Gnome / Industry playbookCampaign briefing
Positioning needs to distinguish research evidence from team assumptions.
Gnome / Industry playbook
Marketing
Turn approved research and campaign inputs into reviewable planning drafts.
Planning guidance, not a claim of installed capabilities or customer results. Validate scope and feasibility before deployment.
Industry overview
Marketing teams translate research, positioning, and channel constraints into reviewable plans. Agents can organize evidence and draft alternatives while keeping claims, rights, and publication approval with people.
Channel variants
Channel length limits do not remove brand or asset-license restrictions.
Claim review
An attractive performance claim may have no supporting study.
Use cases
01
Campaign briefing
- Context
- Positioning needs to distinguish research evidence from team assumptions.
- Human action
- Draft campaign briefs from approved research.
- Intended outcome
- A reviewable brief with evidence gaps explicitly marked.
02
Channel variants
- Context
- Channel length limits do not remove brand or asset-license restrictions.
- Human action
- Compare channel variants against brand constraints.
- Intended outcome
- Draft alternatives checked against the same approved constraints.
03
Claim review
- Context
- An attractive performance claim may have no supporting study.
- Human action
- Create a claim-evidence checklist for editorial review.
- Intended outcome
- A claim-evidence checklist before editorial and legal approval.
Agent, tool, and model capabilities
Separate tasks, preserve evidence
Separate research synthesis, copy drafting, and brand checks with scoped content tools. Select models through factuality and tone reviews; generated copy must not invent customer endorsements or performance results.
Evidence contract
Keep source version, tool inputs, and execution status with each draft. Missing evidence remains visible.
A person owns the decision
A reviewable brief with evidence gaps explicitly marked.
Define acceptanceProposed capabilities must be tested against representative inputs. Unsupported or low-confidence results belong in a review queue, not an automatic decision.
Real-world scenario
Hypothetical, not a client story
Hypothetical: a launch brief requests a strong performance claim with no supporting study. The workflow flags the gap and drafts a factual alternative for brand and legal reviewers.
- 01
Context
Positioning needs to distinguish research evidence from team assumptions.
- 02
Review trigger
A draft or exception needs source verification before it can leave the workspace.
- 03
Human response
Draft campaign briefs from approved research.
- 04
Intended result
A reviewable brief with evidence gaps explicitly marked.
How it works
Approved inputs
Receive a bounded task and permission-limited documents. Record source versions and reject access outside the agreed scope.
Agents and tools
Route retrieval, calculation, or drafting to selected models and scoped tools. Preserve failures, evidence, and approval boundaries in the run record.
Reviewed deliverable
An assigned person checks evidence, records the outcome, and follows the existing operational procedure. Rejected signals feed back into evaluation.
Business and operational value
Measure brief usefulness, source traceability, and edit cycles before publication.
Evidence quality
Accepted observations / reviewed observations. Count missed cases separately against the manual reference.
Target: agree before pilotReview effort
Record minutes per reviewed item, including rework and escalations. Compare the same task with the manual baseline.
Target: agree before pilotSafe failure
Record whether stale inputs, denied access, and unavailable sources stop or visibly degrade the workflow.
Target: agree before pilotEstablish a manual baseline, agree acceptance thresholds with the operational owner, and compare review effort as well as accuracy. Any benefit must be measured in the pilot; no savings or ROI are promised here.
Deployment plan
Pilot one unpublished campaign brief with approved assets and a fixed revision budget. Test unsupported claims, asset restrictions, and conflicting brand instructions before enabling broader content access.
- Scope: name the owner, permitted inputs, reviewers, and acceptance criteria.
- Prepare: assess local or approved hosted models, tool isolation, context limits, and a per-run cost budget.
- Validate: compare with human-labelled samples, exercise denied access and outages, and document rejected results.
- Decide: approve a limited rollout only after review; keep a rollback owner and re-evaluate when inputs change.
Existing tools and infrastructure
Assess asset permissions, brand-guideline versions, content formats, and model-provider handling of unreleased material. CCTV is not needed, and ad-account spending permissions are unnecessary for drafting.
| Check | Required evidence |
|---|---|
| Source access | Approved formats, source versions, licenses, and read permissions. |
| Tool boundaries | Sandbox, denied-command tests, credential isolation, and context limits. |
| Compute & recovery | Model endpoint, per-run budget, timeout behavior, and resumable evidence. |
A workflow is not a universal connector. Verify file formats, authentication, tool permissions, model context limits, and failure recovery in the actual environment before committing to a setup.
Integration planning
01
Approved source
02
Scoped processing
03
Human approval
04
Controlled export
Example: export an approved draft into a content planning workspace. CMS or campaign connectors need explicit configuration and publication gates; ad spending and live publishing are not assumed.
These are example integration plans, not live connectors. Confirm schemas, least-privilege credentials, delivery acknowledgements, retry limits, and duplicate handling in a sandbox before enabling data exchange.
Security and privacy
Use aggregate research rather than personal targeting profiles. Protect unreleased plans, respect asset licenses, and forbid fabricated testimonials, sensitive-trait targeting, or unauthorized publication.
Least privilege
Approve reviewer roles and test a denied-access case before launch.
Data lifecycle
Set retention, deletion ownership, and encryption for stored and transmitted evidence.
Accountable operations
Log access and decisions; rehearse incident escalation and rollback.
Before launch, approve purpose and lawful access, role-based permissions, encryption configuration, retention and deletion rules, audit logging, and incident ownership. Verify these controls in the chosen environment; this page does not claim compliance certification.
Hypothetical pilot example
HYPOTHETICAL PILOT
One bounded question. Evidence before expansion.
Hypothetical pilot: prepare two channel drafts from one approved brief containing a deliberately unsupported claim. Reviewers check whether both drafts flag the claim and preserve asset restrictions before accepting them.
A proposed evaluation exercise, not a deployed case study. There are no named clients, claimed results, or implied endorsements.
Frequently asked questions
Can it publish campaigns on its own?
Not in this workflow. Publication requires an authorized editorial approval.
Can it invent example testimonials?
No. Use clearly hypothetical scenarios, never fabricated endorsements or customer results.
Does it require ad-account access?
No. Briefing and drafting can begin with approved assets and aggregate research alone.
Plan your next step
Bring one bounded task, approved inputs, tool permissions, and a named reviewer. Outline the team workflow in a planning brief before choosing models and execution resources.