Skip to main content

Casual mode

Casual agents are designed for everyday, general-purpose activities. They offer a versatile set of capabilities that make them suitable for a wide range of tasks and interactions.

Key Features​

  1. General-Purpose Interaction: Casual agents are equipped to handle a variety of everyday queries and tasks, making them ideal for general conversation and assistance.

  2. Image Generation: One of the standout features of Casual agents is their ability to generate images based on user requests. This can be particularly useful for creative tasks or visual explanations.

  3. Video Generation: Another important feature of Casual agents is the ability to create videos, up to 6 seconds long. ToothFairyAI behind the scenes generates two videos, one with audio and one without to grant maximum flexibility to the user.

  4. Document Analysis: Casual agents can analyse uploaded files, bypassing the Knowledge Hub. This feature allows for quick, on-the-spot document processing and information extraction.

  5. Multimodal Capabilities: When enabled, Casual agents can generate responses that include not just text, but also images, charts, tables, and mind maps, enhancing the richness of their output.

  6. File Upload Support: Users can upload various types of files including images, audio, video, and documents for the agent to process and analyse.

Image Generation Settings​

  • Allow images generation: Enables the agent to create new images based on user input. ToothFairyAI agents generate by default four images at each interaction allowing users to further refine the output.

  • Image generation model: Users can select from different models:

    • Mystica SD for general-purpose image creation
    • Mystica SD realism for photographic generation tasks
    • Flux Pro, Flux Pro 1.1, and Flux Pro 1.1 Ultra Realistic for commercial use cases (Enterprise plans only)

  • Max images generated: This setting allows the user to select the number of images to be generated at each interaction. The default value is 4. When the agent is invoked by the planner agent by default the image generation will produce only one at each step

Flux Pro

When a Flux Pro model is selected ToothFairyAI defaults the Max images generated to 1

Planner

When a Planner agent invokes a Casual agent with Image generation enabled, only one image will be generated at any given step.

Video & 3D Model Generation (Enterprise Only)​

  • Allow videos generation: This setting allows the agents to generate new videos based on the user input. ToothFairyAI agents generate by default two videos - one with audio and one without. The user can also pass the initial frame of the video to generate by uploading an image file inside the chat. If multiple images are passed only the first one will be used for the start of the video.

  • Video generation model: Mystica SD video is the default model for video creation.

  • Allow 3D model generation: This setting allows the agents to generate new 3D models based on the user input. ToothFairyAI agents with this must receive an image inside the chat to generate the 3D model. If multiple images are passed only the first one will be used for the 3D model generation. The agent cannot generate a 3D model based on the prompt alone.

Planner

When a Planner agent invokes a Casual agent with Video generation enabled, only one video will be generated at any given step.

Use Cases​

  1. Creative Assistance: Helping with brainstorming, idea generation, and visual concept creation.
  2. Quick Document Analysis: Providing summaries or insights from uploaded documents without needing pre-loaded knowledge.
  3. Visual Explanation: Creating images or diagrams to explain concepts or ideas.
  4. General Q&A: Answering a wide range of questions on various topics.
  5. Task Planning: Assisting with day-to-day task organisation and planning.
  6. Content Creation: Helping generate ideas or drafts for various types of content.
  7. Visual Content Generation: Creating custom images or short videos for presentations, social media, or personal projects.
  8. Interactive Learning: Using multimodal capabilities to provide engaging explanations on various subjects.
  9. Quick File Analysis: Offering rapid insights on uploaded documents, images, or audio files.
  10. Everyday Problem Solving: Providing advice and solutions for common daily challenges.

Advanced Features​

  • Multimodal Output: Ability to generate responses combining text, images, charts, and mind maps for comprehensive explanations.
  • File Processing: Capability to analyse and extract information from various file types including documents, images, and audio.
  • Contextual Understanding: Ability to maintain context throughout a conversation for more coherent and relevant responses.

Limitations​

  • Casual agents do not have access to the extensive knowledge base that Retriever agents use.
  • They cannot execute code like Coder agents.
  • They cannot accomplish complex, multi-step tasks like Planner agents.
  • Image and video generation quality may vary based on the complexity of the request.
  • 3D model generation requires an initial image input and may have limitations in detail and complexity.

Best Practices​

  1. Be Specific in Requests: Provide clear, detailed instructions when asking for image or video generation.
  2. Utilise Multimodal Capabilities: Combine requests for text, images, and other visual elements for comprehensive responses.
  3. Leverage File Upload: When seeking analysis or insights, upload relevant files for the agent to process.
  4. Iterate on Creative Tasks: Use the agent's output as a starting point and refine through follow-up requests.
  5. Combine with Other Agent Types: For complex tasks, consider using Casual agents in conjunction with other specialised agents.

By leveraging these features and following best practices, Casual agents can serve as versatile assistants for a wide range of everyday tasks and creative endeavours.