Chat Channel: Difference between revisions

From Tygron Support wiki
Jump to navigation Jump to search
← Older edit
Frank@tygron.nl (talk | contribs)
Tygron, Tygron_admin, Bureaucrats, Interface administrators, Administrators
48,743 edits
No edit summary
 
(49 intermediate revisions by 2 users not shown)
Line 1: Line 1:
Chat Channels define the conversation with AI Agents. Each channel can have multiple [[Chat Message]]s.
{{Beta functionality}}
 
Chat Channels define the chat interaction with [[AI Agent]]s visible in the [[Chat panel]]. Each channel can have multiple [[Chat Message]]s.


==AI Agents==
==AI Agents==
The {{software}} currently has several default AI Agent channels:
{{main|AI Agent}}
The {{software}} has several default [[AI Agent|Chat Agent]]s available. It is also possible to add additional Agents with custom instructions.


* '''WIKI Assistant''': Searching the Tygron Wiki for information on features, configurations and guides.
===Model===
* '''TQL & Combo Generator''': Creates [[TQL]] queries and formulas for [[Combo Overlay]]s.
{{main|Generative AI (GenAI)}}
* '''Project Coder''': Can edit data in your Project, by executing [[TQL]] queries or interact with project [[API]] endpoints.


===LLM===
The Large Language Model used by the Agent.
List of open source [[Large Language Model (LLM)|Large Language Models]] available to the Chat Channel Agents:
* '''Gemma4 (Speed)''': Gemma4 model{{ref|Gemma4}} optimized for fast reactions.
* '''Qwen3.8 (Quality)''': Qwen3.8 model optimized for quality needed for coding and [[TQL]].


===Privacy===
===Instructions===
To protect your data, the following measures are in place:
An instruction is a set of prompts, settings, or rules that guides an [[AI Agent]]’s behavior, determines what data it can access, and explains how to respond to inputs.


* Chat messages are stored within your [[Project]] and follow the same data and privacy terms described in your license agreement.
===Tools===
* All models run exclusively on [[Cloud Computing|Tygron-owned GPU infrastructure]].
{{main|Agent Tool}}
* Zero Data Retention (ZDR): no data or metadata is stored by the AI model and conversations are not used for AI training.
Tools can help the Agent achieve it's goal.


===MCP Tools===
===Skills===
List of available Model Context Protocol (MCP) Tools for the Chat Channel Agents:
{{main|Skill}}
 
It is also possible to help the AI with [[Skill]]s. These are "job descriptions" of how to do specific tasks and can increase the scope of the agent's capabilities.
* '''get-summary''': Get AI Summary on a [[Main Page|WIKI]] subject.
* '''search-page''': Search the [[Main Page|WIKI]] Pages.
* '''get-page''': Get specific [[Main Page|WIKI]] Page.
 
* '''validate-endpoint''': Validate Tygron [[Endpoints|API Endpoint]].
* '''validate-query''': Validate Tygron [[TQL]] Query.
 
* '''execute-query''': Execute [[TQL]] Query in your connected Project [[session]].
* '''execute-endpoint''': Execute [[Endpoints|API Endpoint]] in your connected Project [[session]].


==Attributes==
==Attributes==
Chat Channel attributes can be used to guide the behavior of the underlying [[Large Language Model (LLM)]].
{{:Agent Attributes}}
 
{{LLM attributes|suppresscategory=true|allowselflink=true|
{{:temperature (LLM Attribute)}}
{{:top_p (LLM Attribute)}}
{{:top_k (LLM Attribute)}}
{{:num_predict (LLM Attribute)}}
{{:timeout_sec (LLM Attribute)}}
{{:think_mode (LLM Attribute)}}
{{:cacheable (LLM Attribute)}}
{{:project_info (LLM Attribute)}}
}}
 


{{article end
{{article end
|notes=* To properly use this technology and to protect your data, several measures have been taken. These are described in our [[AI Rules]].
|howtos=*[[How to add a Chat Channel]]
*[[How to duplicate a Chat Channel]]
*[[How to remove a Chat Channel]]
*[[How to set the instructions of a Chat Channel]]
*[[How to change the LLM of a Chat Channel]]
*[[How to configure a Chat Channel]]
*[[How to allow a Chat Channel to edit a project]]
*[[How to toggle the thinking section of a Chat Channel]]
|api=*[[Api session items chatchannels]]
|api=*[[Api session items chatchannels]]
*[[Api session event editor chatchannel]]
*[[Api session event editor chat]]
|references=
*[[Api session event editor chat set instructions]]
<references>
*[[Api session event editor chat add item channel]]
{{ref|Gemma4
|seealso=*[[Chat Message]]
  |name=Gemma4
*[[Generative AI (GenAI)]]
  |author=
*[[AI Agent]]
  |page=
*[[Agent Tool]]
  |source=
*[[Chat panel]]
  |link=https://deepmind.google/models/gemma/gemma-4/
*[[Skill]]
  |lastvisit=2026-06-29
}}
</references>
}}
}}
{{Editor community nav}}


[[Category:Items]][[Category:Chat]]
[[Category:Items]][[Category:Chat]]

Latest revision as of 11:56, 15 October 2026

This functionality is currently in BETA.
Read more about Beta features.


Chat Channels define the chat interaction with AI Agents visible in the Chat panel. Each channel can have multiple Chat Messages.

AI Agents

Main article: AI Agent

The Tygron Platform has several default Chat Agents available. It is also possible to add additional Agents with custom instructions.

Model

Main article: Generative AI (GenAI)

The Large Language Model used by the Agent.

Instructions

An instruction is a set of prompts, settings, or rules that guides an AI Agent’s behavior, determines what data it can access, and explains how to respond to inputs.

Tools

Main article: Agent Tool

Tools can help the Agent achieve it's goal.

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 the agent's capabilities.

Attributes

Agent attributes can be used to guide the behavior of the underlying AI Agent's Generative AI (GenAI) model.

Attribute Unit Description Default value
TEMPERATURE number Temperature controls the randomness of text that is generated by Agent's GenAI model during inference. A value >1 is more creative, <1 is more strict behavior. 1
THINKING_BUDGET_TOKENS number The maximum number of tokens the Agent's LLM can think before stopping. 1000
TOP_P number Top-P sampling selects a group of Agent GenAI model tokens whose cumulative probability is at least P. 0.95
TOP_K number Top-K sampling limits the Agent's LLM to choosing from the K most likely tokens at each step. 64
MAX_TOKENS number The maximum number of tokens the Agent's LLM can generate before stopping. 5000
TIMEOUT_SEC sec The maximum time allowed for the AI Agent before it is stopped. 600
THINK_MODE boolean With think-mode enabled the Agent's LLM returns both the reasoning and final answer. 1
PROJECT_INFO boolean Whether to include some basic info about the project that is accessible by the AI Agent. 1
CACHEABLE boolean Debug value, when deactivated the Agent Tools can no longer cache wiki pages. 1

Notes

  • To properly use this technology and to protect your data, several measures have been taken. These are described in our AI Rules.

How-to's

See also

API Endpoints

Editor Community
Community
Public Share • Blog • Wiki • Tickets • Chats • Sign in ArcGIS
GenAI
Chat Channel • Chat Message • AI Agent • Skill • Agent Tool • AI Rules • Agent Attributes
Editor
Current Situation • Future Design • Multi Scenario • Tools • Community
Retrieved from "https://support.tygron.com/w/index.php?title=Chat_Channel&oldid=96042"