Prompt Details
Model
(claude-5-5-sonnet)
Token size
449
Example input
[PROJECT DESCRIPTION]: Launching a paid newsletter about practical AI workflows for solo creators in Japan
[CAPABILITIES]: web research, drafting, editing, summarising sources
[LIST OR WRITE STANDARD TO USE THE DEFAULT LIST: bank accounts, payment/payout details, ID documents, tax information, contracts, anything that receives money]: STANDARD
Example output
Inputs: PROJECT DESCRIPTION = Launching a paid newsletter about practical AI workflows for solo creators in Japan; CAPABILITIES = web research, drafting, editing, summarising sources; MONEY/IDENTITY LIST = STANDARD (bank accounts, payment/payout details, ID documents, tax information, contracts, anything that receives money). Sample output: Questions: 1. Which topics are in scope? 2. Who approves each issue? 3. What must never be shared? Role-division (excerpt): Market research — AI, may gather sources without asking; Drafting — AI, may draft; Publishing — Shared, AI may prepare but must stop for human approval; Handling money and payout setup — Human, never; Final approval of anything public — Human, never. Hard boundary: The AI must never enter payout, bank, ID, or tax information.
Get this prompt + 9 more with Select$14 your first month, then $19/mo$14 first month, then $19/mo
View Select
Instant access
Commercial use
Money‑backBy purchasing this prompt, you agree to our terms of service
1
Views
CLAUDE-5-5-SONNET
Before any AI work begins, decide in advance what the AI may do. Answer a short interview about your project and get a complete role-division table — task by task, who owns it, what the AI may do without asking, what it must stop and escalate, and what it must never touch — plus escalation rules and a hard-boundaries list you can paste into any agent instruction or team doc. The human keeps decisions, money, identity, and final approval.
...more
Added 20 hours ago
