49.1 Existing Sources

The bottom of the Agent's Knowledge Sources page contains Existing sources.

This list is where you review each Source's processing state, sync information, page progress, errors, and maintenance actions.

49.2 Searching Sources

Use Search sources… to locate a Source when the Agent has many entries.

The Sources list is paginated so large Knowledge collections can be reviewed without loading every Source at once.

49.3 Source Statuses

The deployed interface recognizes these primary Source statuses:

  • Pending
  • Crawling
  • Indexed
  • Failed

49.4 Pending

Pending means the Source has been created or requeued but processing has not yet completed.

49.5 Crawling

Crawling indicates that website content is currently being fetched or processed through the crawl pipeline.

Allow background processing to complete before concluding that the Source has failed.

49.6 Indexed

Indexed indicates successful Source processing. For multi-page Sources, also review the number of pages indexed compared with the total expected page count.

49.7 Failed

Failed indicates that the Source could not complete processing. The Sources list can display a human-readable error next to the Source.

Use that message to decide whether to correct the Source or try Reindex. If the message indicates an external connection problem, use your normal support process rather than changing Workspace connection settings.

49.8 Last Sync and Page Progress

Each Source can display:

  • Its human-readable title.
  • Source type or subtitle.
  • Last synchronized date, or never synced.
  • Indexed-page progress.
  • Current status.
  • An error message when applicable.

49.9 Preview What the AI Sees

Select the Preview icon for a Source to open What the AI sees for this source.

The preview reports the Source status, page indexing progress, and any error.

49.10 Previewed Documents

For extracted Documents, the preview can display:

  • Document title.
  • URL.
  • Fetched date.
  • Total Chunk count.
  • A limited set of the first Chunks for inspection.

49.11 Viewing Chunks

Select View chunks within the Preview to inspect the actual extracted text.

Each shown Chunk includes its order and token count.

This is one of the most useful checks for determining whether the Agent received meaningful content.

49.12 No Extracted Content

If the Source has no extracted Documents yet, the interface states:

No content extracted yet. Try Reindex, or check the error message above.

49.13 Sources Page vs. Knowledge Page

The Source Preview is useful for checking one ingestion Source. The separate What the AI knows page provides an Agent-wide view of indexed Documents and Chunks across all Sources.

Write Your Comment