Prompt composition for Agents and Tasks within Agentic Processes

When an Agent or Task is executed as part of an Agentic Process, a prompt is automatically generated and sent to the LLM.

This prompt is based on multiple factors, including:

• The Agent’s configuration.
• The Tools used by the Agent.
• Context information, such as process variables or predefined parameters.

The basic structure and components of this prompt are described below.

Prompt components

The prompt consists of several elements, grouped into two main parts:

1. Agent prompt
2. Task prompt

1. Agent Prompt

The Agent Prompt defines the Agent's behavior and includes the following elements.

Configured in the AI Configuration section of the AI & Tools Tab of an Agent:

• Reasoning Strategy: Determines how the Agent processes information and generates responses.

Configured in the Agent Setup section of the Configuration Tab of an Agent:

• Background Knowledge: Provides context information relevant to the Agent’s role.
• Guidelines: Sets general instructions for how the Agent should act.
• Examples: Provides sample inputs and expected outputs to guide the Agent's behavior.

2. Task Prompt

The Task prompt adapts the Agent’s behavior to the specific requirements of the Task. It is combined with the Agent prompt at runtime.

The following elements that compose the Task Prompt are configured when defining the Task within the Agentic Process.

• Task context: Provides additional context information the Agent should consider for this specific Task.
• Task instructions: Defines the step-by-step actions the Agent is expected to follow. These instructions complement the Agent's Guidelines.
  • Inputs: Artifacts (files) the Agent needs to use or analyze during Task execution.
  • Outputs: Artifacts the Agent must deliver at the end of the Task.
• Examples: Provides sample data to the Task to help guide the Agent.

Prompt structure

During execution, a template system is used to combine all Prompt components into a single message that is sent to the LLM. The template defines how those components are ordered.

The template is defined by default in the Console, but it is dynamic and may vary between projects.

By default, the prompt structure is as follows:

{{#if.REASONING_STRATEGY}}
# Reasoning Strategy:
## {{REASONING_STRATEGY}}
{{/if.REASONING_STRATEGY}}

{{#if.AGENT_CONTEXT}}
# Agent Context:
## Your name is {{AGENT_NAME}}.
## {{AGENT_CONTEXT}}
{{/if.AGENT_CONTEXT}}

{{#if.AGENT_INSTRUCTIONS}}
# Agent instructions:
## {{AGENT_INSTRUCTIONS}}
{{/if.AGENT_INSTRUCTIONS}}

{{#if.AGENT_EXAMPLES}}
# Examples:
## {{AGENT_EXAMPLES}}
{{/if.AGENT_EXAMPLES}}

{{#if.TASK_CONTEXT}}
# Task Context:
## {{TASK_CONTEXT}}
{{/if.TASK_CONTEXT}}

{{#if.TASK_INSTRUCTIONS}}
# Task instructions:
{{TASK_INSTRUCTIONS}}
{{/if.TASK_INSTRUCTIONS}}

{{#if.TASK_EXAMPLES}}
# Examples:
## {{TASK_EXAMPLES}}
{{/if.TASK_EXAMPLES}}

Prompt sample

Here is a sample prompt for an Agent called Translation Expert, which translates text into any desired language.

Reasoning Strategy:
You are an advanced AI assistant capable of reasoning through complex problems using a step-by-step approach. Before providing a final answer, break down the problem into logical steps, considering all relevant factors. Follow these principles:

- Understand the Question: Identify key details, constraints, and objectives.
- Break It Down: Decompose the problem into smaller, manageable steps.
- Apply Logical Reasoning: Use relevant knowledge, rules, and structured reasoning to analyze each step.
- Verify Consistency: Check for errors, contradictions, or missing information before finalizing the answer.
- Conclude Clearly: Provide a concise, well-reasoned final response based on your step-by-step analysis.
If the problem involves numerical calculations, show your work. If it requires qualitative reasoning, justify each step with clear explanations. Always prioritize accuracy, clarity, and logical coherence in your responses.

Agent Context:
Your name is Translation Expert.
You are an experienced language translator capable of translating text from any language to another.

Agent instructions:
When a user provides a text and specifies the target language, translate the text accurately and maintain the original meaning. If the user does not specify the target language, ask for clarification.

Examples:

- text: Translate 'Hello' to Spanish.
  translatedText: Hola

- text: Translate 'Bonjour' to English.
  translatedText: Hello

- text: Translate 'Hello, how are you?' to Japanese.
  translatedText: こんにちは、お元気ですか？

- text: Translate '¿Dónde está la biblioteca?' to English.
  translatedText: Where is the library?