Drop a wav file, add a folder, or connect to a stream.
or click the file icon on the left
Working...
Loading…
| Name | Size | Modified | Models |
|---|
Loading…
| Colour | Name | Target | Source | Fitness | Macro F1 | Updated | Actions |
|---|
Save the current folder run — its folder, the model(s) run, the spectrogram spec params and every emitted decision — so you can reload it later without re-running. On a supported browser the source folder reopens in one click; otherwise you'll be asked to re-pick it.
Evaluate selected models on selected recordings, rank them by macro F1, and export the report (JSON / LaTeX / PDF). Runs synchronously on the training server.
Waiting for the worker…
| File | Model | tmin (s) | tmax (s) | Score |
|---|
| When (UTC) | Type | What | How | To |
|---|
Loading…
| Name | Target | Band (Hz) | Duration | Source | Actions |
|---|
| Vessel | MMSI | Points | Type | Flag | Speed | Course | Destination | Position | Distance | Last seen (UTC) | Since report |
|---|
| Vessel | Type | Closest | Closest approach (UTC) | Fixes |
|---|
Loading…
Select two thumbnails to merge.
Select a file to split.
| Time | Cat. | Level | Message |
|---|
Each agent will plan + train + evaluate models on your behalf, reporting back here. You set the target tag and minimum F1 — the agent decides everything else within the budget you give it.
Build your agentic work flow by dragging and dropping the components onto the canvas.