Getting StartedChoose Your Path

Choose Your Path

Aerostack offers several ways to build AI-powered backends. Here’s how to decide which one fits your use case.

Quick Decision Tree

“I want to…”

  • …expose an API endpointFunctions
  • …build a chatbot on Discord/Telegram/WhatsApp/SlackBots
  • …give an LLM access to external servicesWorkspaces + MCP Servers
  • …deploy a prompt as a REST API with tool-useAgent Endpoints
  • …orchestrate multi-step logic with conditions and approvalsWorkflows (configured inside Bots or Agent Endpoints)
  • …let an AI agent manage my infrastructureAgent Automation

Comparison Table

FeatureFunctionsBotsAgent EndpointsWorkflows
What it isEdge-deployed REST APIsAI chatbots on messaging platformsPrompts deployed as REST APIsVisual logic orchestration
Best forCustom backend logic, CRUD, webhooksCustomer support, community managementAI-powered API routes with tool-useMulti-step processes with approvals
LLM required?NoYesYesOptional (LLM nodes available)
Connects to MCP tools?Via codeVia workspaceVia workspaceVia MCP tool nodes
Deploys asREST endpointBot on 5 platformsREST endpoint with streamingRuns inside bot or agent endpoint
Setup time3 min5 min5 min10 min

Common Combinations

Customer Support System

Bots (user-facing chat) + Workflows (escalation logic) + Workspace (Stripe, Zendesk, CRM tools)

AI-Powered API

Agent Endpoints (REST API) + Workspace (GitHub, Notion, Slack tools)

Internal Automation

Workflows (scheduled triggers) + Functions (custom logic) + Workspace (external service tools)

Developer Platform

Functions (backend APIs) + MCP Servers (publish tools for other developers)

Still Unsure?

Start with a workspace — it’s the foundation. Connect a few MCP servers, then decide whether to expose them via a bot, an agent endpoint, or a custom function.

Or use the AI Assistant — describe what you want to build and it will set everything up for you.