Chat widget

A chat widget you
don't have to build.

One script tag puts a configured agent on your site. It answers from your documents, calls your systems, and streams replies as they are written.

Start free trialExplore a live demo

14 days free · No credit card · Bring your own model keys

Installing it

One script tag. Any stack.

If your site can render a script tag, it can run the widget. Nothing to add to your backend, no plugin for someone to keep updated.

WordPress

Paste the snippet into your theme footer once. It appears on every page the theme renders.

WWordPress

Shopify

Add it to the theme layout and it follows shoppers through product, cart and checkout pages.

SShopify

Webflow

Drop the snippet into project settings, publish, and it is live on the domain minutes later.

WWebflow

Anything else

Plain HTML, Next.js, Rails, a static site generator. The widget only ever needs one script tag.

index.html
<script src="sentientone.ai/widget.js"
        data-agent="support" />

What it can do

It answers from your business. Not from the web.

The widget is a front end for the agent you already configured — same knowledge, same tools, same traces in the dashboard afterwards.

Reads your documents

Refund windows, delivery times, warranty terms — quoted from your PDF, with the page it came from.

Refunds are processed within 30 days.policy.pdf · p.12

Calls your systems

Connect an MCP server and it looks up the real order, rather than explaining how someone could look it up.

Where's order #1234?
GET /orders/1234
Shipped today, arriving Friday.

Streams replies

Tokens appear as they are generated, so a long answer never reads as a frozen page.

We refund within 30 days for any

Stays current

Point it at your site and it re-crawls on a schedule. A new pricing page means new answers, not a stale script.

yoursite.com
/pricing
/features
/docscrawling…
/blog

What teams say

“Every time you want to add AI to your app, you end up writing a ton of code — managing API keys, handling conversation history, engineering prompts, counting tokens. And then six months later a better model comes out and you have to refactor everything. SentientOne just removes all of that.”
Daniel Marsh · CTO

Pricing

Plans for every team size.
Fourteen-day trial, cancel anytime.

Starter

$19/month

For developers putting the first AI feature into a product.

Start free trial

1 agent · 10k requests/mo

  • 1 MCP server per agent
  • Knowledge — 100 credits †
  • Embeddable chat widget
  • Analytics · 30 requests/min
  • 14-day logs & chat history
  • Community support
  • Streamable HTTP endpoint
  • AI Workspace (team chat)

Pro

Most popular
$49/month

For teams running AI in production and watching the numbers.

Start free trial

5 agents · 50k requests/mo

  • 2 MCP servers per agent
  • Knowledge — 300 credits †
  • Full tracing, cost & token analytics
  • Streamable HTTP endpoint
  • AI Workspace (team chat)
  • Extra seats at $9/member
  • 90-day logs · 50 requests/min
  • Email support, 48h response

Enterprise

Custom

For organisations with compliance, scale or data-residency rules.

Talk to us

Unlimited agents & requests

  • Unlimited MCP servers & knowledge
  • Self-hosted / single-tenant option
  • Custom rate limits & log retention
  • SSO and organisational support
  • Security review assistance
  • Dedicated SLA & onboarding

Prices in USD. Every plan includes bring-your-own model keys, the agent chat interface, and a 14-day trial. † 1 credit = 1 FAQ · 5 credits = 1 document.

Get started

Answer visitors at 2am. Without hiring for it.

Configure an agent, attach your documents, paste the snippet. The first real conversation can happen this afternoon.

  • Create an agent
  • Add documents and FAQs
  • Paste the snippet
  • Read the transcripts
Start free trialSee pricing

14 days free · No credit card required