> ## Documentation Index > Fetch the complete documentation index at: https://docs.ishlabs.io/llms.txt > Use this file to discover all available pages before exploring further. # Glossary > One-line definitions of every ish term, each linking to the concept page that explains it in full. Every term used across the ish CLI and MCP docs, defined once. Each entry links to the concept page that carries the full mental model. For exact flags, parameters, and return shapes, follow the links into the [CLI](/cli/overview) and [MCP](/mcp/overview) reference. ## Core objects | Term | Definition | | --------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Workspace](/concepts/workspace) | The top-level container that holds your studies, asks, people, sources, and secrets, and the unit ish bills and caps against. Alias prefix `w-`. | | [Study](/concepts/study) | The persistent unit of research: show simulated people something, read their reactions, change it, and run again. Alias prefix `s-`. | | [Iteration](/concepts/iteration) | One configured version of a study that attaches the single artifact (a URL, a media file, or a chatbot endpoint) participants experience. Labelled `A`, `B`, `C`, with alias prefix `i-`. | | [Ask](/concepts/ask-and-round) | A lighter comparison: one prompt and one or more variants of creative put in front of a fixed panel. Alias prefix `a-`. | | [Round](/concepts/ask-and-round) | One pass of an ask's panel over a prompt and its variants. The first round is created with the ask; later rounds reuse the same people. An ask holds up to five. | | [Variant](/concepts/ask-and-round#variants-the-things-being-compared) | One candidate inside an ask round: a headline, a hero image, an ad cut. Each has a kind and a value. | | [Brand](/concepts/benchmarking) | A workspace flagged as a comparison target (type `competitor`). Shares the `w-` alias prefix; surfaced in its own `brand` namespace. MCP only. | | [Benchmark](/concepts/benchmarking) | A clone of a study across a set of brands so each brand runs the same study head to head. MCP only. | ## People | Term | Definition | | -------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Person](/concepts/people) | A durable persona definition: structured demographics, universal enums, and a versioned accessibility profile. Alias prefix `p-` on the CLI, `tp-` on the MCP server. | | [Participant](/concepts/people#a-person-is-a-reusable-persona) | One instance of a person inside a single run. The same person across two runs produces two participants reading from the same profile. | | [Audience](/concepts/people#how-people-fit-a-run) | The set of people a run dispatches: sampled from the pool, named explicitly, or generated to fit a brief. | | [Panel](/concepts/ask-and-round) | The audience of an ask, fixed at creation so every round runs the same people. | | [Pool](/concepts/people#two-ways-to-get-the-people-you-need) | The people available to a workspace, filtered by demographic to assemble an audience. | | [Visibility](/concepts/people#where-a-person-lives-visibility) | The scope that decides who can see and use a profile: workspace, platform, or community-shared. | | [Source](/concepts/source) | Real evidence (a transcript, recording, screenshot, support email, PDF) handed to person generation to ground a persona in how someone actually reacted. | ## Study definition | Term | Definition | | --------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Modality](/concepts/modalities) | The kind of thing a study puts in front of people. ish supports seven: `interactive`, `text`, `image`, `video`, `audio`, `document`, `chat`. | | [Content type](/concepts/modalities#content-types-tune-the-modality) | An optional sub-type that tunes a modality (for example `editorial` or `reference` for `text`). Five modalities carry one; `interactive` and `chat` do not. | | [Assignment](/concepts/assignment-questionnaire#assignments-what-people-do) | A single task a simulated person attempts during a run. A study carries one or more, run in order. | | [Step](/concepts/assignment-questionnaire#steps-a-checklist-inside-an-assignment) | An ordered atomic action inside an assignment, each a name of 1 to 80 characters. | | [Questionnaire](/concepts/assignment-questionnaire) | The set of questions each simulated person answers. Lives on the study, alongside assignments. | | [Site access](/concepts/site-access) | How ish reaches a gated URL: public, HTTP basic auth, a session cookie, or a login form. Configured per workspace. | | [Secret](/concepts/secrets) | A per-workspace named value that backs a `{{secret:KEY}}` placeholder in chatbot endpoint config, resolved on the wire at dispatch. | ## Running and reading | Term | Definition | | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------ | | [Run](/concepts/run-vs-ask) | Sending simulated people through a real surface end to end (a link, an app, a video) against the latest or a named iteration. | | [Dispatch](/concepts/credits-and-limits#the-20-participant-dispatch-cap) | One request that sends a group of simulated people at once. Capped at 20 participants, independent of tier. | | [Reactions](/concepts/reactions-and-results) | What each simulated person reports back: what they noticed, where they got stuck, and what they would do next. | | [Reported journey](/concepts/reactions-and-results#the-layers-of-a-reported-journey) | The full record a run returns per participant: transcript, signals, and the reasoning behind them, plus screenshots for interactive runs. Not a score. | | [Signals](/concepts/reactions-and-results) | The measured layers of a reported journey: sentiment, friction, blockers, completion. Each carries the reasoning behind it. | | [Sentiment](/concepts/reactions-and-results) | A per-participant label and valence, rolled up as a histogram across the panel from completed participants only. | | [Share link](/concepts/sharing) | A public, no-login URL to one study's results, hosted on the web app, that anyone opens in a browser to read the run as a stakeholder would. | ## Credits and limits | Term | Definition | | ------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | | [Credits](/concepts/credits-and-limits#credits-are-a-usage-allowance-not-money) | A usage allowance every run draws down. Paid plans refill monthly; the free tier gets a one-time grant of 200 at signup. Not money. | | [Limits](/concepts/credits-and-limits#limits-cap-how-much-you-can-have) | Per-tier caps on how many entities (workspaces, studies, people) an account can hold. Enforced at create time, distinct from credits. | | [Dispatch cap](/concepts/credits-and-limits#the-20-participant-dispatch-cap) | The structural limit of 20 participants on every single dispatch, independent of tier and credits. Larger panels split into multiple runs. | ## Surfaces and tooling | Term | Definition | | ----------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | | [CLI](/cli/overview) | The `ish` command line, reading as `ish `. One developer surface onto the backend. | | [MCP server](/mcp/overview) | The same operations exposed as tools an AI agent calls, hosted at `https://mcp.ishlabs.io/mcp`. The other developer surface. | | [Active context](/concepts/active-context) | The CLI's saved workspace, study, and ask, kept in `~/.ish/config.json` (or `ISH_HOME`), so you do not repeat IDs. The MCP server is stateless. | | [Alias](/concepts/workspace#how-you-select-one) | A short, prefixed id every object carries (`w-`, `s-`, `i-`, `a-`, `p-` for a person, `ps-` for a source) that any tool taking that object's id accepts. | New to ish? Start with [how ish works](/concepts/overview) for the mental model, then the [CLI quickstart](/start/cli-quickstart) or [connect an agent](/start/connect-an-agent).