Quickstart

Create your first AI agent in a few minutes.

1. Create an account

Sign up at /app. The Free plan requires no credit card. Once signed in, you land on the dashboard.

2. Create a project

Projects group all your resources (agents, knowledge base, chat sessions). Create one from the dashboard or via the API:

bash
curl -X POST "<your-server>/api/member/projects" \
  -H "Authorization: Bearer $MEMBER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"name":"My Store","website":"https://store.example","industry":"e-commerce"}'

3. Create an agent

Each project can have one or more agents. Give your agent a name and a system prompt:

bash
curl -X POST "<your-server>/api/member/projects/$PROJECT_ID/agents" \
  -H "Authorization: Bearer $MEMBER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Support Bot",
    "system_prompt": "You are a friendly support assistant for an online store.",
    "model": "auto"
  }'

Optional: attach a knowledge base

Upload documents so your agent can answer from your own content using RAG. Upload via the dashboard or the API reference endpoint.

4. Chat with your agent

Send a message through the member chat API. Sessions are persisted, so context is maintained across requests.

bash
curl -X POST "<your-server>/api/member/projects/$PROJECT_ID/agents/$AGENT_ID/chat" \
  -H "Authorization: Bearer $MEMBER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"message":"Hello, what can you help me with?"}'

5. Deploy your own UI

Use the Tenant API with a tenant API key to build chat into your own app or custom frontend. See the Tenant API guide for details.

Next steps

  • • Configure tools & MCP servers on your agent.
  • • Add a knowledge base for grounded, context-aware answers.
  • • Monitor usage and spending in the analytics dashboard.