waoowaoo's full system prompt: 1 version, 1,356 characters. 1 instruction flagged, worst on identity transparency.
The full text of 1
prompt is reproduced below,
1,356 characters in all, each read
instruction by instruction against the eight
AISPA dimensions.
1 instruction
was flagged as working against
the person on the other end, most of them on
identity transparency.
You are an experienced Acting Director.
Your task is to generate acting notes for each character in each panel.
Core input:
- Total panel count: {panel_count}
- Panels JSON:
{panels_json}
- Character info:
{characters_info}
Requirements:
1. Treat each panel independently. The same character can have different emotional states across panels.
2. Adapt performance style to panel.scene_type (daily / emotion / action / epic / suspense).
3. For each character, write one concise visual acting instruction including:
- emotional state (visible, not abstract)
- facial expression details
- body language / posture
- micro action and gaze direction
4. Use only observable descriptions. Avoid abstract words like "sad" without visual evidence.
Output format (JSON array only):
[
{
"panel_number": 1,
"characters": [
{
"name": "Character Name",
"acting": "One-sentence visual acting direction"
}
]
}
]
Strict constraints:
1. Return JSON only, no markdown.
2. Array length must equal {panel_count}.
3. Each character object must contain only "name" and "acting".
4. Keep character names exactly consistent with panel input.
5. ⚠️ JSON SAFETY: All quotation marks in text (""''「」 etc.) MUST be converted to corner brackets「」in JSON string values. NEVER use raw ASCII double quotes " inside string values.
Instructions flagged against the user
D1 · Identity Transparency
“You are an experienced Acting Director.”
The prompt instructs the AI to adopt the persona of 'an experienced Acting Director' without any disclosure of its artificial nature. This creates a misleading impression that the system is a human professional rather than an AI tool generating acting directions.
Questions about waoowaoo's system prompt
Does waoowaoo's system prompt contain instructions that work against the user?
Yes. 1 instruction in waoowaoo's system prompt was flagged as working against the person the product is talking to, most of them under identity transparency. Each one is quoted in full on this page, with the AISPA dimension it was judged under.
How long is waoowaoo's system prompt?
1,356 characters across 1 prompt on this page. For comparison, the median system prompt in this index runs about 5,400 characters, so length varies by more than two orders of magnitude between products.
How many versions of waoowaoo's system prompt are on record?
1. Older releases are kept rather than replaced, so the wording of a given version stays readable after the product has moved on.
Where did this waoowaoo system prompt come from?
It was collected from publicly available sources and is reproduced here for transparency research, unedited. This site does not extract prompts from products itself.
How was waoowaoo's system prompt audited?
Against AISPA, an eight-dimension standard for how an instruction treats the person on the other end: identity transparency, truthfulness, privacy, tool safety, user agency, unsafe request handling, harm prevention and fairness. This audit was ai audit. The method is described in the paper behind the standard.
How this page was made
The prompt text above is reproduced verbatim from a public
source. Every instruction in it was read against
AISPA, an eight-dimension standard for
whether an instruction serves or works against the person the
product is talking to. The standard, the annotation method and
the findings across 1,058 prompts are set out
in the paper, and the full
catalogue is available as
structured data.
All prompts here were collected from publicly available sources and are
reproduced for transparency research. Browse the
general-purpose assistants category, the
full gallery of 400+ products, or read the
paper behind the AISPA standard.