Using Clouisle
From first sign-in to building, publishing, and operating AI agent teams
Clouisle is a multi-agent collaboration platform and workflow engine: with the team as the resource boundary, it orchestrates published Agents into multi-agent pipelines through visual workflows and combines them with Knowledge Bases, models, tools, and Skills into governable AI applications. Platform users build, debug, and publish applications in the workspace; administrators configure models, permissions, security policies, and runtime monitoring in the admin panel.
Quick Start
Complete your first sign-in, choose a team, and run a published application.
Core Concepts
Understand teams, Agents, Workflows, Knowledge Bases, models, tools, and security boundaries.
Guides
Complete application, Knowledge Base, model, capability, and team management by feature.
Best Practices
Optimize performance, Knowledge Base quality, prompts, and workflow orchestration with proven patterns.
End-to-End Tutorials
Build an acceptance-ready RAG Agent and automated Workflows from an empty team.
Testing
Agent UI automation test guide and journey matrix.
Changelog
Review significant changes in each Clouisle release.
Recommended learning path
- Start with the Quick Start to confirm your account, team, and model authorization are available.
- Read the Agent, Knowledge Base, and Workflow concepts.
- Enter the Guides by task. When you need field defaults, go to Reference.
- After publishing an application, use Logs and Monitoring in the application to check conversations, Tokens, latency, and failed runs.
How is this guide?