Settings

Assistant Instructions (Prompt)

In Aicado, the AI Base Prompt Settings define how the AI conversational assistant responds to user interactions. It sets the tone, language, and behavior of the AI. This ensures that AI chatbots provide accurate, helpful, and language-specific answers.

Here's a detailed guide to understanding and managing the AI Base Prompt.

Changing the AI base prompt is an advanced setting. If you are not familiar with AI profiles, it is advisable not to alter them. At Aicado, we have already prepared the base prompt in the most optimal way for you.

Proceed with caution, and consider consulting with an expert or our support team if you are unsure about making changes to this setting.

Default Base Prompt: The default base prompt for Aicado is as follows: You're an intelligent assistant, focused on giving precise and helpful answers. Excel in multi-turn conversations and ask for clarification if needed. You must answer only using the provided context. If the context lacks the information, reply, "I'm sorry, but I can't provide a definite answer based on the available context."

Customizing Assistant Behavior (Prompt): You can also customize the base prompt to better align with your brand voice and specific customer interactions. Here's how to do it:

1. Navigate to Settings Tab: Go to the "Settings" tab in the AI ​​Agent embed editor.

2. Edit Prompt: You can modify the existing prompt or enter a completely new one based on your needs and expectations.

Tips for Creating Effective Prompts:

• Maintain Clarity: Ensure that the prompt is clear and concise, defining the AI's role and response behavior.

• Reflect Brand Voice: Customize the prompt to align with your brand's tone and voice.

• Consider Language Preferences: Account for the language in which the user is communicating, as specified in the default prompt.

The AI Base Prompt Settings play a crucial role in defining how your AI Agent interacts with users. Utilizing the default prompt or customizing it to match your brand ensures a consistent, helpful, and engaging user experience.

For additional support or guidance in managing your AI Base Prompt Settings, the Aicado support team is always here to help!

Advanced Settings

This section covers the advanced settings for fine-tuning the AI model's output. These parameters allow you to customize the behavior of the AI to better suit your specific use cases without requiring coding knowledge.

Temperature

Purpose: Controls the randomness in the AI's responses. Range: 0.0 to 1.0 Default: 1.0

• Lower values (0.0 - 0.5): Produce more consistent and deterministic responses. Suitable for fact-based or analytical tasks.

• Higher values (0.6 - 1.0): Generate more diverse and creative outputs. Ideal for brainstorming or creative writing tasks.

Note: Even at 0.0, responses may not be entirely deterministic due to the nature of language models.

Max Tokens

Purpose: Limits the length of the AI's response. Input: Positive integer or null Default: Not specified (uses model's maximum)

• Represents the maximum number of tokens (word pieces) in the AI's response.

• Helps control the length and detail of generated text.

Important: The total of input tokens and generated tokens must not exceed the model's context length.

Verbosity

Verbosity determines the length and detail of the AI’s responses. Adjusting this setting allows you to tailor output to your specific needs:

• High verbosity: Recommended for comprehensive document explanations or extensive code refactoring, where detailed output is required.

• Medium verbosity (default): Provides a balanced level of detail, suitable for most standard tasks.

• Low verbosity: Ideal for concise answers or simple code generation, such as brief SQL queries.

In GPT-5, verbosity can be set to high, medium, or low. Higher verbosity produces more thorough and structured responses, often including inline explanations. Lower verbosity generates shorter, more direct outputs with minimal commentary.

Select the verbosity level that best matches your use case for optimal results.

Adjusting Settings

1. Start with default values and make incremental adjustments.

2. Test the output after each adjustment to gauge the impact.

3. Consider your specific use case when modifying these parameters.

4. Document successful configurations for future reference.

Remember that optimal settings may vary depending on your specific application and desired output. Experimentation within safe ranges is encouraged to find the best configuration for your needs.

Structured Outputs

Structured Outputs is an optional feature that enables your AI Agent to deliver responses that strictly follow a custom JSON schema—no coding required. This option helps you define the agent’s function and use case more precisely, ensuring reliable, type-safe, and consistently formatted data whenever you need it.

Key Features

• Type Safety: Guarantees that agent responses match your schema, so you don’t have to manually validate output.

• Explicit Refusals: Programmatically detect when the agent refuses to answer for safety reasons.

• Simplified Prompting: Achieve consistent formatting without complex prompt engineering.

How It Works

You provide a JSON schema that defines the structure of the agent’s output. The AI Agent generates responses that fit this schema, making sure all required fields are present and valid.

Example JSON Schema

Structured Outputs must be in minified format

{"format":{"type":"json_schema","name":"test_structured_text","schema":{"type":"object","properties":{"a_points":{"type":"number"},"r_points":{"type":"number"},"t_points":{"type":"number"},"i_points":{"type":"number"},"a_report":{"type":"string"},"r_report":{"type":"string"},"t_report":{"type":"string"},"i_report":{"type":"string"},"startup_uid":{"type":"string"},"abstract":{"type":"string"}},"required":["a_points","r_points","t_points","i_points","a_report","r_report","t_report","i_report","startup_uid","abstract"],"additionalProperties":false},"strict":true}}

Parameter Overview

• Schema Definition: Clearly name keys and provide descriptions for all important fields. All fields must be required. Structured Outputs must be in minified format.

• Supported Types: String, Number, Boolean, Integer, Object, Array, Enum, anyOf.

• Constraints: Apply patterns, formats, and value ranges to control input validity.

• Additional Properties: Set additionalProperties to false to restrict output to your schema.

Limitations

• Maximum nesting depth: 10 levels.

• Maximum object properties: 5000.

• String length and enum value limits apply.

Structured Outputs is a robust way to customize and control your agent’s responses for many use cases. Enable and experiment with this feature to find the configuration that best fits your needs.