Content
One Post a Week Experiment
Change one variable per week and let useful audience behavior decide.
Use when
You want a repeatable content format and need audience evidence.
Cadence
Weekly for six weeks
Verification
Winner is supported by comparable replies, saves, and questions, not just likes.
Advanced specStructured loop spec
| Field | Value |
|---|---|
| Name | One Post a Week Experiment |
| Category | Content |
| Trigger | Weekly for six weeks |
| Objective | Change one variable per week and let useful audience behavior decide. |
| Allowed inputs | Relevant files, source notes, logs, tests, screenshots, metrics, or task state for this loop |
| Allowed actions | Define the exact scope, source of truth, and approval boundary.; Inspect current state and rank the highest-risk gap.; Make one small, reversible improvement.; Run the stated verification and record evidence.; Stop on success, budget, no progress, or approval required. |
| Verification | Winner is supported by comparable replies, saves, and questions, not just likes. |
| Stop condition | Stop when the verifier passes, the budget is exhausted, no progress is made, a blocker appears, or approval is required. |
| Budget | Set a time, turn, token, retry, file, or dollar cap before running the loop. |
| Approval boundary | Human approval required before publishing, sending, deleting, spending, changing accounts, touching production, or making reputational/legal/financial commitments. |
| Safe output | Draft, report, checklist, table, or approval-gated recommendation |
| Works with | Claude, ChatGPT, Gemini, any tool-using AI assistant |
RunbookSteps
- Define the exact scope, source of truth, and approval boundary.
- Inspect current state and rank the highest-risk gap.
- Make one small, reversible improvement.
- Run the stated verification and record evidence.
- Stop on success, budget, no progress, or approval required.
Copy promptPrompt
Run the One Post a Week Experiment loop. Use it when You want a repeatable content format and need audience evidence. Work in bounded iterations: inspect current state, choose the highest-risk gap, make one reversible improvement, verify it, and record evidence. Stop when Winner is supported by comparable replies, saves, and questions, not just likes. or when blocked, budget exhausted, or approval is required.