Glossary
Plain definitions of the terms used in AI user testing and research.
User research
How teams learn what people need, and what changes when the participants are AI.
- Heuristic evaluation
- Also called expert review, design review, UX audit
- Heuristic evaluation is an expert review of an interface against a set of principles, such as Nielsen’s ten usability heuristics, that lists each problem found and the principle it breaks.
- Sycophancy in synthetic research
- Also called AI sycophancy, LLM sycophancy
- Sycophancy is the tendency of language models to tell the person asking what they seem to want to hear. In synthetic research it shows up as simulated users who like every concept they are shown.
- Synthetic research
- Also called synthetic user research, AI-led user research
- Synthetic research is user research run with AI participants instead of recruited people: interviews, usability tasks and studies where the participants are personas played by AI agents.
- Synthetic users
- Also called AI users, simulated users, AI personas
- Synthetic users are AI agents given a persona (a background, goals and constraints) that stand in for real users in research or testing.
- Think-aloud protocol
- Also called think aloud, concurrent think-aloud
- The think-aloud protocol asks a participant to say what they are thinking as they work through a task, so a researcher hears the reasoning behind each click, not only the click.
- Usability testing
- Also called user testing, moderated usability testing, unmoderated usability testing
- Usability testing watches people attempt real tasks in a product to find where they hesitate, make mistakes or give up.
- User persona
- Also called persona, AI persona
- A user persona is a profile of a type of person a product serves: who they are, what they are trying to do, what they know already and what gets in their way.
Testing and quality
How teams check that a product still works, from scripted tests to users in a real browser.
- AI user testing
- Also called AI usability testing, automated user testing
- AI user testing sends AI agents with defined personas through a product in place of recruited participants, and reports what each one did and where it got stuck.
- End-to-end testing
- Also called E2E testing, browser automation testing
- End-to-end testing runs a scripted path through a whole application, from the interface to the database and back, to check that the parts work together the way a user would meet them.
- Prototype testing
- Also called Figma prototype testing, concept testing
- Prototype testing puts an unfinished design in front of users to see whether they can complete the key tasks before anything is built.
- Synthetic monitoring
- Also called synthetic checks, active monitoring
- Synthetic monitoring runs scripted checks against a live site on a schedule, from outside, to catch outages and slow pages before real visitors meet them.
- UX regression testing
- Also called experience regression testing, continuous UX testing
- UX regression testing checks, after every change, that the flows users depend on still work and still make sense, not only that the code still passes.
AI agents and the web
The words for agents that use websites on someone’s behalf, and what makes a site easy for them.
- Agent experience (AX)
- Also called AX, agentic experience
- Agent experience is how well an AI agent can use a product on someone’s behalf: find what it needs, understand the page, and finish the task without a person stepping in.
- Agentic commerce
- Also called agent-led shopping, AI shopping agents
- Agentic commerce is buying and booking done by an AI agent on a person’s behalf: the agent searches, compares the options and completes the checkout, and the person approves the result.
- Browser agent
- Also called computer-use agent, web agent
- A browser agent is an AI model that operates a web browser: it reads the page, decides on an action such as a click or a keystroke, performs it, and repeats until the task is done.
- llms.txt
- llms.txt is a plain-text Markdown file at the root of a website that tells language models what the site is and links to the pages worth reading, in a form that is cheap to fetch and parse.
- Model Context Protocol (MCP)
- Also called MCP, MCP server
- The Model Context Protocol is an open standard for connecting AI assistants to tools and data. A service exposes an MCP server, and any MCP client, such as Claude or Cursor, can call its tools.
Get started
Your cast is ready to start
Create your first actor in minutes.
Run your first scene
Plans from $9 a month, self-serve, no sales call. See pricing