AI Glossary

AI Glossary: Agents & Tool Use

Fearghal

07 May 2026 — 2 min read

The agentic paradigm represents a fundamental shift from reactive chatbots to proactive AI systems that can plan and execute multi-step tasks.

AI Agents / Agentic AI

Systems autonomously planning, deciding, and acting to accomplish goals—moving beyond single-response chatbots to multi-step problem solvers. Combine LLMs (reasoning), tools (actions), and memory (context). 2024 was called "the year of agents."

Reference: Russell, S. & Norvig, P., "Artificial Intelligence: A Modern Approach", Prentice Hall, 1995 (4th ed. 2020)
Classical: Wooldridge, M. & Jennings, N.R., "Intelligent Agents: Theory and Practice", The Knowledge Engineering Review 10(2), 1995
LLM-based: Wang, L. et al., "A Survey on Large Language Model based Autonomous Agents", 2023

Tool Use / Function Calling

LLM capability to invoke external tools, APIs, or functions. Models decide when to call tools, generate formatted arguments, and incorporate results. Transforms LLMs from passive assistants into active agents taking real-world actions.

Reference: Schick, T. et al., "Toolformer: Language Models Can Teach Themselves to Use Tools", 2023
Industry: OpenAI, "Function calling and other API updates", June 2023

ReAct (Reasoning and Acting)

Prompting framework alternating between reasoning steps (thinking through what to do) and action steps (executing tools). Creates transparent decision-making process. ReAct-style patterns are foundational to modern agent architectures.

Reference: Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y., "ReAct: Synergizing Reasoning and Acting in Language Models", ICLR 2023

Multi-Agent Systems

Architectures where multiple specialized agents collaborate—"researcher" gathers information, "analyst" processes it, "writer" produces output. Enable parallel processing and specialization. Frameworks: AutoGen, LangGraph.

Reference: Wooldridge, M. & Jennings, N.R., "Intelligent Agents: Theory and Practice", The Knowledge Engineering Review 10(2), 1995
LLM-based: Guo, T. et al., "Large Language Model based Multi-Agents: A Survey of Progress and Challenges", 2024

Orchestration

Coordinating execution flow between AI components, tools, and services. Systems like LangChain and CrewAI handle logic of when to call which component, manage state, handle errors, and combine results. Critical for complex AI applications.

Reference: ⚠️ No single authoritative foundational paper — industry/framework concept.
Reference: IBM, "What is LLM Orchestration?", 2024

This glossary is part of a series covering AI and LLM concepts for product designers.

AI Glossary: Infrastructure & Deployment

Understanding infrastructure helps designers appreciate performance constraints, cost considerations, and deployment options that affect product decisions. Hardware & Serving GPU (Graphics Processing Unit) Specialized processor for parallel calculations, dominant hardware for AI. GPUs excel at thousands of simultaneous calculations essential for neural networks. NVIDIA's H100 and A100 are

AI Glossary: Human-AI Interaction & UX Design

This is probably the most important part of the glossary for designers and these patterns and principles are directly relevant to product design practice. Understanding them enables the creation of AI experiences that are useful, usable, and appropriately trusted. Interaction Patterns Conversational UI Interface paradigm where interaction occurs through natural

AI Glossary: Safety, Alignment & Evaluation

These concepts are critical for responsible AI product development—understanding failure modes, safety measures, and evaluation approaches directly informs design decisions. Safety Concepts AI Safety The interdisciplinary field preventing accidents, misuse, or harmful AI consequences. Encompasses alignment research, risk monitoring, robustness, and developing norms for beneficial AI operation. Reference: Amodei,

AI Glossary: Training, Fine-Tuning & Data

Understanding how models are built and adapted helps designers recognize capability sources, appreciate customization options, and understand training-related behaviors and limitations. Pre-Training Concepts Pre-training The initial, computationally intensive phase of training on massive unlabeled text. During pre-training, models learn language patterns, grammar, factual knowledge, and reasoning capabilities by processing billions