Support customers in their own language
English docs, answers in the customer's language.
Your docs are in English but your customers are not. Translating and maintaining docs in five languages is unaffordable, so non-English customers file more tickets, get slower answers, and churn at higher rates.
With a customization's Language setting, Kelu answers in the language of the question while retrieving from your English knowledge base, with citations back to the original docs. Workspace analytics break down questions by language so you can see which markets are asking what — and prioritize translation only where data says it matters.
How it works
- 1
Keep writing docs in English (or your primary language) — no translation project required.
- 2
Kelu retrieves from your knowledge base regardless of the question's language.
- 3
Answers can be generated in the language of the question (set in a customization's Language field), with citations to the original docs.
- 4
Language analytics show which markets ask what, so you translate only where data says to.
What you get
- Serve non-English customers without maintaining translated documentation.
- Give every language the same instant, cited answers.
- Prioritize translation investment with per-language question analytics.
- Reduce the ticket premium your non-English customers currently pay.
Features that make it work
Got questions?
Frequently asked questions
Do I need to translate my docs first?
No. The assistant retrieves from your existing docs and, with a customization's Language setting, answers in the language of the question. Citations link to the original pages so users can still verify the source.
Which languages are supported?
Answering follows the language of the question once a customization's Language field says so — the underlying LLM handles the major world languages users actually ask in. Workspace analytics break down question volume by language so you can see coverage in practice.
How do I know which languages my customers use?
The workspace analytics overview includes top languages across questions, alongside questions per week and top sources — a data-driven view of where multilingual demand is concentrated.
How long does setup take?
Most teams are live the same day. You connect a source — a docs URL, GitHub repo, Notion workspace, or a file upload — and Kelu crawls, normalizes, chunks, and embeds the content automatically. The website widget is a single script tag, and the Slack bot installs in a few clicks. There is no model to fine-tune and no infrastructure to run.
Are answers backed by citations?
Yes. Every answer from your docs includes a structured citations list with the URL, title, and excerpt of each source used, and the answer text cites sources inline. Users can click through to verify any claim against the original document — which is what makes the answers trustworthy enough for support, sales, and internal use.
Is my content used to train AI models?
No. Your indexed content, embeddings, and conversations are isolated to your workspace and are only used to answer your own questions. Content is never shared across customers, and data is encrypted at rest and in transit. Enterprise plans add OIDC/SAML SSO, a widget without Kelu branding, and a custom SLA.
Which knowledge sources can I connect?
24 source types: websites, GitHub (docs files, source code, issues, pull requests, discussions), Notion, Confluence, Google Drive, OneDrive, Zendesk (Help Center and solved tickets), Jira, Jira Service Management, Linear, Salesforce Knowledge articles, Salesforce Cases, Discourse, Stack Overflow for Teams, YouTube, OpenAPI specs, S3, curated Q&A, and direct file uploads (PDF, DOCX, XLSX, CSV, Markdown, TXT, HTML). Sources sync on a schedule, and GitHub sources can re-index automatically via webhook on every push.
What happens when the AI is not confident in an answer?
Answers are grounded in your sources. When they do not cover a question, Kelu returns a transparent, configurable fallback — typically pointing users to your support channel — instead of guessing. Those unanswered questions are logged in knowledge gap analytics so you can close the gap in your docs.
Ready to support customers in their own language?
Connect your knowledge sources and see cited AI answers in minutes — free, no credit card required.
Free to start · No credit card required