Developers & SaaS
Add an assistant to landing pages, apps, dashboards, docs, or admin consoles without building the entire AI runtime yourself.
- Embedded widget and Chat API
- Browser voice for support flows
- Tools that call product APIs
Use case hub
Use cases for assistants that speak, remember, and act.
Assistant Core fits production products where assistants need to support users, answer from private data, call workflows, speak in realtime, or run on hardware.
SaaS & developer platformEnterprise knowledge assistantSmart device & robot voice
4 teams
Developers, businesses, creators, and device teams
Many channels
Web, apps, widgets, voice, and hardware
Action-ready
Tool/MCP for workflows and private APIs
Product teams that fit
The use cases share one pattern: the assistant needs to understand private data, keep context, speak naturally, and take action through tools when needed.
Customer support
Support assistants answer from knowledge base content, move into voice, and call tools to look up status.
- RAG over support docs
- Conversation history and feedback
- Order or ticket lookup workflows
Internal knowledge
Businesses can build assistants for HR, sales, onboarding, training, or knowledge management on private data.
- Per-assistant permissions
- Private docs per team
- Memory for user context
Creator & expert assistant
Creators, experts, and educators can package knowledge into assistants for students, communities, customers, or followers.
- Expert-style prompting
- Knowledge base from private material
- Memory for personalization
Smart device & robot
Bring voice assistants to education robots, smart toys, kiosks, smart homes, or compact learning hardware.
- Activation code to bind devices
- MQTT gateway for hardware
- Cloud voice runtime to reduce device load
Workflow automation
Assistants can do more than answer: they can trigger actions in CRMs, ticketing, internal tools, or IoT systems.
- Controlled tool calling
- MCP servers for external systems
- RBAC-limited actions
Use case hub
How to choose a use case
A strong use case has a clear user, trusted data, a primary channel, and a bounded set of actions the assistant is allowed to take.
01
Identify user and channel
Choose web chat, browser voice, widget, app, or smart device as the first touchpoint.
02
Prepare trusted knowledge
Add documents, websites, FAQs, or business data to the knowledge base.
03
Define allowed actions
Connect tools or MCP for the things the assistant may do, with role-based limits.
04
Measure and expand
Track conversations, feedback, tool errors, LLM traces, and add more channels after the use case is clear.
Use case FAQ
Explore next
Which use case should we start with?
Start with a use case that has clear data and measurable value, such as knowledge-base support, internal FAQs, or a voice assistant for one specific device.
Do we need a separate assistant for every use case?
If the use case has different data, prompt, permissions, or domain, separate assistants keep isolation clean. If it is multiple channels for one experience, one assistant can be shared.
Can an assistant both chat and control devices?
Yes. The assistant can share prompt and knowledge on web while calling device tools or gateways to act on connected hardware.