Documentation Index
Fetch the complete documentation index at: https://koreai-v2-home-nav.mintlify.app/llms.txt
Use this file to discover all available pages before exploring further.
Studio overview
Studio is the primary web interface for building, testing, deploying, and monitoring AI agents on the Agent Platform 2.0. It provides a unified workspace where teams can manage every phase of the agent lifecycle, from initial design through production operations.
Getting around Studio
Dashboard and home screen
When you sign in, Studio displays the Projects dashboard — a grid of project cards showing all projects in your workspace. Each card displays the project name, description, orchestration pattern badge, agent count, and last-updated timestamp.
From the dashboard you can:
- Search projects using the search bar at the top of the page.
- Create a new project using the “New Project” dropdown in the header (see Project management below).
- Open a project by clicking any project card, which navigates into that project’s workspace.
The top header bar is always visible and contains:
- Logo and product name — click to return to the Projects dashboard.
- Breadcrumb trail — shows your current location in the hierarchy (e.g., Projects > My Agent Project > Agents).
- Connection status indicator — a green or red dot showing real-time WebSocket connectivity.
- AI Architect toggle — opens the AI Architect side panel (available inside any project). See Agent development.
- Theme toggle — switch between light and dark mode.
- Admin link — navigate to workspace-level administration.
- User menu — account settings, profile, and sign-out.
Inside a project workspace, the left sidebar provides hierarchical navigation organized into three sections:
Build
| Item | Description |
|---|
| Overview | Adaptive project home page with metrics, agent list, and quick actions |
| Agents | Agent list, agent editor, and testing |
| Workflows | Workflow builder and execution monitoring |
| Item | Description |
|---|
| Tools | HTTP tools, code sandbox tools, and MCP servers |
| Knowledge Bases | Document ingestion, indexing, and search configuration |
| Integrations | Third-party connector catalog and active connections |
| Group | Pages |
|---|
| Evaluate | Evaluations, Experiments |
| Operate | Sessions, Deployments, Inbox, Alerts, Transfer Sessions |
| Insights | Dashboard, Agent Performance, Quality Monitor, Customer Insights, Voice Analytics |
| Govern | Guardrails, Governance |
| Settings | Members, API Keys, Models, Config Variables, Git, Advanced, Runtime Config, Trace Dimensions, Agent Transfer, PII Protection |
Project switcher
At the top of the sidebar, the project switcher dropdown lets you move between projects without returning to the dashboard. It shows a scrollable list of all your projects with the current project highlighted.
Project workspace overview
When you enter a project, the Overview page adapts based on project maturity:
- Empty state (no agents) — a get-started prompt guiding you to create your first agent or import existing agents.
- Building state (agents exist, no deployments) — metric cards showing agent count, session count, and deploy ratio, plus a quick-access agent list and resource summary on the right.
- Live state (active deployments) — full dashboard with session, message, token, cost, and deployment metrics. Includes active deployment list, recent activity timeline, and quick action cards for testing and deploying.
The overview also provides Import and Export buttons for moving agent definitions between projects or environments.
Command palette
Press Cmd+K (macOS) or Ctrl+K (Windows/Linux) from anywhere in Studio to open the command palette. The palette provides fuzzy search across:
- Navigation — go to any page within the current project.
- Agents — load a specific agent by name.
- Actions — reset session, clear events, and other quick commands.
Tip: The command palette is the fastest way to navigate large projects. Type a few characters of the page or agent name to filter results instantly.
Feature gating
Some Studio features depend on workspace-level configuration or your assigned role:
- AI Architect requires an LLM provider to be configured in workspace admin settings. An in-panel banner appears when the feature is not yet configured.
- Platform Admin link is visible only to users with super-admin permissions.
- Admin pages (Members, Models, Security, etc.) require workspace administrator permissions.
- Certain Insights pages (Agent Performance, Quality Monitor, Customer Insights) may display a “coming soon” placeholder if they are not yet enabled for your workspace.
Keyboard shortcuts
| Shortcut | Action |
|---|
| Cmd/Ctrl + K | Open command palette |
| Escape | Close dialogs, panels, and modals |
Project management
A project is the top-level container in Studio that groups agents, tools, knowledge bases, workflows, connections, and configuration together. Every agent you build belongs to a project, and projects provide the isolation boundary for deployments, access control, and analytics.
Creating a project
Studio offers three ways to create a new project from the Projects dashboard:
AI-guided creation
Click New Project > Start with AI Architect to launch the guided project creation wizard. This is the recommended approach for new users. The wizard walks you through a multi-phase process:
- Welcome — introduces the wizard and explains what to expect.
- Interview — the AI Architect asks questions about your use case, target audience, and requirements.
- Upload — optionally upload documents (knowledge base content, API specs, existing scripts) that inform the agent design.
- Generating — the AI Architect generates agent definitions, tool configurations, and project structure based on your inputs.
- Reveal — review the generated project structure and make adjustments.
- Review — finalize the configuration before creation.
- Create — the project is created and you are taken to the project workspace.
Blank project
Click New Project > Blank Project to open a creation dialog where you configure the project manually.
Required fields:
- Name — a descriptive name for your project.
Optional fields:
- Description — a brief summary of the project’s purpose.
Orchestration pattern selection:
Every project uses an orchestration pattern that determines how agents coordinate with each other. Choose from:
| Pattern | Description | Best for |
|---|
| Concierge (recommended) | A single front-facing agent delegates to specialist agents behind the scenes. The user always interacts with the concierge. | Customer service, help desk, general-purpose assistants |
| Router | A triage agent routes incoming requests to the appropriate specialist. The user is transferred to specialists directly. | Multi-department support, intent-based routing |
| Tiered | A triage agent routes to L1 agents that can escalate to L2 agents for complex issues. Supports de-escalation. | Technical support with escalation paths |
| Custom | No predefined structure. Agents can be connected in any topology. | Advanced use cases requiring flexible orchestration |
Tip: Choosing an orchestration pattern does not lock you in. It pre-configures agent roles (concierge, triage, specialist, L1, L2) and coordination blocks when you create new agents within the project, saving setup time.
From template
Click New Project > From Template to create a project based on a predefined template. Templates provide pre-built agent configurations for common use cases.
Project dashboard metrics
The project overview displays key metrics at a glance:
- Agent count — total number of agents in the project.
- Session count — conversations processed.
- Messages — total messages exchanged.
- Tokens — LLM token usage.
- Estimated cost — computed cost based on token consumption.
- Deployed ratio — how many agents have active deployments versus total agents.
The overview also includes a clickable agent list (with deployment status indicators), a resources panel summarizing tools and knowledge bases, quick action cards for testing and deploying, and an activity timeline for projects with active sessions.
Export and import
Exporting a project
From the project overview, click the Export button. The export dialog creates a downloadable package containing agent definitions and project configuration. Use exports to:
- Back up project state before major changes.
- Move agents between projects or environments.
- Share configurations with team members.
Importing into a project
From the project overview, click the Import button to upload a previously exported package. The import process merges the uploaded agents and configurations into the current project.
Important: Importing does not overwrite existing agents. If an agent with the same name already exists, the import process will flag the conflict.
Deleting a project
To delete a project:
- Open the Projects dashboard.
- Click the three-dot menu on the project card you want to delete.
- Select Delete.
- In the confirmation dialog, type the project name to confirm.
- Click Delete.
Warning: Deleting a project permanently removes all agents, tools, knowledge bases, workflows, sessions, and deployment configurations. This action cannot be undone.
Project settings
Project settings are organized into dedicated pages accessible from the Settings group in the sidebar. See Insights & settings for complete documentation of each settings page.
Related pages
