Skip to main content
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 and MCP reference.

Core objects

TermDefinition
WorkspaceThe top-level container that holds your studies, asks, people, sources, and secrets, and the unit ish bills and caps against. Alias prefix w-.
StudyThe persistent unit of research: show simulated people something, read their reactions, change it, and run again. Alias prefix s-.
IterationOne 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-.
AskA lighter comparison: one prompt and one or more variants of creative put in front of a fixed panel. Alias prefix a-.
RoundOne 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.
VariantOne candidate inside an ask round: a headline, a hero image, an ad cut. Each has a kind and a value.
BrandA workspace flagged as a comparison target (type competitor). Shares the w- alias prefix; surfaced in its own brand namespace. MCP only.
BenchmarkA clone of a study across a set of brands so each brand runs the same study head to head. MCP only.

People

TermDefinition
PersonA durable persona definition: structured demographics, universal enums, and a versioned accessibility profile. Alias prefix p- on the CLI, tp- on the MCP server.
ParticipantOne instance of a person inside a single run. The same person across two runs produces two participants reading from the same profile.
AudienceThe set of people a run dispatches: sampled from the pool, named explicitly, or generated to fit a brief.
PanelThe audience of an ask, fixed at creation so every round runs the same people.
PoolThe people available to a workspace, filtered by demographic to assemble an audience.
VisibilityThe scope that decides who can see and use a profile: workspace, platform, or community-shared.
SourceReal evidence (a transcript, recording, screenshot, support email, PDF) handed to person generation to ground a persona in how someone actually reacted.

Study definition

TermDefinition
ModalityThe kind of thing a study puts in front of people. ish supports seven: interactive, text, image, video, audio, document, chat.
Content typeAn optional sub-type that tunes a modality (for example editorial or reference for text). Five modalities carry one; interactive and chat do not.
AssignmentA single task a simulated person attempts during a run. A study carries one or more, run in order.
StepAn ordered atomic action inside an assignment, each a name of 1 to 80 characters.
QuestionnaireThe set of questions each simulated person answers. Lives on the study, alongside assignments.
Site accessHow ish reaches a gated URL: public, HTTP basic auth, a session cookie, or a login form. Configured per workspace.
SecretA per-workspace named value that backs a {{secret:KEY}} placeholder in chatbot endpoint config, resolved on the wire at dispatch.

Running and reading

TermDefinition
RunSending simulated people through a real surface end to end (a link, an app, a video) against the latest or a named iteration.
DispatchOne request that sends a group of simulated people at once. Capped at 20 participants, independent of tier.
ReactionsWhat each simulated person reports back: what they noticed, where they got stuck, and what they would do next.
Reported journeyThe full record a run returns per participant: transcript, signals, and the reasoning behind them, plus screenshots for interactive runs. Not a score.
SignalsThe measured layers of a reported journey: sentiment, friction, blockers, completion. Each carries the reasoning behind it.
SentimentA per-participant label and valence, rolled up as a histogram across the panel from completed participants only.
Share linkA 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

TermDefinition
CreditsA usage allowance every run draws down. Paid plans refill monthly; the free tier gets a one-time grant of 200 at signup. Not money.
LimitsPer-tier caps on how many entities (workspaces, studies, people) an account can hold. Enforced at create time, distinct from credits.
Dispatch capThe structural limit of 20 participants on every single dispatch, independent of tier and credits. Larger panels split into multiple runs.

Surfaces and tooling

TermDefinition
CLIThe ish command line, reading as ish <noun> <verb>. One developer surface onto the backend.
MCP serverThe same operations exposed as tools an AI agent calls, hosted at https://mcp.ishlabs.io/mcp. The other developer surface.
Active contextThe 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.
AliasA 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 for the mental model, then the CLI quickstart or connect an agent.