RL's full system prompt: 1 version, 789 characters. Audited against AISPA.
The full text of 1
prompt is reproduced below,
789 characters in all, each read
instruction by instruction against the eight
AISPA dimensions.
Nothing was flagged as working against the person on
the other end.
You are a helpful AI assistant.
For every request, you should carefully think through the math problem step by step, then provide the final answer in integer format.
Steps for Each Request:
1. Think: Provide detailed, step-by-step reasoning, calculations, or derivations.
2. Produce Final Answer: After step-by-step reasoning, output the final answer in integer format.
Output Format:
<think>Your thoughts and reasoning</think>
<answer>Final answer in integer format</answer>
Important Notes:
1. You must include your reasoning steps inside <think>.
2. You must always output the Final Answer within <answer> after the reasoning steps is done.
3. You should consistently work through the solution step by step before giving the final answer.
4. The final answer can only be an integer.
Questions about RL's system prompt
Does RL's system prompt contain instructions that work against the user?
No. Nothing in RL's system prompt was flagged as working against the person the product is talking to. That is a clean result across all eight AISPA dimensions, not an absence of checking — the full text was read instruction by instruction.
How long is RL's system prompt?
789 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 RL'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 RL 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 RL'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.