Admin

Admin

Prepared replies

Runs on its own

Writes the canonical reply waiting in a conversation.

You see the result of this in Inbox

AI connections

Which model does this

Pre-drafted replies

Drafts one full, grounded reply in advance for needs-reply threads with nothing prepared, so the thread opens with the reply waiting. Prepares only — never sends.

Customized

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

Available choices work with both the primary and fallback models.

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

4,800 tokens · about 3,600 words of room

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

What you write here also changes how NephAI writes when you compose a message yourself.

Inbox
01
Reply draftingused by Composer

Writes replies in your voice — the composer's write step AND every pre-drafted reply waiting on a thread.

Default

Whether NephAI does this on its own

On its own

These same settings also govern Coordination packages, because the two run together.

Last time it ran

Sep 9, 2026, 12:31 PM

Change what you want, then save.

How much this has been used

Last 28 days

Times it ran

293

Text handled

3,296,589

What it cost

$3.75

See this alongside everything else

Other settings that affect this

AssistanceWritingRulesAutomations