Decision inputs
Facts that change the policy answer
The working material is approved specifications, prices and product images; the intended result is customer-facing product descriptions. Recording that pair prevents a vague approval from spreading to other uses.
- 1Task and owner
- Commerce editor wants to generate ecommerce product descriptions. The policy check should identify who can approve, correct or withdraw customer-facing product descriptions.
- 2Information involved
- Approved specifications, prices and product images. Look beyond pasted text: files, integrations and retrieval connections can expose the same material.
- 3Tool and account
- An approved company account. A personal login can handle information differently from the company-managed version of the same tool.
- 4Intended result
- The expected result is customer-facing product descriptions. Its destination matters: private working material creates a different consequence from a sent, published or automated result.
- 5Consequence if it is wrong
- The model may invent dimensions, compatibility or performance claims. Use this consequence to distinguish a routine request from one needing specialist approval.
- 6Human review
- catalogue owner should inspect, change, reject or stop the result. Their role should include checking source facts, correcting errors and refusing the proposed use.
Possible policy routes
The task name alone cannot decide it.
A published workplace policy can return different answers for the same task. These are the practical branches worth encoding.
A routine policy route may be possible
The least restrictive path starts only after the exact account is approved, only the minimum internal information is used, customer-facing product descriptions remains within the stated purpose, and catalogue owner reviews it before use.
Approval may be required
The request moves beyond routine handling when the account or data handling is uncertain, the model may invent dimensions, compatibility or performance claims, or customer-facing product descriptions reaches people or systems beyond the requester’s authority.
The request may need to stop or change
Do not continue unchanged when restricted information would enter an unapproved service, the output would act before catalogue owner can intervene, or validate every specification and remove claims absent from the source catalogue cannot be maintained. Consider less information, a controlled account or a non-AI process.
Request checklist
Questions to ask before using the tool
- 01
Has the company approved this account configuration for generate ecommerce product descriptions, rather than only approving the product?
- 02
Can any personal, sensitive, confidential or secret part of approved specifications, prices and product images be removed?
- 03
Who receives customer-facing product descriptions, and what will they do with it?
- 04
Can catalogue owner inspect the complete result and its source before reliance?
- 05
Is this genuinely one request, or will repeated use turn it into an embedded process?
Worked request
What the employee should submit
This example supplies decision facts without pasting the underlying material into the approval record.
- requester
- commerce editor
- task
- Use AI to generate ecommerce product descriptions.
- information
- approved specifications, prices and product images
- tool
- An approved company account
- frequency
- Recurring work
- region
- Where the work and affected people are located
- purpose
- Draft or analyse
- impact
- External publication
- review
- Complete human review
- owner
- catalogue owner
Useful safeguards
Controls that fit this request
- ✓
Validate every specification and remove claims absent from the source catalogue
- ✓
Reduce approved specifications, prices and product images to the smallest useful extract and remove fields unrelated to customer-facing product descriptions.
- ✓
Write the boundary around customer-facing product descriptions clearly so later users do not expand the approval by assumption.
- ✓
Make the final route reproducible from the recorded facts, safeguards and policy version.
Questions people ask
About this AI use
Is using AI to generate ecommerce product descriptions automatically allowed?
The task name cannot settle the answer. Apply the company’s published rules to approved specifications, prices and product images, the exact account, customer-facing product descriptions, its audience and the proposed review.
What belongs in the employee’s request?
Describe customer-facing product descriptions, identify approved specifications, prices and product images, name the exact tool and account, explain who will receive or rely on the output, and state how catalogue owner will review it.
What should remain after the decision?
Make the final route reproducible from the recorded facts, safeguards and policy version. A classification and controlled reference may be enough when copying approved specifications, prices and product images would create unnecessary risk.