AI UX Glossary: Terms for Designers & PMs

Source: AI UX Playground glossary · undated

AI product design is the practice of shaping how people understand, trust, and control AI-powered features, not only how they look.

AI UX (AI user experience) is how people perceive and interact with AI features: streaming replies, tool pickers, citations, autonomy, memory, and recovery when something goes wrong.

In AI product teams, a design engineer sits between design and code, prototyping AI flows in real stacks, defining motion and states agents must preserve, and reviewing generated UI for trust and craft.

Chain of thought (CoT) is a prompting approach where the model shows intermediate reasoning steps before the final answer.

Context assembly is how a product builds the full prompt stack before send: system rules, @-mentioned files, retrieved docs, memory, and the user’s message combined into one model request.

Few-shot prompting includes a small number of example input/output pairs in the prompt so the model mimics your format, tone, or decision style.

Multimodal input lets users combine text with images, audio, video, or files in one request so the model can reason across media types.

Progressive disclosure reveals AI output in layers: summary first, details on expand, advanced controls only when needed.

A prompt is the instruction or question you give an AI model: the user message, template, or form that tells it what to do.

Grounding in UX is how an interface ties AI answers to verifiable sources, documents, URLs, files, or tool results. So users can check claims.

Retrieval-augmented generation (RAG) retrieves relevant documents or records first, then asks the model to answer using that material.

Capability disclosure is the practice of telling users. In plain language. What an AI feature can and cannot do before and during use.

Explainability is how clearly an AI product shows why it produced an answer: sources, reasoning steps, confidence, or feature influence.

Guardrails are rules, filters, and policies that block unsafe inputs, limit risky outputs, and keep AI behavior aligned with product and brand standards.

A hallucination is when an AI states something confidently that is false, outdated, or unsupported by its inputs.

Human-in-the-loop (HITL) means a person reviews, approves, or corrects AI output before it affects users, records, or systems.

Moderation is the process of detecting and handling harmful, abusive, off-brand, or policy-violating content in AI inputs and outputs.

A2A (agent-to-agent) communication is when one AI agent delegates tasks, shares context, or negotiates outcomes with another agent instead of only talking to the user.

An action receipt is a plain-language record of what an agent did, when, and with what permissions, like a bank notification, not a server log.

An agent is an AI system that plans steps, uses tools, and acts across multiple turns to complete a goal, not just answer a question.

Agentic UX is the design of interfaces for software that plans and acts on a user's behalf, tools, files, APIs, and multi-step workflows, not only text replies.

An autonomy slider lets users set how independently an agent may act, from suggest-only to draft to execute, often per task or surface.

An agent skill is packaged, reusable expertise an AI assistant loads for a specific job, accessibility audit, PRD draft, Figma handoff, without the user rewriting instructions each time.

An AI-native design system encodes tokens, components, and rules that both designers and coding agents can consume, often via DESIGN.md, SKILL.md, or structured exports.

Design.md is a markdown file that captures design system rules, component usage, tokens, and UX standards for humans and AI agents building your product.

Generative UI (GenUI) is when AI produces live interface elements (forms, dashboards, cards, charts) from prompts or data, not just static text.

AI evals are automated or human frameworks that measure model accuracy, bias, safety, and task performance before and after you ship.

Latency is the delay between a user action and a usable AI response: time to first token, time to complete answer, or time to finish an agent run.