Skip to main content
Version: 2.0

Create agent

POST 

/v2/agents

Create a new agent. An agent is compromised as 3 main things of functionality:

  1. The instructions an agent follows. Known as a system in prompt in other platforms.
  2. The steps an agent follows when receiving an input.
  3. The tools an agent can use to resolve those steps and instructions. Instructions are tied to each step, and should be well crafted so that the agent can perform the desired actions when given an input.

To use an agent, create a new session (called thread or chat in other platforms), and send new inputs to the agent to get responses.

Note: Only a single step is supported with no follow up steps. So the first_step will be only the only step. We will add multiple steps and step types to execute complex workflows, but many agents can work well with a single step.

Request

Responses

The agent has been created successfully.