Skip to main content

Agent Functions

The agent_function field defines the purpose and behavior of each agent within the network. It specifies what tasks the agent is responsible for and guides its operations.

Why are Agent Functions Important?​

  • Clarity of Purpose: Clearly defines what an agent does.
  • Behavioral Guidance: Instructs the agent on how to perform its tasks.
  • Coordination: Helps other agents understand the capabilities of their peers.

Defining Agent Functions​

Agent functions are defined using the agent_function field, which takes an array of strings describing the functions.

Example:​

  • Stock_news_searcher:

    agent_function:
      - "Your function is to search the web or the internet for the latest news about given companies and the stock market, including all relevant news articles and official filings."

  • sms_sender:

    agent_function:
      - "You can send SMS messages to the user using Twilio."

  • my_supervisor:

    index.js
    agent_function:
      - "You are the supervisor of the agents defined in outgoing edges."

Explanation:​

  • Descriptive statements that instruct the agent on its role.
  • Helps in tailoring the agent's behavior during execution.

Best Practices:​

  • Be Specific: Clearly state what the agent should do.
  • Use Action Verbs: Start functions with verbs like "Search", "Send", "Process".
  • Limit Scope: Keep functions focused on a single responsibility.

Visualization Suggestion​

Include a use case diagram or activity diagram that shows the functions of each agent.

  • Diagram Type: Activity Diagram.
  • Description: Visual representation of the agent's tasks and decision points.

Example:​

  • Stock_news_searcher:
    • Start → Search for news → Compile results → End

Defining clear agent functions ensures that each agent operates as intended, contributing effectively to the overall network.