agent actions and new scripts ask first unless you turn on YOLO mode.
How the work flows
Capabilities you will use most
Transformations
Generated Python and SQL on each node
Describe the step. The agent writes Python and SQL from the upstream schema and attaches it to the node.
Explore transformationsRuns
A node, a branch, or the full pipeline
Run a node, a downstream branch, or the whole pipeline in isolated, observable jobs.
Explore runsAnalysis
Questions answered from saved outputs
Ask in plain language. Answers come from persisted node outputs, and new work becomes a node you can rerun.
Explore analysis
Ready to build a pipeline you can inspect?
Describe the outcome, inspect what the agent proposes, and run it when you trust it.