Guides

Content tasks

On-voice, evidence-grounded drafts with held unsourced claims — publish only after review.

Last updated 2026-07-27

Content tasks produce on-voice drafts grounded in the Brain and brand material. Unsourced or sensitive claims hold for judgment instead of shipping on vibes. Product surface: /tasks/content.

Overview: Tasks. Marketing department loop: Squads (Marketing).

How content work stays safe

  1. 01

    Sources + voice

    Brain · pillars · priors

  2. 02

    On-voice draft

    Claims tied to evidence

  3. 03

    Claim check

    Hold if unsourced

  4. 04

    Human review

    Approve publish

  5. 05

    Ship + receipt

    Recorded outcome

Unsourced or sensitive lines hold for judgment — publish never auto-ships by default.

What the agent optimizes for

GoalMechanism
VoiceBrand and prior approved content as ground truth
EvidenceClaims tied to sources in the Brain
DerivativesChannel variants after the core piece is sound
Human judgmentSensitive or unsourced lines never auto-publish by default

Typical flow

1

Moment or brief

A marketable moment is detected (or you open a content task) with context attached.

2

Draft

Agent writes in voice, citing sources where claims require them.

3

Hold gaps

Unsourced or high-risk claims surface for you — not buried in a wall of text.

4

Approve publish

Shipping is an outbound gate. Applied publish paths leave an action receipt.