Platform Concepts

Everything you need to understand how Kajoo Agentic is structured — workspaces, agents, skills, recipes, connections, and more.

This page explains the core concepts behind Kajoo Agentic. You don't need to read it before using the platform — but it's here when you want to understand what's happening under the hood, customize a workspace, or build one from scratch.


Workspace

A workspace is the container for a delivery engagement. It holds everything needed to complete a specific job — agents, connections, skills, tool permissions, and prompt templates — organized around a single use case or project.

One workspace typically maps to one migration engagement, one client site, or one delivery workflow. Your organization can have multiple workspaces, and they are fully isolated from each other. A workspace is visible to the person who created it, the people it's shared with, and your Organization Owners — see Team, roles and sharing.

What a workspace contains:

ComponentWhat it is
AgentsThe AI workers that execute the workflow
ConnectionsMCP servers that give agents access to external systems
ProjectsWorking areas with chats, tasks and scheduled jobs
SkillsKnowledge packages loaded into agents
Prompt templatesReusable prompts you can invoke from chat
ModelsThe AI models the workspace's agents can use

Workspaces can be created from a recipe (pre-configured for a specific use case) or from scratch (manually assembled). See Getting Started for how to create one.


Agents

Agents are the AI workers inside a workspace. Each agent has a specific role and a defined set of tools, skills, and an LLM assigned to it based on the nature of its work.

Orchestrator agents vs. sub-agents

Kajoo workspaces use a two-tier agent structure:

  • Orchestrator agents coordinate the overall workflow, manage your conversation, and delegate tasks to sub-agents. You interact with orchestrators directly.
  • Sub-agents execute specific tasks — analyzing code, migrating a component, pushing content, converting a rendering. They work in the background, called by orchestrators as needed. Their questions and approvals come to you in the main chat.

What each agent has

PropertyWhat it does
System instructionsDefines the agent's role, knowledge, and behaviour
MCP connectionsWhich tools the agent can call
SkillsCurated knowledge packages the agent draws from
LLM ModelWhich model the agent uses: a specific model, or Auto
Tool permissionsPer-tool human-in-the-loop settings (auto-approve or approval required)
Prompt templatesReusable prompts that can be invoked from the chat window

Models and Auto routing

Each agent is assigned the right model for its task. Lighter planning and orchestration tasks can use smaller, faster models. Code migration, synthesis, and reasoning tasks use more capable models. Models are grouped in tiers: Mini, Pro, Max and Ultra.

Choose Auto and Kajoo picks the most efficient model for each task, from the models your workspace has turned on in Workspace Settings → LLM Models. You can also pick a model for a single chat without changing the agent. See Working in chat.

Every model call goes through the Kajoo AI Secure Gateway, which keeps your secrets and personal data out of logs. See the Overview.


Skills

Skills are curated knowledge packages attached to agents. They contain the DXP-specific context, rules, and patterns an agent needs to do its job correctly — things like how Sitecore XP templates map to SitecoreAI components, how to structure a headless SXA layout, or how to generate a TypeScript GraphQL adapter.

Skills are what make Kajoo agents DXP-aware rather than generic. A code migration agent without the right skills is just an LLM. With the right skills, it understands Sitecore rendering models, Content SDK 2.0 patterns, and JSS component structure.

A skill can be a single set of instructions or a folder of files: a SKILL.md plus references, scripts and assets. When you create a workspace from a recipe, the appropriate skills are loaded automatically. You can add, swap, or remove skills from any agent in the workspace configuration. Add Skill offers four ways to add one: Create with Kajoo, Write Skill Instructions, Import from URL, and Upload a Skill.


Recipes

A recipe is a pre-configured workspace template for a specific delivery use case. When you create a workspace from a recipe, Kajoo automatically provisions:

  • The full agent team for that workflow
  • All required MCP connections
  • The appropriate skills for each agent
  • Human-in-the-loop tool permissions
  • A setup wizard to connect your environments
  • For some recipes, the workflow: its phases and tasks on your task board

Recipes encode hard-won delivery knowledge — the agent structure, tool permissions, phase sequencing, and guardrails for a particular type of work. You don't assemble this from scratch; you start from a recipe, connect your project, and begin working.

Available recipes:

RecipeWhat it delivers
Sitecore Migration v3Sitecore XP to SitecoreAI migration with a dynamic workflow: the plan grows on your task board as Setup and Discovery uncover what your site needs.
XP → SitecoreAI MigrationFull Sitecore XP to SitecoreAI (formerly XM Cloud) migration — code, content, and presentation — in six fixed phases. Supports both Headless (JSS) and MVC source sites.

You can also build a workspace from scratch for custom workflows, or use an existing recipe as a starting point and customize from there.

Recipe Library and Recipe Sync

Your organization can add its own recipes from public GitHub repositories under General Settings → Recipe Library, and choose which of Kajoo's recipes it starts workspaces from. A workspace stays linked to the recipe it came from: re-apply the recipe or update to a newer version from Workspace Settings → Recipe Sync, which shows every change for you to review before anything is saved, or Detach the workspace to keep your own changes. See Recipes.

Recipe Builder

A Recipe Builder is coming to Kajoo Agentic — allowing teams to remix existing recipes, customize agent configurations, and compose entirely new recipes without writing infrastructure code.


MCP Connections

MCP (Model Context Protocol) connections are the integrations that give agents access to external systems. Each connection exposes a set of tools that agents can call — reading from a repository, pushing content to a CMS, querying a GraphQL endpoint, creating a branch.

Connections are registered at the workspace level. All agents in a workspace can be granted access to any connection in that workspace.

Connections in a recipe workspace are pre-configured. When you create a workspace from a recipe, the required connections are provisioned automatically. You connect your specific environments (repos, CMS instances) through the setup wizard.

You can add your own connections to any workspace. Go to Workspace Settings → MCP Servers and click Create MCP Connection:

The MCP Servers page with the Create MCP Connection menu open
ConnectionWhat it gives agents
GitHubWork with your repositories: read files, create branches, commit, and open pull requests
Azure DevOpsThe same for Azure DevOps repositories
Sitecore XP and Sitecore XMCAccess to your Sitecore instances
FigmaRead your design files, components and comments
Custom MCPAny remote MCP server. Servers that sign in with OAuth open their sign-in in your browser when you click Connect.

Community MCP servers. Agents can find and install community MCP servers from the official MCP registry when you ask them to. Switch on Dynamic Tool Discovery in the agent's tools first. Every install needs your approval, and the server runs in the workspace sandbox.

Interactive results. Some connected servers, including Kajoo's own, return interactive widgets — such as reports and task cards — that show right in the chat.


Human-in-the-loop

Human-in-the-loop (HITL) is the control mechanism that determines how much agents do autonomously vs. how much requires your explicit approval.

Every tool an agent can call has a HITL setting:

SettingBehaviour
Auto-approveThe agent executes the tool call without asking. Used for low-risk read operations.
Approval requiredThe agent pauses and presents the proposed action for your review before executing. Used for write operations, commits, content pushes, and other high-impact actions.

In recipe workspaces, HITL settings are pre-configured based on the risk level of each tool. You can adjust any tool's setting at any time in the agent configuration panel.

On top of these settings, each chat has an approval mode, set from + in the message box:

ModeWhat happens
Default ApprovalsFollows each tool's setting above
Auto ApprovalsKajoo checks each action and runs the safe ones without asking. Risky ones, and every delete, come to you.
Bypass ApprovalsEvery action is approved automatically

On an approval card you can also choose Always approve in this session. See Working in chat.


Projects

Projects are the working areas inside a workspace. A workspace can have multiple projects — for example, one per client site or one per migration engagement.

Each project has its own chats where you interact with agents directly, a task list organized into phases, and scheduled jobs. A project can have multiple chats running simultaneously, which is how parallel workstreams (like running code migration and content migration at the same time) are supported.

⚠️

Don't run two code migration sessions in parallel within the same project. Code migration sessions share the same sandbox — concurrent sessions cause conflicts. Parallel sessions are safe for independent workstreams (e.g. code migration + content migration).


Tasks and phases

Each project's work is planned as tasks grouped into phases. You see them in the project's Plan panel, as a list or on a task board, next to an Overview of the artifacts pinned to the project. Agents read and update the same tasks as they work. A task's Start button opens a chat with an agent and hands the task over. See Tasks and phases.


Scheduled jobs

A scheduled job runs an agent on a schedule — hourly, daily, weekly, monthly or once — with instructions you write. Every run lands in the job's own chat. See Scheduled jobs.


Agent Units (AU)

Agent Units (AU) are the usage and billing unit for Kajoo Agentic. AU is an outcome-based measure — it reflects the delivery work completed, not raw AI consumption (tokens, runtime minutes, or infrastructure).

You don't need to think about AU while working. It's reported in your workspace usage dashboard. Pricing and AU details are available from your Kajoo contact or on the Kajoo pricing page.


Migration tools reference

These tools are available in every XP → SitecoreAI migration workspace. Call them directly from the chat window at any time.

ToolWhat it does
migration-workflow-docsPulls up the full workflow reference guide for your migration type
migration-workflow-statusReturns pipeline status — which phases are done, in progress, or blocked, and what to run next
migration-get-infoShows current workspace config — connectors, paths, site name, SitecoreAI environment details
migration-set-connectorsConfigures source/target connectors, repos, and SitecoreAI environment details
dev-server-startStarts the sandbox dev server
dev-server-set-modeSwitches the sandbox between mock mode and live mode
dev-server-set-envSets individual environment variables in .env.local

What's next

New to Kajoo Agentic?See Overview for what the platform does and who it's for
Ready to create a workspace?See Getting Started
Working with agents day to day?See Working in chat
Start a Sitecore migration?See Recipes

Did this page help you?