Glossary
AI agent glossary
Plain-English definitions for the terminology behind AI agent platforms — what each term means, how it works, and where it shows up in AgentWorks.
All terms
Definition
Agent observability
Agent observability is the practice of capturing what an AI agent did, why it did it, and how well it did it, in a form that engineers can search and reviewers can audit. It combines three pillars: logs (the steps), traces (the causal chain across LLM calls and tools), and evals (continuous scoring of output quality).
Read definitionDefinition
Agent-to-agent protocol(A2A)
An agent-to-agent (A2A) protocol is a standardised way for AI agents — potentially built by different vendors, on different stacks — to discover each other, exchange tasks, and report results. Where tool calling lets one agent invoke deterministic functions, A2A lets one agent delegate to another autonomous agent that may itself plan, use tools, and call other agents.
Read definitionDefinition
AI agent
An AI agent is a software program that uses a large language model (LLM) to autonomously plan and complete a task, combining reasoning, tool use, and memory. Unlike a one-shot prompt, an agent can break a goal into steps, call external tools or APIs, and decide what to do next based on intermediate results.
Read definitionDefinition
AI agent management
AI agent management is the discipline of operating AI agents at scale — covering deployment, role-based access, budget allocation, performance monitoring, audit logging, and lifecycle (retire, refresh, replace). It is to AI agents what fleet management is to vehicles or what DevOps is to software services.
Read definitionDefinition
AI agent platform
An AI agent platform is software that lets organizations build, deploy, govern, and monitor AI agents at scale — typically with a workspace UI, multi-LLM access, knowledge bases, integrations, scheduling, and audit logging. The platform replaces the need for each team to assemble agent infrastructure from raw frameworks.
Read definitionDefinition
AI workforce
An AI workforce is the practice of running multiple AI agents under shared governance, budgets, and access controls — treating them as a coordinated digital workforce rather than isolated tools. The term reframes AI from "feature inside one app" to "set of workers your organization manages centrally."
Read definitionDefinition
Chunking strategy
A chunking strategy is the algorithm a RAG pipeline uses to split source documents into the pieces ("chunks") it will later embed, store, and retrieve. Chunking is the single biggest determinant of RAG quality: poor chunking puts the right answer in the wrong slice and no embedding model can recover it. There is no universal optimum — strategy must match document type, query pattern, and embedding model context window.
Read definitionDefinition
EU AI Act Article 12 (Record-keeping)
Article 12 of the EU AI Act requires high-risk AI systems to automatically record events ("logs") throughout their lifecycle, in a form that enables traceability of the system's functioning. Logs must capture timestamps, inputs, outputs, tools invoked, and human decisions — enough that an inspector can reconstruct what happened on any given run.
Read definitionDefinition
General Purpose AI(GPAI)
General Purpose AI (GPAI) under the EU AI Act is an AI model that displays significant generality and can perform a wide range of distinct tasks — large language models like GPT-4o, Claude, Gemini, and Mistral all qualify. GPAI providers carry specific obligations on technical documentation, training-data summaries, copyright compliance, and (above 10^25 FLOPs of training compute) systemic-risk controls.
Read definitionDefinition
Human-in-the-loop(HITL)
Human-in-the-loop (HITL) is a design pattern where a human reviewer must approve, edit, or veto an AI agent's output before it executes a consequential action. The agent pauses, surfaces what it is about to do, waits for the human, and then proceeds — a deliberate brake to keep autonomy bounded.
Read definitionDefinition
Model Context Protocol(MCP)
Model Context Protocol (MCP) is an open standard introduced by Anthropic in 2024 that defines how AI agents connect to external data sources and tools. MCP servers expose data and capabilities; MCP clients (LLMs and agent platforms) discover and call them through a uniform interface — eliminating per-tool custom integration code.
Read definitionDefinition
Multi-agent orchestration
Multi-agent orchestration is the practice of chaining multiple specialized AI agents into a single workflow, where each agent has a defined role (researcher, writer, reviewer, publisher) and outputs flow from one agent to the next. The orchestrator decides the order, handles retries, and enforces guardrails between steps.
Read definitionDefinition
Multi-LLM chat
Multi-LLM chat is a chat interface that lets you switch between multiple large language model vendors — OpenAI (GPT), Anthropic (Claude), Google (Gemini), Mistral, and others — inside a single conversation thread. You pick the model best suited to the next turn instead of being locked into one vendor for the whole task.
Read definitionDefinition
Prompt governance
Prompt governance is the operational discipline of treating production prompts (system prompts, tool descriptions, eval rubrics) as code: version-controlled, reviewed before merge, tested against fixed cases, and rollback-ready when production behaviour regresses. Without it, prompt changes drift, regressions compound, and the team loses the ability to explain why the agent behaves as it does.
Read definitionDefinition
Prompt injection
Prompt injection is an attack where untrusted text fed to an LLM overrides the developer's instructions, causing the model to leak data, call unauthorised tools, or follow attacker goals. It is the LLM equivalent of SQL injection and ranks #1 on the OWASP Top 10 for LLM applications because there is no model-level fix — defence requires layered controls outside the model.
Read definitionDefinition
Retrieval-Augmented Generation(RAG)
Retrieval-Augmented Generation (RAG) is a technique that grounds a large language model in a specific corpus of documents at query time. Instead of relying only on what the model learned during training, RAG retrieves relevant passages from your data and adds them to the prompt — letting the model answer using your knowledge, current and proprietary.
Read definitionDefinition
Role-Based Access Control(RBAC)
Role-Based Access Control (RBAC) for AI is a security model that grants permissions to AI agents and AI users based on roles rather than individuals. A "marketing analyst" role can run a defined set of agents, read certain knowledge bases, and call approved tools — and changes to the role propagate to everyone who holds it.
Read definitionDefinition
Tool calling
Tool calling (also "function calling") is the LLM capability that lets a model emit a structured request to execute an external function, receive the result, and incorporate it into the next response. It is the technical primitive that turns a passive chatbot into an active agent — without tool calling, an LLM can only talk; with it, it can act.
Read definition