A ready-to-use system prompt for a multilingual support agent that replies in the visitor's language while staying grounded in your content and citing the source — so global customers get accurate help without you translating every page. Copy it, fill the brackets, and paste it into your agent's instructions.
What this agent does
Your content may be in one language, but your visitors aren't. This prompt makes the agent detect the visitor's language and answer in it, while drawing the facts strictly from your indexed content and citing the source. That keeps answers accurate across languages — the agent translates its reply, not your policies, so it can't drift from what your documentation actually says. When the answer isn't in your content, it says so in the visitor's language and offers to escalate.
The prompt
You are the support assistant for [Product]. Detect the visitor's
language and reply in it. Base every answer only on the provided context
drawn from [Product]'s documentation, regardless of the content's
language, and cite the source. If the answer is not in the context, say
so in the visitor's language and offer to capture their email or
escalate. Never invent facts. Keep replies clear and concise.
How to use it
Replace [Product] with your product name, index your docs, and paste the prompt into your agent's instructions — no per-language content needed. The analytics dashboard shows what's asked across languages. See the education platforms use case for a multilingual example, then start free.
Why grounding beats a bare prompt
A prompt alone doesn't make a multilingual agent reliable — grounding does. Pasted into a generic chatbot, these instructions still let the model answer from its general knowledge and invent details. In AIML.chat the same prompt sits on a retrieval layer that feeds the agent only the content you indexed, so "answer only from the provided context" is enforced by the system rather than merely requested. Every claim links back to a page you control, and the analytics record what people ask so you can refine both the prompt and the content behind it. That pairing — your instructions plus your own grounded content — is what turns this template into a dependable agent.
Do I need to translate my docs?+
No — the agent answers in the visitor's language while sourcing facts from your existing content in whatever language it's written.
Will translating cause inaccurate answers?+
The prompt keeps facts grounded in your indexed content and cited, so the agent translates its reply, not your underlying policy.
Is there a free plan?+
Yes — 100 messages a month and one website on the free tier. See pricing for higher limits.