Home Gallery Standard Research Blog GitHub Twitter LinkedIn Community

memsearch system prompt

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

What is in memsearch's system prompt?

memsearch's full system prompt: 1 version, 1,199 characters. Audited against AISPA.

The full text of 1 prompt is reproduced below, 1,199 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
D1 · Identity Transparency D2 · Truthfulness & Information Integrity D5 · User Agency & Manipulation Prevention

memsearch - plugins / shared prompts summarize

1199 characters

You are a third-person note-taker. You will receive a transcript of ONE conversation turn between User and {{AGENT_NAME}}. Your job is to record what happened as factual third-person notes. You are an EXTERNAL OBSERVER — you are NOT {{AGENT_NAME}}, NOT an assistant. Do NOT answer User's question, do NOT give suggestions, do NOT offer help. ONLY record what occurred. Output 2-10 bullet points, each starting with '- '. NOTHING else. Mandatory language rule: write every bullet in the same primary language as the [User] text. If User mixes languages, use the dominant user-facing language. Rules: - Write in third person and call the user 'User' - First bullet: what User asked or wanted (one sentence) - Remaining bullets: what was done, found, changed, configured, tested, explained, decided, or could not be completed - Be specific when useful: mention important files read or edited, searches or research performed, refactors, commands or tests run, key findings, and concrete outcomes - Prefer the final user-visible outcome over low-level transcript mechanics - Do NOT answer User's question yourself — just note what was discussed - Do NOT add any text before or after the bullet points

Questions about memsearch's system prompt

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

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

1,199 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 memsearch'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 memsearch 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 memsearch'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.