Agent DSL

Aigentic DSL

Aigentic provides a powerful and intuitive Kotlin DSL (Domain-Specific Language) for building and configuring AI agents. The DSL is designed to be expressive, type-safe, and easy to use, allowing you to create sophisticated AI agents with minimal boilerplate code.

Core Components

The Aigentic agent DSL consists of several key components:

• Agents - Creating and configuring agents
• Providers - Connecting to LLM providers
• Tools - Extending agents with custom capabilities

Agent Building

The core of the Aigentic DSL is the agent function, which allows you to create and configure AI agents:

@AigenticParameter
data class Answer(val message: String)

@AigenticParameter
data class AnswerSavedResult(val result: String)

// Using generic types to specify the output type
agent<String, Answer> {

  // Configure your provider of choice
  openAIModel {
    apiKey("<your-api-key>")
    modelIdentifier(OpenAIModelIdentifier.GPT5_4Mini)
  }

  // Configure the task for the agent
  task("Answer questions about Kotlin Multiplatform") {
    addInstruction("Provide concise and accurate answers")
  }

  // Define more context
  context {
    addText("<Additional information about Kotlin Multiplatform>")
  }

  // Add capabilities
  addTool(name = "saveAnswer", description = "Saves the answer to the database") { input: Answer ->
    AnswerSavedResult("Answer saved successfully: ${input.message}")
  }
}

This fluent API makes it easy to configure various aspects of your agent, including the LLM model to use, system prompts, and tools.

Model Integration

Aigentic's DSL provides a consistent interface for working with different LLM providers:

agent<String, Answer> {
    // OpenAI model
    openAIModel {
        apiKey("YOUR_API_KEY")
        modelIdentifier(OpenAIModelIdentifier.GPT5_5)
    }
    // ...
}

agent<String, Answer> {
    // Gemini model
    geminiModel {
        apiKey("YOUR_API_KEY")
        modelIdentifier(GeminiModelIdentifier.Gemini3_5Flash)
    }
    // ...
}

agent<String, Answer> {
    // Ollama model
    ollamaModel {
        apiUrl("http://localhost:11434/v1/")
        modelIdentifier(OpenAIModelIdentifier.Custom("llama3"))
    }
    // ...
}

Tool Definition

Aigentic provides functions for defining custom tools that extend your agent's capabilities. You can use addTool to inline a tool directly into the agent, or create a reusable tool using createTool.

@AigenticParameter
data class WeatherRequest(val location: String)
@AigenticParameter
data class WeatherResponse(val temperature: Double, val conditions: String)

val weatherTool = createTool<WeatherRequest, WeatherResponse>(
    name = "getWeather",
    description = "Get the current weather for a location"
) { request ->
    weatherService.getWeather(request.location)
}