PlatformNEW

Kanata features

Combine four features to put your internal knowledge to work.

In Kanata, you combine four main features (Kanata AI Agent, Kanata Library, Kanata Apps and Kanata Studio) in projects created for each purpose. AI answers, creates and acts based on your internal knowledge.

Video: Kanata features

An introduction to the four features (AI Agent, Library, Apps and Studio) and how to combine them in a project.

Structure

How the features are structured and work together

Outputs created in Apps, Studio or AI Agent are all gathered in the Library and become the basis for the AI agent.

Kanata project structure A space contains projects, and each project contains four main features: Kanata Apps, Kanata Studio, Kanata AI Agent and Kanata Library. The AI agent takes requests in chat, reviews the plan according to the autonomy level, and runs Apps and Studio within its execution permissions. Minutes, training materials and data from Apps are saved to the Library, and images and slides you choose to save in Studio are registered in the Library. The AI agent acts using the internal knowledge in the Library as its basis and input, and saves its output to the Library. SPACE / PROJECT Projects for each purpose within a space (organization) APP · Everyday use Kanata Apps AI Recording, e-Learning, etc. STUDIO · Creation Kanata Studio Images, slides, apps, Design System AI AGENT · On your behalf Kanata AI Agent Takes requests in chat and, by autonomy level, reviews plans LIBRARY · Knowledge Kanata Library (internal knowledge) Content (knowledge AI refers to as a basis) and Media (the files themselves) Saves minutes, materials and app data Registers images and slides you save Execute Execute Save output Basis and input

SPACE / PROJECTProjects for each purpose within a space (organization)

APP · Everyday use

Kanata Apps

AI Recording, e-Learning and more

STUDIO · Creation and building

Kanata Studio

Images, slides, business apps and Design System

AI AGENT · Works on your behalf

Kanata AI Agent

Takes requests in chat and acts after the plan is reviewed according to the autonomy level

LIBRARY · Knowledge accumulation

Kanata Library (internal knowledge)

Content (knowledge AI refers to as a basis) and Media (the files themselves)

Minutes, training materials and data from Apps are saved to the Library, and images and slides you choose to save in Studio are registered in the Library.

4 Functions

Four main features

AI Agent · Works on your behalf NEW

Kanata AI Agent

Takes on the work you request. Shared in the project and called up from chat DMs or the button at the bottom right of the screen.

  • Request from chatCall up from DMs or the button at the bottom right
  • Set what it handlesReference folders, execution permissions, model and autonomy level
  • Act after approvalReview the plan; only the approved scope is run
A sales support agent presenting an execution plan to create an image in ImageStudio and waiting for approval

Library · Knowledge accumulation NEW

Kanata Library

Where internal knowledge is stored and becomes the basis for AI answers and actions. Editing, versions and permissions for records are also managed here.

  • The foundation for RAGDocuments, minutes and prompts
  • Files tooImages, video, audio, PDFs and slides
  • Manage permissions and sourcesPermissions per folder and a record of sources
Documents such as the work rules listed in the Library's "Internal policies" folder, with their source, last updated date and author

App · Everyday use

Kanata Apps

Where you use AI in everyday work. Records do not stay inside the app; they are saved to the Library.

  • AI RecordingJoins meetings and creates recordings and minutes automatically
  • e-LearningCreates materials and exams from videos and tracks learners' progress
The app creation screen showing three apps: AI Summary, e-Learning and AI Recording

Studio · Creation and building BetaNEW

Kanata Studio

Where you create. Work in progress is managed inside Studio, and only finalized work is registered in Media.

Reviewing exhibition announcement banner options created in ImageStudio, along with the settings used to create them

Models

Supported AI models

Use generative AI models from OpenAI, Anthropic and Google from a single screen. Each model has a credit consumption multiplier, and higher-performance models consume more credits.

OpenAI

GPT

GPT 6 LunaGPT 6.1 TerraGPT 6.1 SolGPT 6 Astra

Anthropic

Claude

Claude Haiku 5.5Claude Sonnet 5.5Claude Opus 5.5

Google

Gemini

Gemini 3.1 Flash-LiteGemini 3.5 Flash-LiteGemini 4 HydrogenGemini 4 CarbonGemini 4 Argon

Supported models as of . Supported models and credit consumption multipliers are updated as needed. The latest list is shown in the model selection menu in the app.

How it works

The cycle of work and knowledge

The four features make possible a cycle of learning, decision-making, recording, delegating to AI and reviewing. Each time the cycle repeats, your internal knowledge grows richer.

01

Learn

People Decide

e-LearningDocumentVersion management

02

Decide

Share the Why

AI RecordingMinutesOrganizing decisions

03

Record

Share the Why

LibraryContent and MediaVersions and sources

04

Delegate to AI

Build the Harness

Kanata AI AgentAutonomy levels and plan reviewKanata Studio

05

Review

Close the Loop

Credit managementFeed into the next round of learning

Reflect what you learn from reviews in the next round of learning and decisions

Design rules

Kanata's design rules

When we add screens or features, we decide where they go according to these five rules.

  1. Outputs are saved to the Library
    Outputs created in Apps, Studio or AI Agent are saved to the Library, and where they were created is recorded as the "source".
  2. Content is the basis for AI
    AI refers to content as its basis. Media is managed as files.
  3. AI usage is recorded
    AI processing consumes the requesting user's credits. Space admins check the remaining credits and purchase more as needed.
  4. Editing, versions and permissions are managed in one place
    Editing, versions and viewing permissions for records are managed in the Library; Apps and Studio only have screens for using and for creating. What can be done in AppStudio app screens is set with app permissions.
  5. Work in progress is kept separate from finalized work
    Work in progress is managed inside Studio and is not registered in the Library. Only what you choose to save is registered in the Library's Media.

FAQ

FAQ

QWhat is the difference between a space and a project?

A space is the unit for an organization such as a company or team. A project is a unit you create within a space for each business purpose, with its own members, chat, AI agents, Library, Studio and apps. You can use projects for different purposes while keeping each department's confidential information separate.

QWhich AI models are available?

You can choose from OpenAI's GPT, Anthropic's Claude and Google's Gemini. Higher-performance models consume more credits per task, so you can use a lightweight model for everyday questions and a high-performance model for important analysis. The latest list and credit consumption multipliers are shown in the model selection menu in the app.

QWhat happens to the existing AI Chat and AI Summary?

AI Chat will be discontinued in the new version. You will ask AI for help through chat DMs and the AI agent at the bottom right of the screen. AI Chat apps, settings and conversations will not be migrated to the AI agent or chat. How past conversations are handled (the period for viewing and exporting them) will be announced in our news. Save documents you want the agent to refer to in its reference folders. The AI Summary app will be discontinued in the new version.

Last updated: