The Agentic AI knowledge graph
A precise, interconnected encyclopedia of the concepts behind Agentic AI Operating Systems. Every term links to related concepts and to the GFO frameworks that put them into practice.
Foundations
Agentic AI
Agentic AI refers to AI systems capable of planning, selecting tools, executing multi-step tasks and adapting their actions toward a defined objective, rather than only responding to a single prompt.
AI Agent
AI Agent is a software system that uses a language model to reason about a task, call tools and take actions to complete it, operating within defined permissions and oversight.
Large Language Model
Large Language Model is an AI model trained on large volumes of text to understand and generate language, providing the reasoning and language ability at the core of an AI agent.
Retrieval-Augmented Generation
Retrieval-Augmented Generation is a technique that grounds a language model's output in retrieved documents, so answers reflect trusted, current and permissioned data rather than the model's memory alone.
Tool Calling
Tool Calling is the mechanism by which a language model invokes defined functions or APIs — to retrieve data or take actions — turning a model that only generates text into an agent that can act.
Knowledge Base
Knowledge Base is the curated, permissioned store of an organization's documents and data that an AI system retrieves from — through Retrieval-Augmented Generation — to answer questions and act on grounded, current facts rather than guesses.
Vector Database
Vector Database is a system that stores information as numerical embeddings so an AI can retrieve it by semantic similarity — finding content by meaning rather than exact keywords — which is what makes Retrieval-Augmented Generation practical at scale.
Prompt Engineering
Prompt Engineering is the practice of designing the instructions, context and constraints given to a language model so it produces reliable, relevant and safe output for a defined task.
Fine-Tuning
Fine-Tuning is the process of further training a base language model on a curated set of examples so it better matches a specific domain, style or task, adjusting the model's own weights rather than only its instructions.
Systems & Orchestration
AI Operating System
AI Operating System is a secure orchestration layer that coordinates specialized AI agents, business data, enterprise applications and human approvals to execute multi-step business workflows.
AI Orchestration
AI Orchestration is the coordination layer that decides which AI agent or tool handles each step of a workflow, passes context between them and inserts human approvals where required.
Multi-Agent System
Multi-Agent System is a system in which several specialized AI agents, each with a defined role, collaborate — coordinated by an orchestration layer — to complete work that exceeds a single agent's scope.
Model Context Protocol (MCP)
Model Context Protocol (MCP) is an open standard that defines a consistent way for AI systems to connect to external tools, data sources and services — so integrations are reusable and governed rather than bespoke for every system.
Workflow Automation
Workflow Automation is the execution of predefined, rule-based sequences of steps across systems — reliable and deterministic for structured processes, but limited to the paths explicitly designed in advance.
AI Workforce
Autonomous AI Workforce
Autonomous AI Workforce is a coordinated set of specialized AI agents — sometimes called AI employees or digital workers — that handle defined business tasks under human oversight and governance.
Enterprise AI
Enterprise AI is the application of artificial intelligence inside organisations under real-world constraints — security, governance, system integration, reliability and accountability — rather than in isolated experiments.
Digital Employee
Digital Employee is a specialized AI agent framed as a team member with a defined role, responsibilities and boundaries — such as a sales or support AI — that works alongside people under governance and supervision.
Governance, Security & Trust
Human-in-the-Loop
Human-in-the-Loop means a person reviews, approves or can override an AI system's consequential actions before they take effect, keeping accountability and judgement with humans.
AI Governance
AI Governance is the set of policies, roles, boundaries and controls that keep AI systems accountable, compliant and aligned with business intent throughout their lifecycle.
Enterprise AI Security
Enterprise AI Security is the discipline of protecting the data, identities and actions involved in AI systems — through least-privilege access, encryption, isolation, auditability and human approval.
AI Observability
AI Observability is the ability to see, log and evaluate what AI agents do — their inputs, actions, outcomes and errors — so systems remain reliable, auditable and improvable.
AI Guardrails
AI Guardrails are the technical and policy controls that constrain what an AI system is allowed to say and do — enforcing boundaries, blocking unsafe actions and routing sensitive decisions to people.
AI Hallucination
AI Hallucination is a confident but false or unsupported output produced by a language model — plausible-sounding text that is not grounded in fact — which is why enterprise AI must combine grounding, guardrails and human oversight.
Prompt Injection
Prompt Injection is an attack in which malicious instructions are hidden inside content an AI system processes — an email, a document, a web page — attempting to override its rules and trigger unintended actions.
Apply these concepts to your business
Book a confidential, executive-led session to see how an Agentic AI Operating System works in your France business.