draft-evidence-contentlisted

# Draft Evidence Content Create a useful answer while preserving which claims are observed, reported, inferred, recommended, or unknown. ## Inputs Require: - audience and question; - approved evidence IDs; - current authoritative sources for time-sensitive facts; - product claim policy; - public, internal, and restricted data boundaries; - CTA and publication approval boundaries. ## Workflow 1. State the reader question and desired next decision. 2. Build a claim ledger before drafting. 3. Link each material claim to evidence IDs or external sources. 4. Label inference and recommendation rather than presenting them as observed facts. 5. Write the direct answer before background detail. 6. Add limitations, counterevidence, and update dates where they change interpretation. 7. Remove or generalize restricted customer detail. 8. Create a review checklist for accuracy, privacy, brand, legal, and CTA. 9. Stop at a draft. Never publish without explicit approval. ## Boundaries - Let the model propose structure, explanation, examples, and CTA wording. - Use deterministic checks for claim IDs, evidence references, dates, links, and private-data patterns. - Require a person to approve product, legal, commercial, and public claims. - Do not invent testimonials, customer quotes, benchmarks, or product capabilities. - Do not convert internal evidence into public proof without permission. ## Outputs Create: - `content-brief.json` - `content-brief.md` - `draft.md` - `claim-ledger