> ## Documentation Index
> Fetch the complete documentation index at: https://docs.plaisolutions.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Concepts Overview
> Understand PLai Framework's architecture and how concepts fit together
Everything nests inside something else: an organization holds one or more projects, and each project holds the agents, tools, datasources, and automation that use them. The hierarchy below starts at the top and drills down to the pieces you'll configure day to day.
***
## PLai Architecture
* **Organization Level**
* Organizations (Teams)
* Projects (Workspaces)
* Members & Roles
* Organization Settings
* Invitations
* Billing
* Team Management
* **Project Level** (Inside Each Project)
* Agents (AI Workers)
* Tools (Service Integrations)
* Datasources (Knowledge Bases)
* Workflows (Multi-step Automation)
* Jobs (Scheduled Execution)
* Triggers (Event-based Automation)
* Monitor (Project Analytics & Metrics)
* **User Level** (Global)
* Profile & Account Settings
***
## The Five Core Concept Groups
Structure, team management, and workspace isolation
The building blocks you create and configure
How to automate and schedule your work
Access control, credentials, and safety guardrails
Project-level analytics, metrics, and performance tracking
***
## Understanding the Hierarchy
### Level 1: Organizations & Projects
**Scope:** Organization-wide structure
Where you live:
* **Organizations** - Top-level container for your team
* **Projects** - Isolated workspaces where you do the actual work
* **Members** - People with roles (OWNER, ADMIN, VIEWER)
Everything else happens inside a Project.
🔗 **Read more:** [Organizations & Projects](./organizations-and-projects.mdx)
***
### Level 2: Building Blocks
**Scope:** Inside a Project
What you create:
* **Agents** - AI assistants that perform tasks
* Configuration: Model, system instructions, capabilities
* Properties: Name, description, role-based settings
* **Tools** - External services agents can use
* Types: API Requests, Web Search, Browser, MCP Servers, Datasources
* Purpose: Extend agent capabilities
* **Datasources** - Knowledge bases for agents
* Types: Files, URLs, Websites, Content
* Purpose: Provide context and facts to agents
🔗 **Read more:** [Agents, Datasources & Tools](./agents-datasources-and-tools.mdx)
***
### Level 3: Automation
**Scope:** Inside a Project
How you scale:
* **Workflows** - Multi-step sequences combining agents and tools
* Example: Route customer → Sales Agent → CRM Tool → Response
* **Jobs** - Scheduled executions
* Example: Run data processing every day at 2 AM
* **Triggers** - Event-based automation
* Types: Webhook, Schedule, Manual
* Example: Process form submission automatically
🔗 **Read more:** [Workflows, Jobs & Triggers](./workflows-jobs-and-triggers.mdx)
***
### Level 4: Safety & Access
**Scope:** Spans Organization and Project
How you protect:
* **Roles & Permissions** - Who can do what (RBAC)
* Organization roles control team access
* Project roles control resource access
* **Credentials** - Securely store secrets
* API keys, passwords, tokens
* Encrypted storage, audit logged
* **Guardrails & Answer Filters** - Safety constraints
* Content filtering
* Rate limiting
* Compliance rules
🔗 **Read more:** [Security & Compliance](./security-and-compliance.mdx)
***
### Level 5: Observability
**Scope:** Project-level
How you understand what's happening:
* **Metrics** - Performance data
* Speed, accuracy, success rates, errors
* **Analytics** - Usage patterns
* Agent activity, tool usage, workflow performance
* **Activity Logs** - Audit trail
* Who did what, when, and what changed
🔗 **Read more:** [Monitoring](./monitoring.mdx)
***
## Decision Tree: Which Concept Do I Need?
**I want to organize my team**
↓
→ [Organizations & Projects](./organizations-and-projects.mdx)
**I want to create AI agents**
↓
→ [Agents, Datasources & Tools](./agents-datasources-and-tools.mdx)
**I want to automate workflows**
↓
→ [Workflows, Jobs & Triggers](./workflows-jobs-and-triggers.mdx)
**I want to control access or store secrets**
↓
→ [Security & Compliance](./security-and-compliance.mdx)
**I want to track performance and costs**
↓
→ [Monitoring](./monitoring.mdx)
***
## Quick Reference: Typical User Journeys
### Journey 1: Getting Started
1. **Understand structure** → [Organizations & Projects](./organizations-and-projects.mdx)
2. **Invite your team** → [Organizations & Projects](./organizations-and-projects.mdx) (Roles section)
3. **Create first agent** → [Agents, Datasources & Tools](./agents-datasources-and-tools.mdx)
4. **Add knowledge** → [Agents, Datasources & Tools](./agents-datasources-and-tools.mdx) (Datasources section)
### Journey 2: Going to Production
1. **Set up security** → [Security & Compliance](./security-and-compliance.mdx)
2. **Configure guardrails** → [Security & Compliance](./security-and-compliance.mdx) (Guardrails section)
3. **Monitor performance** → [Monitoring](./monitoring.mdx)
4. **Audit access** → [Monitoring](./monitoring.mdx) (Logs section)
### Journey 3: Scaling Up
1. **Build workflows** → [Workflows, Jobs & Triggers](./workflows-jobs-and-triggers.mdx)
2. **Schedule jobs** → [Workflows, Jobs & Triggers](./workflows-jobs-and-triggers.mdx) (Jobs section)
3. **Set up triggers** → [Workflows, Jobs & Triggers](./workflows-jobs-and-triggers.mdx) (Triggers section)
4. **Track results** → [Monitoring](./monitoring.mdx)
***
## Key Mental Models
### Model 1: Container Nesting
* **Organization**
* **Project 1**
* Agent A
* Tool X
* Datasource D
* **Project 2**
* Agent B
* Agent C
* Tool Y
**Rule:** Members of Organization see all Projects they're invited to. Members of a Project see only that Project's resources.
### Model 2: Separation of Concerns
* **Org Level** (Who + What Access)
* Organizations & Projects
* Members & Roles
* Organization Settings
* **Project Level** (What You Build & Run)
* Agents, Tools, Datasources
* Workflows, Jobs, Triggers
* Monitor (Performance)
* **Security** (Spans Both)
* Credentials
* Guardrails
* Activity Logs
### Model 3: Data Flow
1. **Datasource (Knowledge)** and **User Input** feed into the **Agent**
2. **Agent → Tool → External Service** — filtered/validated by **Guardrails** along the way
3. **Result → Monitor** (Track) **→ Analytics Dashboard**
***
## Important Reminders
**Start small.** You don't need Workflows, Jobs, and Triggers right away. Begin with Agents and Tools, then add automation as you grow.
**Everything is project-scoped.** What happens in Project A stays in Project A. Other projects don't see it.
**Security matters early.** Set up guardrails and credentials management before going to production, not after.
**Monitor from day one.** It's easier to understand costs and performance from the start than to debug problems later.
***
## Next Steps
1. **Understand your structure** → Read [Organizations & Projects](./organizations-and-projects.mdx)
2. **Create your first agent** → Go to [Agents, Datasources & Tools](./agents-datasources-and-tools.mdx)
3. **Follow the tutorial** → Check out [Create Your First Agent](../../guides/first-agent.mdx)
Or jump directly to the concept group you need most:
* **[Organizations & Projects](./organizations-and-projects.mdx)** - Team structure, roles, workspace management
* **[Agents, Datasources & Tools](./agents-datasources-and-tools.mdx)** - Building your AI workers
* **[Workflows, Jobs & Triggers](./workflows-jobs-and-triggers.mdx)** - Automating at scale
* **[Security & Compliance](./security-and-compliance.mdx)** - Protecting your data and access
* **[Monitoring](./monitoring.mdx)** - Tracking performance and costs