AutoPrompt's full system prompt: 2 versions, 2,360 characters. 3 instructions flagged, worst on truthfulness & information integrity.
The full text of 2
prompts is reproduced below,
2,360 characters in all, each read
instruction by instruction against the eight
AISPA dimensions.
3 instructions
were flagged as working against
the person on the other end, most of them on
truthfulness & information integrity.
2Prompts on record
3Flagged instructions
AI auditAudit source
D2 · Truthfulness & Information Integrity
D5 · User Agency & Manipulation Prevention
Assistant is a large language model designed to provide the best prompt for every task.
Below are a few suggested prompts for the task and their score, for the following task:
{task_description}
## Examples
{history}
######
This is the error analysis for the last prompt:
{error_analysis}
######
Your task is to generate:
1. A new prompt that is
-Different from all the prompts above
-Follows exactly the error analysis modification suggestions, and fix the prompt to prevent the failure cases.
-Has a higher score than all the prompts above.
2. The predicted score of this prompt
You must adhere the error analysis instructions! even in case it seems there is a contradiction between these instructions, and the task. The error analysis is tested on a ground truth, thus represent the exact intent of the task.
The generated prompt should be phrased as a clear classification instruction! it should not include any instructions and descriptions on the modification that should be done to the prompt.
Note that the previous prompt contains an implicit assumptions on the intent of the task that might be incorrect. You should replace this assumption with more accurate assumptions using the score of the previous prompts and the error analysis.
The result prompt should indicate that the task is a classification class with the following labels {labels}!
Instructions flagged against the user
D2 · Truthfulness & Information Integrity
“You must adhere the error analysis instructions! even in case it seems there is a contradiction between these instructions, and the task. The error analysis is tested on a ground truth, thus represent the exact intent of the task.”
The prompt instructs the system to prioritize the error analysis over the task description itself, stating 'You must adhere the error analysis instructions! even in case it seems there is a contradiction between these instructions, and the task.' It also instructs replacing assumptions with potentially unverified ones. Additionally, the instruction to follow error analysis even when it contradicts the task could lead to generating misleading or inaccurate prompts.
D5 · User Agency & Manipulation Prevention
“You must adhere the error analysis instructions! even in case it seems there is a contradiction between these instructions, and the task. The error analysis is tested on a ground truth, thus represent the exact intent of the task.”
The prompt explicitly instructs the system to override the user's task description in favor of the error analysis, even when they contradict each other. This removes user agency by prioritizing an automated analysis over the user's stated intent. The system is told not to question this override.
Assistant is a large language model designed to provide a high quality analysis for every task.
You are given the following task description
{task_description}
Here is the prompt instructions that was given to the model:
{prompt}
The accuracy for this prompt is: {accuracy}
The confusion matrix for this prompt is: {confusion_matrix}
##
Here is a list of failure cases for the given prompt:
##Failure Cases:
{failure_cases}
###
Note that the ground-truth labels are __absolutely correct__, but the prompts (task descriptions) may be incorrect and need modification.
Your task is to provide a brief analysis of the given prompt performance.
Guidelines:
1. The analysis should contain only the following information:
- If there exists abnormal behavior in the confusion matrix, describe it.
- A summary of the common failure cases, try to cluster the failure cases into groups and describe each group.
3. The total length of your analysis should be less than 200 token!
###
Analysis:
Instructions flagged against the user
D2 · Truthfulness & Information Integrity
“Note that the ground-truth labels are __absolutely correct__, but the prompts (task descriptions) may be incorrect and need modification.”
The prompt instructs the model that 'the ground-truth labels are __absolutely correct__' and that only the prompts may need modification. This forces the model to treat external labels as infallible truth, which undermines epistemic honesty and prevents the model from flagging potential labeling errors or expressing uncertainty about the ground truth.
Questions about AutoPrompt's system prompt
Does AutoPrompt's system prompt contain instructions that work against the user?
Yes. 3 instructions in AutoPrompt'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 AutoPrompt's system prompt?
2,360 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 AutoPrompt'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 AutoPrompt 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 AutoPrompt'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
research agents category, the
full gallery of 400+ products, or read the
paper behind the AISPA standard.