Skip to main content

Prerequisites

Install HasteKit SDK

Setting up the SDK

Making LLM Calls

Make a call to the model provider to generate a response:
Finally, extract the generated text from the response:

Responses API

Learn more about making LLM calls with the Responses API.

Creating Agents

Create a simple agent with system instructions and an LLM:
Execute the agent with user messages. Execute() returns an *AgentHandle; the simplest way to get the aggregated AgentOutput is handle.Result(), which drains the chunk stream internally. To render chunks live (e.g. forward to a UI), range over handle.Chunks yourself and then call handle.Wait().
Extract the agent’s response:

Agents

Learn more about building agents with the Agent SDK.