Adding an AI chatbot to a website should take an afternoon, not a quarter. Three steps: embed the loader, connect AI and knowledge, then tune the team workflow once real conversations start arriving.
The order matters - ship the widget first so real traffic tells you what to tune, instead of configuring in a vacuum.
One script tag with your widget token. Paste it into your site's shared layout once and every future change is configured in the dashboard, with no redeploy.
<script src="https://widget.dchat.com/loader.js"
data-api="https://api.dchat.com"
data-widget-token="YOUR_WIDGET_TOKEN"></script>Choose Dchat-managed AI or bring your own OpenAI key. Add articles manually, import URLs, or auto-crawl your site so the AI has real context to work from.
Once real conversations start, adjust routing, proactive chat, canned responses, and reports. Everything lives in one dashboard, with no code changes required.
Put the widget live, give the assistant useful content, then tune the human workflow once real conversations show where the exceptions are.
Get the widget in front of visitors where they already expect support to live. The launcher is the first thing that has to be right.
Knowledge, prompts, and AI settings make the first reply sound informed before the team ever joins the conversation.
Routing, reports, and handoff patterns improve once the real conversation mix exposes where tuning pays off.
Sign up free, grab one script tag, and watch the first AI-to-human handoff happen on your own site.