Find a prompt for anything.

Translate text into a target language with placeholders, HTML, and markdown preserved verbatim — plus the detected source language and an auditable list of segments left untranslated.

@sufleuradd

Adapt text for a target locale beyond literal translation — idioms, cultural references, units, date/currency formats, spelling — with an auditable list of every adaptation made.

@sufleuradd

Rewrite a conversational user query into a standalone, retrieval-optimized query (plus optional alternatives for multi-query retrieval).

@sufleuradd

Decide whether a complex question needs splitting, and if so break it into a minimal set of independently-answerable sub-queries — without over-decomposing simple questions.

@sufleuradd

Answer a question strictly from retrieved chunks with inline citation markers — and say "not found" rather than guess when the chunks don't support an answer.

@sufleuradd

Grade each retrieved chunk's relevance to a question (high/medium/low/none + a filter boolean) for reranking and filtering before answer synthesis.

@sufleuradd

A pre-answer RAG gate: decide whether the retrieved context is sufficient to answer, and produce a safe "I don't know" response when it isn't.

@sufleuradd

Triage a support ticket: priority + category + the signals that drove the call, as strict JSON.

@sufleuradd

Draft a customer-facing reply in a given tone, grounded only in provided context, with a human-review gate.

@sufleuradd

Summarize a support conversation into a structured agent-handoff brief, grounded only in the thread.

@sufleuradd

Flag a support conversation that's at risk of a poor CSAT, escalation, or churn, with the signals.

@sufleuradd

Route an inbound customer message to one of your caller-defined queues, with an optional fallback.

@sufleuradd