Digital Employee Architecture
Overview
The Digital Employee system is an AI-powered automation platform built upon the GL SDK, which provides foundational capabilities including GL AIP (AI Agent Platform), GL Memory, GL Connectors, GL Pipeline, GL Skills, and GL Deep Research. It enables autonomous workflow execution through an orchestration pipeline managed by the Digital Employee (DE) Core SDK.
To learn more about the digital employee, please refer to the Digital Employee GitBook.
Core Components
The architecture consists of five primary layers, supported by cross-cutting concerns:
1. GL SDK (Foundation Layer)
The lowest layer providing core platform capabilities: GL AIP for agent intelligence, GL Memory for persistent context, GL Connectors for external integrations, GL Pipeline for workflow execution, GL Skills for reusable capabilities, and GL Deep Research for advanced information retrieval.
2. Chatbots Layer
Sits above the GL SDK and includes GLChat and other chatbot services, providing conversational interfaces that the digital employees can leverage.
3. Digital Employee (DE) Core SDK
The middleware layer containing the core orchestration engine. It includes the Orchestrator, Pipeline (with Steps), State management, Agent runtime, Identity management, and Configuration services.
4. Digital Employee Instances
Specific digital employee implementations built on top of the DE Core SDK, such as DE HR (the HR Recruiter), DE IT Support, and DE HR Payroll. Each instance leverages the core SDK to perform domain-specific tasks.
5. Client Applications (Claudia)
The user interaction layer through which human users engage with digital employees via Web, WhatsApp, and Mobile & Web Apps.
Cross-Cutting Concerns
The architecture is supported by platform-wide capabilities spanning all layers: Security, Privacy, Compliance, Observability, Tools & Services, No Code configuration, and Multimodal Models & Fine-Tuned Models.
Agent Components
One of the crucial components in a digital employee is the agent. The agent itself has its own components, some of which are Model Context Protocol (MCP) and Tools — many of which are already provided by GL Connectors.
Model Context Protocol (MCP)
The Digital Employee application uses Model Context Protocol (MCP) services to enable agents to interact securely with external systems and services. MCPs are managed through the AIP and use HTTP transport.
Google Workspace Integration
The system integrates with Google Workspace services using API Key authentication (X-API-Key header).
Google Calendar
Calendar Operations
Manages calendar events, schedules interviews, and coordinates meetings.
Google Docs
Document Operations
Handles document creation, editing, and management for recruitment workflows.
Google Drive
File Operations
Enables storage, retrieval, and management of recruitment documents.
Google Mail
Email Operations
Facilitates sending candidate communications and managing recruitment emails.
Google Sheets
Spreadsheet Operations
Manages recruitment data tracking and reporting via spreadsheets.
External Platform Integration
In addition to Google Workspace, the system connects to specialized enterprise platforms.
SQL Tool MCP
Description: Connects to CATAPA's digital_employee PostgreSQL database.
Transport: HTTP.
Authentication: Custom Headers (Bearer token, X-Api-Key, and X-Bosa-Integration headers).
Purpose: Provides direct access to query and manage recruitment data stored in CATAPA's database system.
Tools Framework
Digital employees utilize "Tools" to interact with applications outside the scope of MCPs (for example, the CATAPA API). Tools are categorized into two types: Built-in Tools and User-Defined Tools.
Built-in Tools
Generic, pre-configured collections provided by the AI Agent Platform. Designed for ease of use without coding. These are some of the built-in tools:
date_range_tool: Utility for handling date ranges.cv_extractor_tool: Utility for extracting information from Curricula Vitae.time_tool: Utility for time management.
User-Defined Tools
Custom tools created to handle specific tasks not covered by generic tools. Implemented as single-file Python code. These are some of the user-defined tools:
get_employee_info_tool: Retrieves specific employee information.update_candidate_phase_tool: Updates the recruitment phase of a candidate.detect_sister_company_tool: Logic to detect associated sister companies.
Key Benefits
Automation
Significantly reduces manual intervention by enabling scheduled operations.
Integration
Offers seamless connectivity with Google Workspace and other enterprise systems.
Flexibility
Features an extensible architecture that supports both standard (Built-in) and custom (User-Defined) tools.
Scalability
The MCP-based architecture allows for the easy addition of new services and capabilities as needs evolve.
Last updated