Home / Docs / Getting Started

Getting Started

Follow these 8 steps to build and launch your first AaaS agent. Each step builds on the previous one, but you can revisit and refine any step at any time through the dashboard.

1

Define your service

Think about what service your agent will provide. What problem does it solve? Who are the customers? What are the deliverables and pricing? You don't need to write anything yet, just have a clear picture.

Examples: a used phone marketplace, a travel concierge, a tutoring service, a matchmaker, a food ordering agent, a freelance consulting service.
2

Prepare your data

Gather the files, images, documents, and structured data your agent needs to provide the service. This includes product listings, menus, course materials, photos, PDFs, or any other reference material.

You can add data now or later. Use the Data tab in the dashboard to upload files, create JSON records, or import external files. You can also send data to the agent in chat and let it organize everything.
3

Set up external services

If your agent needs to call external APIs (payments, shipping, weather, email) or delegate to other agents, register them as extensions. Each extension becomes a tool the agent can use during conversations.

You can always add extensions later as your service evolves.
4

Populate your service

Use the chat interface, the CLI, or the Data tab to build your service database with natural language. Tell the agent about your products, rules, and processes and it will structure and store everything for you.

Try chatting in Admin mode: "Add a new product: iPhone 15 Pro, 256GB, Excellent condition, $950". The agent creates the database entry automatically.
5

Write the SKILL

Define how the agent should behave and deliver the service. The SKILL file contains your service catalog, domain knowledge, pricing rules, and boundaries. You can write it yourself or use the chat interface to have the LLM generate it from your description.

In Chat, try: "Write me a SKILL.md for a used iPhone marketplace with these services: browse inventory, list a device, purchase a device." The agent will draft the whole file.
6

Test and improve

Chat with your agent as both a customer and an admin to test how it handles real requests. Try edge cases, ask tricky questions, and refine the skill file based on what you find.

Use Customer mode to simulate a real customer experience. Switch to Admin mode when you need to fix data, update rules, or debug behavior. You can also test via the CLI with aaas chat.
7

Choose platforms and connect

Pick where your agent will be available: HTTP API, Telegram, Discord, Slack, WhatsApp, Relay, or a combination. Each platform has its own setup flow in the Deploy tab of the dashboard.

Start with one platform to validate, then add more later. The HTTP API is the simplest to set up. Use the Relay if you don't have a public server.
8

Go live

Run your agent and it starts serving on all connected platforms. Monitor transactions, review memory, and keep improving the service over time.

Use aaas run from the CLI or click Start in the Deploy tab. Check the Overview tab for stats and the Transactions tab to track service delivery.

What you need

  • Node.js 18+ installed on your machine
  • An LLM API key from any supported provider (Anthropic, OpenAI, Google, OpenRouter, or a local Ollama instance)
  • A platform token if you want to deploy to Telegram, Discord, Slack, or WhatsApp (optional for getting started)

Install and create your first workspace

# Install AaaS globally
npm install -g @streetai/aaas

# Create a new workspace
aaas init my-agent "My Agent" "A helpful service agent"

# Set your LLM provider and choose a model
cd my-agent
aaas config --provider anthropic --key sk-ant-...
aaas config --model claude-sonnet-4-20250514

# Open the dashboard
aaas dashboard

The dashboard opens in your browser with the Setup Guide tab, which tracks your progress through these 8 steps and auto-detects what you've already completed.

Next steps

Once your agent is running, explore the rest of the documentation to learn about each component in detail: