Skip to main content
Magic functions are stateless, AI-implemented functions; each call is independent. Implement magic functions by calling the magic() function within your async functions.

​
Magic function

The magic function enables AI-powered function implementation within your TypeScript code. Function bodies should call magic with a descriptive prompt. 
async function magic<T>(
  prompt: string,
  scope?: object,
  config?: {
    model?: 'openai:gpt-3.5-turbo'
          | 'openai:gpt-4o'
          | 'openai:gpt-4.1'
          | 'openai:gpt-5'
          | 'anthropic:claude-sonnet-4'
          | 'anthropic:claude-opus-4.1'
          | 'anthropic:claude-sonnet-4.5',
    premise?: string,
    system?: string,
    maxTokens?: number,
    listener?: (iid: string, chunk: Chunk) => void,
  },
): Promise<T>;
Parameters
​
prompt
string
The task description that guides the AI’s execution. This describes what the function should do.
​
scope
object
Optional. An object containing runtime resources that are available during execution. Resources in scope may be functions, methods, objects, types or any other value.
​
config
object
Optional configuration object for the magic function execution.
​
config.premise
string
Additional information made available in the agent’s system prompt.
​
config.system
string
Alternatively to providing premise, you can set explicitly set agent’s system prompt.
​
config.model
string
The model used to execute the magic function.One of:
  • openai:gpt-3.5-turbo
  • openai:gpt-4o
  • openai:gpt-4.1
  • openai:gpt-5
  • anthropic:claude-sonnet-4
  • anthropic:claude-opus-4.1
  • anthropic:claude-sonnet-4.5
Defaults to openai:gpt-4.1.
​
config.maxTokens
number
The maximum number of tokens that the agent can generate during one round of inference.Defaults to 2048.
​
config.listener
(iid: string, chunk: Chunk) => void
A callback for streaming model generation. Each streamed text chunk for each magic function call, determined by a unique invocation ID, will route to this callback.
​
Returns
Promise<T>
Returns a promise that resolves to the result of specified or inferred return type T.