Admin

Admin

Automation follow-through

Runs on its own

Confirms from current evidence when prepared Automation work has finished.

You see the result of this in Tasks · Settings → Automations

AI connections

Which model does this

Rule verification

Samples generated artifacts for rule compliance beyond deterministic lint. Budgeted and never on the interactive hot path.

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.

4,096 tokens · about 3,072 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
Coordination & assistant
01
Automation completion assessmentused by Rule verification

Interprets current evidence against one Automation's configured completion definition; factual provider, identity, currentness, and stored-state claims are checked separately.

Default

How much this has been used

Last 28 days

Times it ran

963

Text handled

17,188,247

What it cost

$25.37

See this alongside everything else

Other settings that affect this

AutomationsRules