Turn product questions into purchases and support questions into resolutions. One brand-trained AI agent helps shoppers buy, helps customers get answers, and brings your team in with full context when a human is needed.
See how two beauty brands use StateSet as a customer-facing commerce agent—adapted to each brand, catalog, customer journey, and support model.
Every deployment carries the brand voice from first question through product discovery, post-purchase help, and human escalation.
Shopping + support
Meet Dottie, their StateSet commerce agent.
A brand-trained beauty advisor that helps shoppers discover products, understand routines, manage orders, and move into support flows.
Product + customer care
Meet Beauty Assistant, their StateSet commerce agent.
A product and care assistant that answers brand questions, supports product discovery, and gives customers a conversational path to help.
One agent, two jobs
StateSet understands the conversation, uses the right commerce context, and changes modes without sending the customer to another bot or channel.
Guide discovery with product knowledge, concern-based recommendations, comparison, education, and rich product cards that keep the path to purchase moving.
Answer policy questions, surface order context, guide returns and exchanges, manage subscriptions, and escalate sensitive or complex conversations.
StateSet Chat Desk
Every live thread arrives in one operator workspace with transcript, intent, customer context, priority, ownership, and a clear path to take over.
Chat Desk
Live commerce operations
Shade exchange
YSE Beauty · Product page · Maya R.
Reply as a human or add an internal note…
The StateSet iCommerce Chat Engine combines brand knowledge, product context, customer context, commerce actions, and human support in one continuous conversation.
Token-by-token SSE responses with optional thinking states, tool calls, tool results, and citations rendered inline.
Render products, buttons, forms, and cart actions directly in the transcript instead of bouncing customers into a separate flow.
Built-in tabs for orders, products, subscriptions, returns, and exchanges keep self-service operations inside the widget.
Thread CRUD helpers, payload builders, response parsers, and imperative open or close controls let you wire the widget into any stack.
Run against OpenAI, Anthropic, or Gemini backends with the same route contract and the same front-end surface.
Track message events, widget toggles, outcomes, and conversation exports without forking the component.
Ready for brand, security, and support teams
The StateSet iCommerce Chat Engine was built as a product surface, not a prototype. It includes the controls you need before putting AI in front of real customers.
Sign instances with widget tokens before they can talk to your backend.
Restrict where the widget can be embedded across brand and partner properties.
Nonce-aware scripts and consent gates keep the widget aligned with stricter policies.
Keyboard support, ARIA labels, focus handling, and live-region semantics are built in.
Locale packs, translation overrides, and automatic RTL handling are available at runtime.
Track widget_loaded, chat_toggle, message_sent, outcomes, and feedback events.
Persist sessions and thread IDs so customers can resume without starting over.
Escalate to a human while preserving context and keeping the transcript intact.
1<script src="https://unpkg.com/react@18/umd/react.production.min.js"></script>2<script src="https://unpkg.com/react-dom@18/umd/react-dom.production.min.js"></script>3<link rel="stylesheet" href="https://stateset.com/chat-widget.css" />4<script src="https://stateset.com/chat-widget.bundle.js"></script>5<script>6 const api = window.ChatWidget.mount({7 container: document.getElementById('chat'),8 props: {9 companyName: 'Your Brand',10 agentName: 'Aria',11 messageEndpoint: '/api/chat',12 threadCreateEndpoint: '/api/threads',13 threadEndpoint: '/api/threads',14 enableStreaming: true,15 enableToolVisualization: true,16 enableRichMessages: true,17 enableSourceCitations: true18 }19 });20</script>Mount it once. Wire it to your stack.
The StateSet iCommerce Chat Engine ships as a UMD bundle with a small imperative API, sample servers, and request builders that let you reshape thread and message traffic without forking the UI.
Questions teams ask before rollout
The implementation surface is flexible, but the operating model is straightforward.
Give shoppers answers, actions, and escalation paths in one place instead of sending them through email, ticket forms, and dead-end chatbots.