Skip to main content
The AI Planet Platform is a no-code workspace for building AI agent workflows. You design a workflow visually on a canvas, connect AI agents to the tools and knowledge they need, test it interactively, and deploy it so your team or your applications can run it. If you have ever wanted an AI assistant that can answer questions from your own documents, call external services, and follow rules you define — this is where you build it, without engineering work.

​
What you can build

Document assistants

Agents that answer questions grounded in your uploaded files and knowledge sources.

Tool-using agents

Agents that take action — sending messages, fetching data, updating records in connected apps.

Multi-step workflows

Chains of agents and steps that pass results from one to the next to handle complex tasks.

API-powered features

Workflows you call from your own product through a simple API.

​
How it works

A workflow is a diagram you build on a visual canvas. You drag in nodes — building blocks like an Input, an Agent, or an Output — and connect them to define how information flows. The core building block is the Agent: an AI step you configure with instructions, a model, and optionally tools and a knowledge base. When you run the workflow, each node executes in order and passes its result onward.
The workflow builder canvas

A workflow on the builder canvas — an Input, an Agent, and an Output node connected together.

​
The typical journey

1

Create a workflow

Start from a blank canvas and give your workflow a name.
2

Build it

Add nodes, configure your agent, and connect everything together.
3

Test it

Open the Playground and try your workflow with real inputs.
4

Deploy it

Publish the workflow so it can be run by your team or through the API.
5

Monitor it

Review every run in Tracing to see exactly what happened.

​
Next steps

Quickstart

Build and run your first workflow in a few minutes.

Key concepts

Learn the vocabulary used throughout the platform.