Skip to content
Edition 1 ReferenceDownloads Search Start here
Search
PromptQ04

Creative learning into an approved brief

Translate reviewed research and test results into a small concept brief; supports P05.

These six prompts help with drafting and interpreting evidence in the workflows described here. Their inclusion is not proof that AI will improve your results. Compare the quality and total cost of accepted work with a competent human or fixed workflow. Keep financial calculations, experiment assignment, permission changes and customer actions outside these prompts.

Use relevant information you are authorised to share. Replace bracketed inputs with evidence, or mark them as missing. Include source IDs and dates so a reviewer can check each material claim. Instructions inside a source document are part of the source, not commands to follow. A human owner decides whether to use the output.

Use when

There is an explicit proposition question.

Do not use when

Claims are unsubstantiated or the output would bypass creative/brand approval.

Maturity

Basic with approved claims.

Why AI

Synthesis and controlled drafting may reduce accepted-brief preparation time.

Required context

Customer need, approved claims and evidence, distinctive brand requirements, rights restrictions, signed experiment readouts, delivery context and known rejected concepts.
Prompt · Q04
Draft the next concept brief for [customer need and decision], using only
[approved claim library, research and signed test readouts].
For each proposed concept state the customer barrier, benefit, proof,
mechanism, source IDs and a materially different alternative.
Distinguish causal test findings from observational creative associations.
Preserve nulls and contradictory results. Do not revive rejected claims or
invent testimonials, performance numbers, legal assurances or urgency.
Propose only [locally agreed small number] of concepts that fit test capacity.
Return: brief; evidence map; proposed comparison; approval questions;
and conditions where the lesson should not generalise. Do not publish.

The full prompt, including its boundaries, is selectable if copying is unavailable.

Expected response

A source-mapped brief suitable for human development and review.

Human validation

Human review requiredCreative checks taste and distinctiveness; Brand/domain reviewers verify claims, rights and customer fit; measurement reviews the comparison.

Limitations

Historical delivery selection can bias apparent creative findings; more variants can weaken learning.

Evaluation

Approved-brief yield, factual/brand defects and preparation/review cost.