Guides
Content tasks
On-voice, evidence-grounded drafts with held unsourced claims — publish only after review.
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
- 01Sources + voiceBrain · pillars · priors
- 02On-voice draftClaims tied to evidence
- 03Claim checkHold if unsourced
- 04Human reviewApprove publish
- 05Ship + receiptRecorded outcome
- 01
Sources + voice
Brain · pillars · priors
- 02
On-voice draft
Claims tied to evidence
- 03
Claim check
Hold if unsourced
- 04
Human review
Approve publish
- 05
Ship + receipt
Recorded outcome
What the agent optimizes for
| Goal | Mechanism |
|---|---|
| Voice | Brand and prior approved content as ground truth |
| Evidence | Claims tied to sources in the Brain |
| Derivatives | Channel variants after the core piece is sound |
| Human judgment | Sensitive or unsourced lines never auto-publish by default |
Typical flow
Moment or brief
A marketable moment is detected (or you open a content task) with context attached. The agent researches and holds at an outline until you approve it.
Draft
Agent writes in voice, citing sources where claims require them.
Hold gaps
Unsourced or high-risk claims surface on the phrase itself — Use that when a sourced figure exists, Keep to vouch, or Cut. Not buried in a wall of text.
Approve publish
Shipping is an outbound gate. Applied publish paths leave an action receipt.