Learning the namespace

In the final onboarding step, Scirix indexes your code so its agents can find their way around. The page shows live progress: files discovered, chunks embedded, symbols extracted, and the languages detected in your repositories.

What to expect🔗

• Indexing time depends on repository size. Small repositories finish in minutes; large ones take longer. The progress counters should tick upward steadily.
• Indexing speed also depends on the embedding model chosen in Step 5. Self-served embedding models are usually slower than the platform default.
• You do not need to keep the page open. Indexing continues in the background.
• When learning completes, your namespace is ready. The search index is live and agents can start working on tasks.

If you brought your own hardware, do not be alarmed if your GPU sits idle during indexing. Unless you selected your own embedding provider in Step 5, the index is built with the platform's embedding model. Your hardware's first heavy workload comes with the first audit or task, which run on the roles assigned to your provider.

If the progress counters sit at zero for a long time, something is wrong. See Troubleshooting.

After learning completes🔗

Continue with Your first hour to learn what normal use looks like and how to create your first task.