Vianordis
--:--:-- UTCVianordis / SUPPORT
marketing

Imago

Beta

Imago organizes AI-assisted marketing work into controlled projects. Teams define a topic, goal, channels, and influencer persona, then move through research, planning, content creation, and publishing with a human approval gate before content goes live.

Beta operating manual

Imago beta project manual

Run AI-assisted marketing projects through gather, plan, create, and publish stages with explicit human approval.

Manual
Version 1.0
Product
Imago 2.0.0 beta
Verified
July 15, 2026
Language
English · Source
Owner
Imago product and support
Source
Imago · 975a2af
Review cycle
45 days
Start here

Audience, scope, and prerequisites

Covers Imago beta projects, configured AI influencer personas, staged AI artifacts, human approval, denial, abort, publication state, settings, and history. External channel publication depends on configured integrations and approval policy.

Who this is for

  • Marketing project users
  • Campaign reviewers and approvers
  • Imago operators, auditors, and support

Before you sign in

  • A tenant-scoped Imago role
  • An approved marketing brief, audience, brand, claim, and channel plan
  • Rights for source materials and generated assets
  • A named human approver for every stage and publication
Access model

Roles and responsibilities

RoleAccessResponsibilities
AuditorRead projects, artifacts, and decisions without approving or running work.
  • Review traceability
  • Report unsupported claims or missing approvals
User or reviewerCreate projects, start runs, and approve, deny, or abort when assigned.
  • Validate artifacts against sources and policy
  • Remain accountable for publication
Operator or administratorConfigure settings and tenant behavior.
  • Protect AI provider and channel configuration
  • Reconcile deployment state
Workspace map

Navigation

Projects

/

Create and review tenant marketing projects.

Project detail

/projects/{id}

Review goal, stages, artifacts, approvals, and run history.

Influencers

/influencers

Review configured AI influencer personas.

Settings

/settings

Manage approved tenant AI or provider settings when permitted.

Chapter 01

Plan and run a project

A strong brief and fixed approval criteria reduce uncontrolled AI iteration and accidental publication.

Procedure 1.1

Create a marketing project

Define topic, goal, channels, constraints, sources, and approval ownership.

  1. 1
    Search existing projects

    Avoid duplicate projects for the same campaign or deliverable.

  2. 2
    Enter title and topic

    Use a stable campaign identity and a bounded subject.

  3. 3
    Define the goal

    State audience, desired outcome, required facts, prohibited claims, tone, and success criteria.

  4. 4
    Choose channels

    Select only approved destinations and identify channel-specific constraints.

  5. 5
    Assign review ownership

    Name who will validate factual, brand, legal, privacy, and publication requirements.

Expected result

The project has a bounded, reviewable brief and explicit publication authority.

Procedure 1.2

Start and monitor a project run

Create one run and let it pause at each approval boundary.

  1. 1
    Review the current project

    Confirm goal and channels have not changed since approval.

  2. 2
    Select Start a new run

    Do not start overlapping runs for the same deliverable without a documented reason.

  3. 3
    Monitor stage and status

    Track Gather, Plan, Create, and Publish artifacts and awaiting-approval state.

  4. 4
    Preserve errors

    Do not repeatedly restart a failed stage before capturing the error and run ID.

Expected result

One run advances only to its next human approval point and retains ordered artifacts and status history.

Chapter 02

Review artifacts and control publication

Approving the Create stage can publish content; reviewers must inspect the full artifact, not only a summary.

Procedure 2.1

Review a stage artifact

Check source quality, reasoning, content, and channel suitability before deciding.

  1. 1
    Confirm project and stage

    Verify tenant, project, run, artifact kind, and expected approval boundary.

  2. 2
    Review Gather evidence

    Check source authority, dates, rights, missing context, and unsupported inference.

  3. 3
    Review Plan

    Check audience, messaging, claims, channels, timing, and required reviewers.

  4. 4
    Review Create output

    Check every factual claim, link, brand element, personal data, rights, accessibility, and channel formatting.

  5. 5
    Record findings

    Use the decision note to explain required changes or approval basis.

Expected result

The reviewer has evidence for approval or a precise correction request tied to the current artifact.

Procedure 2.2

Approve, deny, or abort a run

Choose the action that matches review evidence and downstream impact.

  1. 1
    Approve only an accepted artifact

    Confirm the exact version and understand that Create approval may trigger Publish.

  2. 2
    Deny for a redo

    Enter a specific note describing factual, brand, legal, privacy, or format corrections.

  3. 3
    Abort unsafe or obsolete work

    Abort when the goal, authority, channel, or risk has materially changed.

  4. 4
    Verify the next state

    Confirm the run advances, re-enters generation, or stops as intended.

Expected result

The run state matches an accountable human decision and its note remains in approval history.

Procedure 2.3

Verify publication and reconcile history

Confirm the actual destination and preserve the final human decision trail.

  1. 1
    Check run completion

    Confirm the run reports done/published rather than assuming an approval delivered content.

  2. 2
    Open the destination

    Verify content, account, audience, link, media, timing, and formatting on each configured channel.

  3. 3
    Correct through policy

    Use the channel’s approved correction or removal process for a publication defect.

  4. 4
    Review History

    Confirm artifacts, approvals, denials, aborts, and publication state remain traceable.

  5. 5
    Reconcile if inconsistent

    Use the approved operator reconciliation path; do not alter database state manually.

Expected result

The published output matches the approved artifact or a traceable correction/escalation is active.

Operating rules

Security and data handling

  • Keep projects and artifacts tenant-scoped.
  • Use authoritative, licensed source material and verify every generated claim.
  • Require explicit human approval at each stage and before publication.
  • Treat external publication as irreversible even when a channel supports deletion.
  • Protect provider, channel, and BYOAI settings as privileged configuration.
Current release

Known limitations

Read before relying on an unsupported workflow

These limits describe the source-pinned Imago 2.0.0 beta scope and must be rechecked when the product changes.

  • Imago is beta and external publication depends on AI-core and channel integrations.
  • Artifacts are rendered as text/JSON and may require channel-specific preview outside Imago.
  • AI influencer personas do not have independent authority or factual reliability.
  • Denial requests regeneration but does not guarantee the next artifact fixes every issue.
  • Approval of Create is configured as the publication transition and requires special care.
Problem solving

Troubleshooting

You cannot sign in to Imago

Likely cause: The session expired, the identity is not assigned to the application, or the tenant claim is missing.

  1. Open the application from the approved portal and complete sign-in again.
  2. Confirm that the correct organizational identity and tenant are selected.
  3. If access is still denied, record the time and request an entitlement check from support.

A documented action or navigation item is not visible

Likely cause: The current role, release, tenant configuration, or feature flag does not expose that operation.

  1. Confirm the role and prerequisites listed for the procedure.
  2. Reload the page after signing in again; do not attempt to bypass the interface through direct URLs.
  3. Ask the product owner whether the feature is enabled for the tenant before reporting a defect.

A saved change or background operation is not visible

Likely cause: Validation failed, processing is still running, or the current view is stale or filtered.

  1. Review inline validation, status indicators, filters, and the selected tenant or workspace.
  2. Refresh once and search for the item by its stable name or identifier.
  3. Do not repeat irreversible or externally visible actions until the original operation status is known.

A run is stuck or shows an unexpected stage

Likely cause: AI-core, state transition, approval, or reconciliation failed.

  1. Do not start a duplicate run.
  2. Record project ID, run ID, stage, status, and last artifact time.
  3. Have an operator use the approved reconcile path and review side effects.

Published content differs from the approved artifact

Likely cause: Channel transformation, stale integration state, wrong account, or a later external edit occurred.

  1. Preserve the approved artifact and destination evidence.
  2. Restrict or correct the external publication under channel policy.
  3. Review approval and integration history before republishing.
Escalation

Contact support

Contact support when

  • A repeatable Imago error blocks an approved workflow
  • Expected data, permissions, or tenant boundaries appear incorrect
  • A security, privacy, compliance, or data-loss concern is suspected
  • Content publishes without the expected approval
  • A project or artifact crosses tenant boundaries
  • An external account or AI provider configuration is incorrect

Include

  • The page, action, and expected result
  • The exact error text and time of occurrence, including time zone
  • Your tenant, role, browser, and a sanitized record or item identifier
  • Whether the problem can be reproduced and which troubleshooting steps were tried

Never include

  • Passwords, access tokens, API keys, recovery codes, or session cookies
  • Unredacted personal, health, financial, or other regulated data
  • Private encryption keys or complete confidential documents unless an approved channel is provided
Contact support