Settings
Group all eligible, uncached rules for each email into one request. Actions still follow rule order and stop-after-match.
Turn off Process all to limit each request. Use 1 for one rule at a time.
Match when probability is at least this value. Rules may override it. Evaluate thresholds on your own email examples.
Leave blank for unauthenticated endpoints.
Optional header for OpenAI-hosted endpoints.
Optional header for OpenAI-hosted endpoints.
Applied with aggressive reduction. Characters are not tokens; leave room for instructions within your model's context limit.
Classification Rules
Maintenance
| Rule count | |
|---|---|
| Cache entries | |
| Queue items | |
| Current run time | --:--:-- |
| Last run time | --:--:-- |
| Average run time | --:--:-- |
| Total run time | --:--:-- |
| Messages per hour | 0 |
| Messages per day | 0 |
Session Errors
No errors have been recorded since the last start.
Error Log
Visible only for this session.
0
Debug
Prompt Token Reduction: 0%