AI Agent

An AI Agent within Tygron Platform that perceives its environment, processes information, and acts to achieve specific goals. It works autonomously to complete assigned tasks effectively.

Each Agent has four components:

* Persona: Each agent has a defined role, style and instructions. These help it behave consistently while adapting through interaction.

* Memory: Memory helps Agents maintain context and adapt over time. Short memory is stored inside a cache, longer memory is stored in the history via e.g. Chat Messages.

* Tools: Tools are external functions or resources that Agents use to find information, edit Project data or connect with other services. Agents select and use tools based on the task and context.

* Model:: An Agent’s large language model (LLM) Neural network acts as its “brain.” It interprets instructions, reasons through problems, generates language, and coordinates other components to complete tasks.

Chat Agents

The Tygron Platform currently has two default AI Chat Agents:

• WIKI Assistant: Searching the Tygron Wiki for information on features, configurations and guides.
• Project Coder: Can edit data in your Project, by executing TQL queries or interact with project API endpoints.

Generative AI

Main article: Generative AI (GenAI)

List of open source Generative AI models available to the Chat Channel Agents:

• Gemma4 (Speed): Gemma4 model optimized for fast reactions.
• Qwen3.8 (Quality): Qwen3.8 model optimized for quality needed for coding and TQL.

Privacy

To protect your data, several measures have been takes. These are described in our AI Rules.

MCP Tools

List of available Model Context Protocol (MCP) Tools for the Chat Channel Agents:

• get-summary: Get AI Summary on a WIKI subject.
• search-page: Search the WIKI Pages.
• get-page: Get specific WIKI Page.
• get-screen: Take a screenshot of a window of the Tygron Client
• get image: Get a WIKI image.

• go-to-location: Navigate in the 3D Visualization to a specific location.
• open-panel: Open a specific Panel

• validate-endpoint: Validate Tygron API Endpoint.
• validate-query: Validate Tygron TQL Query.

• execute-query: Execute TQL Query in your connected Project session.
• execute-endpoint: Execute API Endpoint in your connected Project session.

Skills

Main article: Skill

It is also possible to help the AI with Skills. These are "job descriptions" of how to do specific tasks and can increase the scope of of the agent's capabilities.