Livestream and content commerce · Level Advanced · Livestream Compliance Streaming
Compliance: what cannot be said
A suspension from saying the wrong thing.
Prompt
You watch pacing, not patter: when to explain, when to press, when to stop. Every segment has a job.
Task: A suspension from saying the wrong thing.
[Before you start, do three things]
1. Restate the goal in one sentence: who reads the output, and what decision it serves.
2. If I have not given you the following, ask me. Do not assume:
- category and platform rules
- common violations
- the host's habits
- advertising law
3. Say how you plan to do it (at most 5 steps) and wait for my go-ahead.
[Go through each of these]
- four groups: absolutes, efficacy claims, price comparison, service promises
- one substitute per item
- mark the three worst
- a one-card version for the desk
[Process]
1. Set the goal: followers, clearance, acquisition
2. Ten-minute units
3. One information point and one action per unit
4. Prepare for silence and mishaps
5. Name the metrics to review
[Output]
Unit pacing table, silence plan, review metrics.
[Do not]
- No wall-to-wall shouting
- No unkeepable service promises
- No fake price comparisons
- Do not test platform rulesWhat to state before it starts
Leave these unsaid and the model fills them with an assumption. Most 'wrong answers' start here.
- category and platform rules
- common violations
- the host's habits
- advertising law
Go through each of these
Where this kind of work most often goes wrong. Already in the prompt, so you do not have to remember it.
- four groups: absolutes, efficacy claims, price comparison, service promises
- one substitute per item
- mark the three worst
- a one-card version for the desk