Create autonomous agents that can use tools, reason, and complete complex tasks over multiple steps.
Latitude Agents are an advanced prompt type that enables AI models to operate autonomously, breaking down complex tasks, using tools, and reasoning through multiple steps until a final goal is achieved.
Unlike simple prompts or even Chains which follow predefined steps, Agents can dynamically decide their next action based on the context and available tools.
When you finish reading this page you can read our take on Anthropic’s building agents article
To turn a prompt into an Agent, simply add type: agent
to its configuration block:
When an Agent prompt is run:
This loop allows the agent to adapt its strategy, handle errors, and utilize tools effectively.
Agents become truly powerful when combined with Tools. Provide the agent with a set of relevant tools, and it will decide which ones to use and when.
In this example, the agent might:
get_weather
.get_location_id
with location_name
.location_id
.get_weather
with the obtained location_id
.You can guide the agent’s final output by specifying a response schema
using JSON Schema:
The agent will work towards fulfilling the task and then structure its final response according to the schema.
While agents operate autonomously, you can provide initial instructions or force specific actions using <step>
tags. The agent will execute these predefined steps first before entering its autonomous loop.
To prevent agents from running indefinitely (e.g., getting stuck in loops), you can limit the maximum number of steps (tool calls + LLM responses) using the maxSteps
configuration option (default: 20, max: 150).
If the limit is reached before the goal is completed, the agent run will terminate with an error.
Agents are run just like any other prompt using the API or SDKs. The response will typically be a stream of events detailing the agent’s thought process, tool calls, and final answer.
You can make any prompt have access to other agents in your project by using the agents
configuration option. This allows you to create a hierarchy of agents, where tasks are delegated to subagents with specific responsibilities.
The main prompt will have access to running the subagent prompt as if it was a tool. This allows you to structure complex tasks into smaller, manageable sub-tasks performed by different agents.
Create autonomous agents that can use tools, reason, and complete complex tasks over multiple steps.
Latitude Agents are an advanced prompt type that enables AI models to operate autonomously, breaking down complex tasks, using tools, and reasoning through multiple steps until a final goal is achieved.
Unlike simple prompts or even Chains which follow predefined steps, Agents can dynamically decide their next action based on the context and available tools.
When you finish reading this page you can read our take on Anthropic’s building agents article
To turn a prompt into an Agent, simply add type: agent
to its configuration block:
When an Agent prompt is run:
This loop allows the agent to adapt its strategy, handle errors, and utilize tools effectively.
Agents become truly powerful when combined with Tools. Provide the agent with a set of relevant tools, and it will decide which ones to use and when.
In this example, the agent might:
get_weather
.get_location_id
with location_name
.location_id
.get_weather
with the obtained location_id
.You can guide the agent’s final output by specifying a response schema
using JSON Schema:
The agent will work towards fulfilling the task and then structure its final response according to the schema.
While agents operate autonomously, you can provide initial instructions or force specific actions using <step>
tags. The agent will execute these predefined steps first before entering its autonomous loop.
To prevent agents from running indefinitely (e.g., getting stuck in loops), you can limit the maximum number of steps (tool calls + LLM responses) using the maxSteps
configuration option (default: 20, max: 150).
If the limit is reached before the goal is completed, the agent run will terminate with an error.
Agents are run just like any other prompt using the API or SDKs. The response will typically be a stream of events detailing the agent’s thought process, tool calls, and final answer.
You can make any prompt have access to other agents in your project by using the agents
configuration option. This allows you to create a hierarchy of agents, where tasks are delegated to subagents with specific responsibilities.
The main prompt will have access to running the subagent prompt as if it was a tool. This allows you to structure complex tasks into smaller, manageable sub-tasks performed by different agents.