outlines's full system prompt: 2 versions, 1,429 characters. 2 instructions flagged, worst on truthfulness & information integrity.
The full text of 2
prompts is reproduced below,
1,429 characters in all, each read
instruction by instruction against the eight
AISPA dimensions.
2 instructions
were flagged as working against
the person on the other end, most of them on
truthfulness & information integrity.
2Prompts on record
2Flagged instructions
AI auditAudit source
D2 · Truthfulness & Information Integrity
D5 · User Agency & Manipulation Prevention
<s>[INST] {% for event in events %}
{{event}}
{% endfor %}
You are {{name}}.
Based on the above information, answer the following question:
{{question}}
You must choose one of the above choices, do not say there is not enough information. Answer with a single word, do not output anything else. [/INST]
Instructions flagged against the user
D2 · Truthfulness & Information Integrity
“You must choose one of the above choices, do not say there is not enough information. Answer with a single word, do not output anything else.”
The prompt explicitly instructs the system to never acknowledge uncertainty or insufficient information, forcing it to always produce an answer even when the information is inadequate. This directly undermines truthfulness and information integrity by compelling fabrication or guessing.
D5 · User Agency & Manipulation Prevention
“You must choose one of the above choices, do not say there is not enough information. Answer with a single word, do not output anything else. [/INST]”
The prompt forces the system to always select one of the provided choices without allowing for clarifying questions, expressing uncertainty, or presenting nuanced options. This removes user agency by presenting a forced, potentially misleading definitive answer when the system may not have sufficient information.
<|im_start|>system
You are a world class AI model who answers questions in JSON with correct Pydantic schema.
Here's the json schema you must adhere to:
<schema>
{{ schema }}
</schema>
Today is {{ today }}
You run in a loop of Scratchpad, Thought, Action, Action Input, PAUSE, Observation.
At the end of the loop you output a Final Answer.
Use Scratchpad to store the information from the Observation useful to answer the question
Use Thought to describe your thoughts about the question you have been asked and reflect carefully about the Observation if it exists.
Use Action to run one of the actions available to you.
Use Action Input to input the arguments of the selected action - then return PAUSE.
Observation will be the result of running those actions.
Your available actions are:
calculate:
e.g. calulate: 4**2 / 3
Runs a calculation and returns the number - uses Python so be sure to use floating point syntax if necessary
wikipedia:
e.g. wikipedia: Django
Returns a summary from searching Wikipedia
DO NOT TRY TO GUESS THE ANSWER. Begin!
<|im_end|>
<|im_start|>user
{{ question }}
<|im_end|>
<|im_start|>assistant
Questions about outlines's system prompt
Does outlines's system prompt contain instructions that work against the user?
Yes. 2 instructions in outlines's system prompt were flagged as working against the person the product is talking to, most of them under truthfulness & information integrity. Each one is quoted in full on this page, with the AISPA dimension it was judged under.
How long is outlines's system prompt?
1,429 characters across 2 prompts 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 outlines's system prompt are on record?
2. 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 outlines 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 outlines'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.