Agent

The Agent block is a fundamental component in Sim Studio that allows you to create powerful AI agents using various LLM providers. These agents can process inputs based on customizable system prompts and utilize integrated tools to enhance their capabilities.

Agent blocks serve as interfaces to Large Language Models, enabling your workflow to leverage state-of-the-art AI capabilities.

Overview

The Agent block serves as an interface to Large Language Models (LLMs), enabling you to create agents that can:

Respond to user inputs: Generate natural language responses based on provided inputs

Follow instructions: Adhere to specific instructions defined in the system prompt

Use specialized tools: Interact with integrated tools to extend capabilities

Structure output: Generate responses in structured formats when needed

Configuration Options

System Prompt

The system prompt defines the agent's behavior, capabilities, and limitations. It's the primary way to instruct the agent on how to respond to inputs.

You are a helpful assistant that specializes in financial analysis.
Always provide clear explanations and cite sources when possible.
When responding to questions about investments, include risk disclaimers.

User Prompt

The user prompt or context is the specific input or question that the agent should respond to. This can be:

Directly provided in the block configuration
Connected from another block's output
Dynamically generated during workflow execution

Model Selection

Choose from a variety of LLM providers:

OpenAI (GPT-4o, o1, o3-mini)
Anthropic (Claude 3.7 Sonnet)
Google (Gemini 2.5 Pro, Gemini 2.0 Flash)
Groq, Cerebras
Ollama Local Models
And more

Temperature

Control the creativity and randomness of responses:

More deterministic, focused responses. Best for factual tasks, customer support, and situations where accuracy is critical.

The temperature range (0-1 or 0-2) varies depending on the selected model.

API Key

Your API key for the selected LLM provider. This is securely stored and used for authentication.

Tools

Integrate specialized tools to enhance the agent's capabilities. You can add tools to your agent by:

Clicking the Tools section in the Agent configuration
Selecting from the tools dropdown menu
Choosing an existing tool or creating a new one

Available tools include:

Confluence: Access and query Confluence knowledge bases
Evaluator: Use evaluation metrics to assess content
GitHub: Interact with GitHub repositories and issues
Gmail: Process and respond to emails
Firecrawl: Web search and content retrieval
And many, many more pre-built integrations

You can also create custom tools to meet specific requirements for your agent's capabilities.

Tools significantly expand what your agent can do, allowing it to access external systems, retrieve information, and take actions beyond simple text generation.

Response Format

Define a structured format for the agent's response when needed, using JSON or other formats.

Inputs and Outputs

User Prompt: The user's query or context for the agent
System Prompt: Instructions for the agent (optional)
Tools: Optional tool connections that the agent can use

Example Usage

Here's an example of how an Agent block might be configured for a customer support workflow:

# Example Agent Configuration
systemPrompt: |
  You are a customer support agent for TechCorp.
  Always maintain a professional, friendly tone.
  If you don't know an answer, direct the customer to email support@techcorp.com.
  Never make up information about products or policies.
 
model: OpenAI/gpt-4
temperature: 0.2
tools:
  - ProductDatabase
  - OrderHistory
  - SupportTicketCreator

Best Practices

Be specific in system prompts: Clearly define the agent's role, tone, and limitations. The more specific your instructions are, the better the agent will be able to fulfill its intended purpose.
Choose the right temperature setting: Use lower temperature settings (0-0.3) when accuracy is important, or increase temperature (0.7-2.0) for more creative or varied responses
Combine with Evaluator blocks: Use Evaluator blocks to assess agent responses and ensure quality. This allows you to create feedback loops and implement quality control measures.
Leverage tools effectively: Integrate tools that complement the agent's purpose and enhance its capabilities. Be selective about which tools you provide to avoid overwhelming the agent.

Agent

On this page