Agentic Prompts

Using ReACT framework, you can create AI agents that integrate the reasoning capabilities of large language models (LLMs) with the ability to take actionable steps, creating a more sophisticated system that can understand and process information, evaluate situations, take appropriate actions, communicate responses, and track ongoing situations.

In Karini AI's prompt playground, you can create an agent prompt by selecting the task type as "Agent". Key components of an agent prompt are:

  • LLM (Large Language Model) : LLM is responsible for generating traces, reasoning and actions for the task.

  • ReAct prompt: ReAct prompting is a technique used to guide the LLM in generating both reasoning traces and actions. This component is crucial for the dynamic reasoning capabilities of the ReACT agent model.

  • Tools: Tools are used to interact with external environments and gather information. Karini AI's agent prompt supports the following tools:

    • Dataset (Vector Store)

    • Prompt (LLM)

    • REST API

    • AWS Lambda

    • Catalog

    • Database

<<Video of Agent prompt>>

Last updated