The launch the dashboard in a new browser window, use:Documentation Index
Fetch the complete documentation index at: https://docs.hiverge.ai/llms.txt
Use this file to discover all available pages before exploring further.
Home page
The home page shows a summary of your team’s experiment activity. At the top are total experiment and iteration counts, followed by a status distribution chart and a timeline of experiment launches. Use the time range selector (7 days, 1 month, 3 months) to adjust the window.
| Experiment status | Description |
|---|---|
| Pending | The experiment is currently running and in progress. |
| Completed | The experiment has finished successfully. |
| Cancelled | The experiment started running but was interrupted before completion. |
| Aborted | The experiment was interrupted before it started running. |
Experiments page
List of all experiments launched by the team, sorted in chronological order.
Overview
The overview provides a high-level summary of the experiment’s progress — key metrics like duration, iteration count, token usage, and cost, along with charts showing iteration status distribution and duration histogram.
Tracking
The tracking tab is an interactive workspace for exploring how the Hive evolves code over time. The evolution chart plots fitness across iterations — hover over a point to see a summary of what the Hive attempted, or select a point to view the corresponding code on the left.
- Legend — colour key for the data points.
- Expand — view the chart in full screen.
- Reset — clear any zoom selection.
- Compare — select two points to view the code diff between them.


Iterations
A searchable, filterable table listing every iteration with its status, duration, and timestamp. Useful for auditing specific runs or debugging failed experiments.
| Iteration status | Description |
|---|---|
| Completed | The iteration successfully proposed a new code candidate and evaluated it. |
| Running | The iteration is currently in progress. |
| Cancelled | The iteration was cancelled, usually because the experiment terminated before it completed. |
| Failed | The iteration encountered an error (e.g., the LLM failed to produce valid code, or the evaluation script errored). |