Admin

Admin

Draft checking

Runs on its own

Checks every prepared reply against your own words and calendar before you see it.

You see the result of this in Inbox

AI connections

Which model does this

Reply availability grounding

Checks a scheduling-shaped prepared reply against the exact Calendar facts it was written from; ungrounded availability claims are revised or the draft is withheld.

Customized

Every model that can actually run this is listed. The one at the top of each group is usually the safe choice.

One of these models always reasons, so Off is unavailable.

Available choices work with both the primary and fallback models.

Thinking harder gives better answers but takes longer and costs more.

1,800 tokens · about 1,350 words of room · at most $0.01 per response

Longer answers cost more. “Normal” suits almost everything; only raise it if answers are being cut short.

Ordered fallbacks
1.
These choices apply to the next request handled by this service.

How you have told it to approach this

Using NephAI's own wording
Inbox
01
Reply availability groundingused by Reply availability grounding

Checks a scheduling-shaped prepared reply against the exact Calendar facts it was written from and revises ungrounded availability claims.

Default

How much this has been used

Last 28 days

Times it ran

43

Text handled

191,467

What it cost

$0.5563

See this alongside everything else

Other settings that affect this

AssistanceWriting