A separate AI agent for each part of your business
Each question is classified and sent to the matching agent. Every agent has its own documents, instructions and the conversation history in view.
Example agents
Example agents. You write the instructions and upload the documents for your own.
Alex, support agent
Customer support
Answers questions about orders, tracking, warranty claims and returns from your policy documents, and walks customers through troubleshooting steps.
Specialties
Reads from
Routes on
refundreturnordershippingtrackingcancelwarrantybrokeninvoiceJordan, sales agent
Plans and pricing
Answers pricing questions from your plan documents, compares plans for the customer, and hands buyers who want to talk to a person over to your sales team.
Specialties
Reads from
Routes on
pricepricingcostbuypurchaseupgradequoteplanTaylor, product agent
Features and comparisons
Explains what your product does, suggests features that fit the customer’s question, and points to the case studies you have published.
Specialties
Reads from
Routes on
comparefeatureintegrationscalecase studyversusDevin, developer agent
API and webhook questions
Helps engineers with your REST API, WebSocket events, webhook signature checks and embedding setup, using your API documentation.
Specialties
Reads from
Routes on
apiwebhooksdkcurlhmactokenendpointdebugSam, privacy agent
Privacy policy questions
Answers questions about your privacy policy, data retention and security practices from the documents you upload. Anything it cannot answer goes to your team.
Specialties
Reads from
Routes on
privacysecurityencryptionretentiondeletepersonal dataYour own agent
Your instructions, your documents
Set up an agent for your own workflow: write its instructions, choose the keywords that route to it, add guardrails, and give it its own documents.
Specialties
Routes on
custommy agentcreateHow a question is routed
From the website widget (WebSocket) or WhatsApp (Meta Cloud API)
Decides if it is about a refund, technical support, billing or sales
The support, sales or product agent takes the conversation
Finds matching passages and checks the confidence score
The answer streams to the customer with its sources
Sample data
Suggested routing rule
Sample: return questions keep coming in, so order tracking and refund tools are linked to the support agent.
// Sample routing rule
router.registerIntent({
intent: "order_inquiry",
targetAgent: "support_specialist",
tools: ["order_tracking", "refund_calculator"],
groundingScoreMin: 0.85
});Customers can get a full refund within 30 days of receiving their order, with no restocking fee.
Annual billing costs 20% less than paying monthly, on every plan. There are no per-resolution fees.
How a question reaches the right agent
Each question is classified and sent to the matching agent. Anything the agents can't answer goes to your team.
Agent routing diagram
Topological State Transition & Intent Scoring
"Where is my order #8492 and can I initiate a refund?"
Support Specialist
Active Memory Bank LoadedState committed to LangGraph route node. Agent responds with strictly grounded vector documentation.
- 01
Intent and topic match
Each question is checked against your department classifiers: returns and orders go to support, pricing questions go to sales.
- 02
Quick path for greetings
Greetings and simple questions get a short reply without a full document search.
- 03
Matching agent takes over
The conversation goes to the agent with the right instructions and documents for that topic.
- 04
Human fallback
If the agent is not confident in an answer, or the question needs a person, the chat moves to your agent inbox.
Set up your first agent
Paste your website link or upload your docs, then copy one embed snippet.