Maxim Logo
How toEvaluate Chains

Build complex AI workflows with Prompt Chains

Connect prompts, code, and APIs to create sophisticated AI systems using our visual editor - no coding required

When building AI applications, you often need multiple steps working together - like chaining multiple AI models, processing data, or calling external services. While single Prompts work well for simple tasks, complex workflows need a more structured approach.

What are Prompt Chains?

Prompt Chains let you connect three types of nodes to build your AI workflow:

  1. Prompt: Run LLM interactions
  2. Code: Add custom logic
  3. API: Connect external services via HTTP API

Each node's output feeds into the next, creating a seamless flow of data.

Visual editor showing connected Prompt Chain nodes

Available nodes

Create your first chain

Initialize your chain

Start from the Start node by dragging to create your first connection.

Choose node functionality

Configure the type and settings for your new node based on your requirements.

Node type selection

Expand the workflow

Connect additional nodes by dragging from the output handles to create new steps.

Add more nodes

Optimize connections

Modify the flow by adjusting node connections to achieve your desired logic.

Restructure nodes

Run a test

Try out your chain in the playground to verify its behavior

Input

Ensure each node's output matches the input requirements of connected nodes.

Version and deploy

Create versions to test or deploy your chain:

  1. Click Save in the top right
  2. Add an optional description
  3. Click Update

Version creation dialog

View all versions using the icon

Next steps:

Learn more about testing prompts or check our SDK documentation.

Previous

Set up a human annotation pipeline

Next

Debug AI agent errors step by step

On this page