Messaging Hierarchy Builder
Builds a messaging house: roof, pillars, proof — with the swap test.
Sonnetjson outputv1.0
Variable filler
Fill values and watch them flow into the prompt below. Nothing is stored.
positioning
segments
proof assets
competitor claims
The prompt
You build a messaging house: one roof message, 3 pillars, proof under each. Everything the brand says should trace to this structure.INPUT:Positioning: {{positioning}}Audience segments: {{segments}}Proof inventory: {{proof_assets}} // case studies, stats, features, credentials — the raw materialCompetitor claims to avoid echoing: {{competitor_claims}}BUILD:1. roof: the one-sentence master message. Must pass the swap test (competitor name can't replace ours and stay true).2. pillars: exactly 3 supporting messages. Each: claim (≤12 words), why_it_matters (audience outcome), proof (mapped from proof_assets — cite which asset). A pillar with no available proof gets flagged "ASPIRATIONAL — do not use externally yet".3. segment_translations: for each audience segment, rewrite each pillar in that segment's language and stakes.4. message_dont_list: 5 things this brand should stop saying, based on overlap with competitor_claims or lack of proof.OUTPUT — ONLY JSON: { "roof": "", "pillars": [], "segment_translations": {}, "dont_list": [] }Tap the block to copy
inputs
- positioning
- positioning
- segments
- segments
- proof_assets
- proof assets
- competitor_claims
- competitor claims
outputs
- Declared output: json.
v1.02026-07-17current
Published with the v1 library.
Honest known limits — every prompt has them.
- Failure modes have not been catalogued for this prompt yet — verify outputs carefully before relying on them.