# AI agent terms, defined plainly. URL: https://www.getdynamiq.ai/glossary > Plain definitions of AI agent terms for enterprise teams: RAG, guardrails, evals, MCP, voice agents, self-hosting, SOC 2, the EU AI Act and more. What each term means, why it matters in regulated industries, and how it shows up in the Dynamiq platform. [A](https://www.getdynamiq.ai/glossary#letter-A) · [B](https://www.getdynamiq.ai/glossary#letter-B) · [C](https://www.getdynamiq.ai/glossary#letter-C) · [D](https://www.getdynamiq.ai/glossary#letter-D) · [E](https://www.getdynamiq.ai/glossary#letter-E) · [F](https://www.getdynamiq.ai/glossary#letter-F) · [G](https://www.getdynamiq.ai/glossary#letter-G) · [H](https://www.getdynamiq.ai/glossary#letter-H) · [I](https://www.getdynamiq.ai/glossary#letter-I) · [K](https://www.getdynamiq.ai/glossary#letter-K) · [L](https://www.getdynamiq.ai/glossary#letter-L) · [M](https://www.getdynamiq.ai/glossary#letter-M) · [O](https://www.getdynamiq.ai/glossary#letter-O) · [P](https://www.getdynamiq.ai/glossary#letter-P) · [R](https://www.getdynamiq.ai/glossary#letter-R) · [S](https://www.getdynamiq.ai/glossary#letter-S) · [T](https://www.getdynamiq.ai/glossary#letter-T) · [V](https://www.getdynamiq.ai/glossary#letter-V) · [W](https://www.getdynamiq.ai/glossary#letter-W) A [Agent memory](https://www.getdynamiq.ai/glossary/agent-memory) The system that lets an AI agent recall earlier conversation turns or durable facts across separate runs, scoped to a user and session. [Agent orchestration](https://www.getdynamiq.ai/glossary/agent-orchestration) The layer that decides which agent or step runs next, in what order and with what shared state, when a task needs more than one agent. [Agent sandbox](https://www.getdynamiq.ai/glossary/agent-sandbox) An isolated, disposable virtual machine an agent can use to run shell commands, execute code and write files, separate from production systems. [Agentic AI](https://www.getdynamiq.ai/glossary/agentic-ai) AI systems that pursue a goal by planning steps, calling tools and acting on the results, rather than only generating a response to a single prompt. [Agentic memory](https://www.getdynamiq.ai/glossary/agentic-memory) Memory an AI agent manages itself, deciding which facts to save, update or recall across sessions, instead of only replaying past conversation. [Agentic workflow](https://www.getdynamiq.ai/glossary/agentic-workflow) A business process modeled as a graph of steps where at least one step is an agent that reasons and chooses its own actions, not a fixed script. [AI agent](https://www.getdynamiq.ai/glossary/ai-agent) A system that pairs a large language model with tools, memory and a control loop so it can plan and carry out multi-step tasks toward a goal. [AI agent platform](https://www.getdynamiq.ai/glossary/ai-agent-platform) Software for building, deploying, governing and monitoring AI agents in one place, from models and tools to approvals, evaluations and traces. [AI gateway](https://www.getdynamiq.ai/glossary/ai-gateway) A single endpoint that routes chat completion requests to many model providers behind one credential, so applications do not hold provider keys. [AI governance](https://www.getdynamiq.ai/glossary/ai-governance) The policies, controls and evidence an organization uses to decide how AI may be used, who is accountable, and how its behavior is checked over time. [AI guardrails](https://www.getdynamiq.ai/glossary/ai-guardrails) Checks placed around a model or agent, such as input screening and output validation, that flag or block unsafe behavior before it reaches anyone. [AI observability](https://www.getdynamiq.ai/glossary/ai-observability) The practice of recording every step an agent or workflow takes so its behavior, cost and failures can be inspected after the fact. [Air-gapped deployment](https://www.getdynamiq.ai/glossary/air-gapped-deployment) A deployment with no network path to the public internet, used when data must never leave a physically or logically isolated environment. [Approval gate](https://www.getdynamiq.ai/glossary/approval-gate) A control on a specific workflow step that pauses execution until a person approves, edits or rejects it, every time that step runs. B [Barge-in and turn detection](https://www.getdynamiq.ai/glossary/barge-in-and-turn-detection) How a voice agent knows a caller has stopped talking, and how it stops speaking immediately if the caller interrupts. C [Chunking](https://www.getdynamiq.ai/glossary/chunking) Splitting a document into smaller pieces before it is embedded and indexed, so retrieval returns focused passages instead of whole files. [Computer use agent](https://www.getdynamiq.ai/glossary/computer-use-agent) An agent that operates a computer the way a person would, controlling a browser or desktop through clicks, typing and screenshots. [Context window](https://www.getdynamiq.ai/glossary/context-window) The maximum amount of text, measured in tokens, a model can read and generate in one call, including the prompt, history and output. [Conversational AI](https://www.getdynamiq.ai/glossary/conversational-ai) Technology that lets people talk with software in natural language, by text or voice, and have it understand the request and respond or act on it. D [Data residency](https://www.getdynamiq.ai/glossary/data-residency) A guarantee about which country or region a system stores and processes its data in, used to meet legal or contractual requirements. [Document parsing](https://www.getdynamiq.ai/glossary/document-parsing) Converting a file such as a PDF, scan or slide deck into clean, structured text, typically Markdown, that a model or index can use. E [Embeddings](https://www.getdynamiq.ai/glossary/embeddings) Numeric vectors that represent the meaning of a piece of text, so pieces with similar meaning end up close together in vector space. [EU AI Act](https://www.getdynamiq.ai/glossary/eu-ai-act) The European Union's risk-based regulation of AI systems, Regulation (EU) 2024/1689, with obligations that scale to how risky a given use is. F [Fine-tuning](https://www.getdynamiq.ai/glossary/fine-tuning) Further training a pretrained model on a smaller, specific dataset so it performs better on a narrower task, tone or domain. [Forward-deployed engineer](https://www.getdynamiq.ai/glossary/forward-deployed-engineer) An engineer who works inside a customer's own environment to build and ship the customer's first production use of a platform. G [GDPR](https://www.getdynamiq.ai/glossary/gdpr) The EU's General Data Protection Regulation, Regulation (EU) 2016/679, governing how personal data of people in the EU and EEA is handled. [GraphRAG](https://www.getdynamiq.ai/glossary/graphrag) A retrieval method that answers questions by walking a knowledge graph of entities and relationships, not only by matching text similarity. [Grounding](https://www.getdynamiq.ai/glossary/grounding) Tying a model's answer to specific, retrievable source material, so the answer can be traced back to a document rather than training data. H [Hallucination](https://www.getdynamiq.ai/glossary/hallucination) An answer a model states with confidence that is not supported by its source material or by fact, presented as if it were true. [HIPAA](https://www.getdynamiq.ai/glossary/hipaa) The US Health Insurance Portability and Accountability Act of 1996, whose Privacy and Security Rules govern protected health information. [Human in the loop](https://www.getdynamiq.ai/glossary/human-in-the-loop) A design pattern where a person reviews, confirms or supplies information at a defined point in an otherwise automated process. I [Intelligent document processing](https://www.getdynamiq.ai/glossary/intelligent-document-processing) Using AI to read unstructured documents such as scans, PDFs and forms and turn them into structured, validated data fields. K [Knowledge graph](https://www.getdynamiq.ai/glossary/knowledge-graph) A database of entities and the relationships between them, such as a person working at an organization, used to answer connection questions. [KYC and AML automation](https://www.getdynamiq.ai/glossary/kyc-and-aml-automation) Using software, including AI, to run the identity checks and transaction monitoring that anti-money-laundering and know-your-customer rules require. L [LLM as a judge](https://www.getdynamiq.ai/glossary/llm-as-a-judge) Using a large language model to score another model's output against a written rubric, in place of, or alongside, a human reviewer. [LLM evaluation](https://www.getdynamiq.ai/glossary/llm-evaluation) Scoring an LLM or agent's outputs against test data with defined metrics, so changes in quality are measured rather than judged by feel. [LLM inference](https://www.getdynamiq.ai/glossary/llm-inference) Running a trained model to produce an output for a given input, as opposed to training the model in the first place. [LLM tracing](https://www.getdynamiq.ai/glossary/llm-tracing) A recorded, node-by-node execution tree of one run, including every prompt, tool call, retrieved document and token count. [LoRA](https://www.getdynamiq.ai/glossary/lora) Low-Rank Adaptation, a fine-tuning method that trains a small set of extra weights on top of a frozen base model, not the whole model. M [Model Context Protocol (MCP)](https://www.getdynamiq.ai/glossary/model-context-protocol) An open protocol that lets an AI agent discover and call tools exposed by an external server over a standard interface. [Model routing](https://www.getdynamiq.ai/glossary/model-routing) Automatically or programmatically directing a request to one of several possible models, based on name, cost, capability or availability. [Multi-agent system](https://www.getdynamiq.ai/glossary/multi-agent-system) Two or more agents working together on one task, each with a narrower role, coordinated by delegation or an explicit control flow. O [Online evaluation](https://www.getdynamiq.ai/glossary/online-evaluation) Automatically scoring a sampled share of a deployed system's live production traffic on an ongoing basis, not a one-time test. [Open-weight model](https://www.getdynamiq.ai/glossary/open-weight-model) A model whose trained weights are published for anyone to download and run, unlike a model only reachable through a hosted API. P [PII detection](https://www.getdynamiq.ai/glossary/pii-detection) Automatically flagging personally identifiable information, such as names, emails or account numbers, before it reaches a model. [Prompt injection](https://www.getdynamiq.ai/glossary/prompt-injection) An attempt, hidden in user input or a retrieved document, to override a model's instructions and make it act against its role. R [Reranking](https://www.getdynamiq.ai/glossary/reranking) Re-scoring and reordering a first pass of retrieved documents with a more precise model, so the most relevant ones reach the model first. [Retrieval-augmented generation (RAG)](https://www.getdynamiq.ai/glossary/retrieval-augmented-generation) Retrieving relevant passages from your own documents and giving them to a model as context, so its answer is grounded in that material. [Role-based access control (RBAC)](https://www.getdynamiq.ai/glossary/role-based-access-control) Granting permissions based on a person's assigned role, such as admin or member, rather than configuring access for each person. S [Self-hosted AI platform](https://www.getdynamiq.ai/glossary/self-hosted-ai-platform) An AI platform installed and run inside an organization's own infrastructure, cloud account or data center, not a vendor's shared cloud. [Single sign-on (SSO)](https://www.getdynamiq.ai/glossary/single-sign-on) Letting people log in to a platform using the identity and credentials their organization already manages, not a separate password. [SIP trunking](https://www.getdynamiq.ai/glossary/sip-trunking) A connection between a phone network and a voice application over the internet using the Session Initiation Protocol, not analog lines. [SOC 2](https://www.getdynamiq.ai/glossary/soc-2) An audit standard from the AICPA evaluating a service organization's controls against the Trust Services Criteria: security, plus optional categories. [Sovereign AI](https://www.getdynamiq.ai/glossary/sovereign-ai) AI that an organization or country controls end to end: where it runs, which models it uses, where its data and records live, and who operates it. [Speech to text](https://www.getdynamiq.ai/glossary/speech-to-text) Converting spoken audio into written text in real time, the first stage of a pipeline voice agent's turn. [Structured output](https://www.getdynamiq.ai/glossary/structured-output) Constraining a model's final answer to a JSON schema, so downstream code receives typed, parseable data instead of free-form prose. T [Text to speech](https://www.getdynamiq.ai/glossary/text-to-speech) Converting written text into spoken audio, the final stage of a pipeline voice agent's turn, or one channel of a realtime model. [Tool calling](https://www.getdynamiq.ai/glossary/tool-calling) A model's ability to invoke a defined function or external action mid-response, then read the result back before continuing. V [Vector database](https://www.getdynamiq.ai/glossary/vector-database) A database built to store embeddings and search them by similarity, returning the nearest vectors to a query, not exact matches. [Voice agent](https://www.getdynamiq.ai/glossary/voice-agent) A real-time conversational agent that talks with people over audio, on a phone call, in a browser, or over a raw audio connection. W [WebRTC](https://www.getdynamiq.ai/glossary/webrtc) An open, browser-native protocol for real-time audio and video that lets a web page or app stream microphone audio to a voice agent. ## See an agent on your own workflow. Bring a process and its documents. Our engineers will show you how Dynamiq runs it, in your environment or ours. [Start free](https://app.getdynamiq.ai/signup) · [Talk to the team](https://www.getdynamiq.ai/book-a-demo)