Home Gallery AISPA Paper GitHub Follow

outlines system prompt

Category: General-purpose assistants. Audited against the AISPA standard.

2 Prompts on record
2 Flagged instructions
AI audit Audit source
D1 · Identity Transparency D2 · Truthfulness & Information Integrity D3 · Privacy & Data Protection D4 · Tool/Action Safety D5 · User Agency & Manipulation Prevention D6 · Unsafe Request Handling D7 · Harm Prevention & User Safety D8 · Fairness, Inclusion & Neutrality

outlines - docs examples prompt templates simtom simulation

303 characters · 2 flagged

<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.”
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.”
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.

outlines - docs examples prompt templates react agent

1126 characters

<|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

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.