> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/aerial/aodt/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/aerial/aodt/_mcp/server.

# AODT Client

The AODT client is the programmatic entry point for launching simulations,
interactive result requests, batch execution, scene generation, calibration,
and simulation YAML configuration. Start with the workflow that matches how much
control your application needs during the run.

## Choose a Workflow

Drive an EM simulation step by step. Query positions, compute selected CIRs,
retrieve results into NumPy, or use C++ zero-copy access for GPU-resident data.

Run a complete EM/RAN simulation in one workflow, producing results for all
time steps in the database as S3 Parquet tables queryable from the catalog.

Generate or prepare scene assets used by simulation workflows.

Placeholder page for calibration.

Prepare the scenario YAML used to define simulation inputs, timelines, and outputs.

## Related References

* See the [DigitalTwinClient API](/api/client) for client methods such as `start`, `get_status`, `run_full_simulation`, `get_cirs`, and `to_numpy`.
* See the [Config Builder API](/api/config) for building simulation configuration in code.
* See [Results Schemas](/results-schemas) to interpret exported Parquet tables after a run.