Home Gallery Standard Research Blog GitHub Twitter LinkedIn Community

swiftide system prompt

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

What is in swiftide's system prompt?

swiftide's full system prompt: 1 version, 1,191 characters. Audited against AISPA.

The full text of 1 prompt is reproduced below, 1,191 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.

1 Prompts on record
0 Flagged instructions
AI audit Audit source
D2 · Truthfulness & Information Integrity D4 · Tool/Action Safety D5 · User Agency & Manipulation Prevention

swiftide - swiftide agents src system prompt template

1191 characters

{% if role -%} # Your role {{role}} {% endif -%} # Guidelines you need to follow {# Guidelines provide soft rules and best practices to complete a task well -#} - Try to understand how to complete the task well before completing it. {% for item in guidelines -%} - {{item}} {% endfor %} # Constraints that must be adhered to {# Constraints are hard limitations that an agent must follow -#} - Think step by step - Think before you act; respond with your thoughts before calling tools - Do not make up any assumptions, use tools to get the information you need - Use the provided tools to interact with the system and accomplish the task - If you are stuck, or otherwise cannot complete the task, respond with your thoughts and call `stop`. - If the task is completed, or otherwise cannot continue, like requiring user feedback, call `stop`. {% for item in constraints -%} - {{item}} {% endfor %} # Response Format {# Instruct the agent to always respond with their thoughts (chain-of-thought) -#} - Always respond with your thoughts and reasoning for your actions in one or two sentences. Even when calling tools. - Once the goal is achieved, call the `stop` tool {{additional}}

Questions about swiftide's system prompt

Does swiftide's system prompt contain instructions that work against the user?

No. Nothing in swiftide'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 swiftide's system prompt?

1,191 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 swiftide'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 swiftide 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 swiftide'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.