ish study list
List studies for a workspace
Usage: ish study list [options]
Options
string
Workspace ID
ish study generate
Generate a study from a problem description using AI
Usage: ish study generate [options]
Options
string
Workspace ID
string
Problem description (what you want to understand) Required.
string
URL of the product to test
string
SSR dimension to measure on the generated study, e.g. purchase_intent (repeatable) Default: [].
ish study get
Get the full study payload - iterations (with run details), assignments, interview questions, sentiment + status counts. Accepts multiple IDs for batched lookup. NOTE: this is the full payload, not a roll-up - for a compact cross-study comparison view use study results <id> --summary.
Usage: ish study get <ids>... [options]
Arguments
Study ID(s) - one or more aliases/UUIDs (space- or comma-separated) (required, variadic)
Options
string
Workspace ID; accepted for consistency (inferred from alias / active context)
ish study update
Update a study
Usage: ish study update <id> [options]
Arguments
Study ID (required)
Options
string
Study name
string
Study description
string
Study status (draft, running, completed)
string
Study modality (interactive, video, audio, text, image, document, chat)
string
Content type
string
Replace all assignments with these (repeatable) Default: [].
string
JSON file with assignments array
string
Inline JSON array of assignments (escape hatch)
string
Replace the questionnaire with these text questions (repeatable) Default: [].
string
Replace SSR dimensions to measure, e.g. purchase_intent (repeatable). Reconciles the auto-added buy-reaction question. Default: [].
string
Replace the questionnaire from inline JSON, @file, or a JSON file path (full InterviewQuestion shape)
string
Workspace ID; accepted for consistency (inferred from alias / active context)
ish study delete
Delete a study
Usage: ish study delete <id> [options]
Arguments
Study ID (required)
Options
string
Workspace ID; accepted for consistency (workspace is inferred from the study)
boolean
Skip confirmation prompt (required in —json or non-TTY contexts)
ish study use
Set the active study (saved to ~/.ish/config.json)
Usage: ish study use [id] [options]
Arguments
Study alias or UUID (optional)
Options
boolean
Remove the active study from config
string
Workspace ID; accepted for consistency (inferred from alias / active context)
ish study benchmark
Run a study’s benchmark against one or more references. Clones the study onto each reference, appends a round, and dispatches simulations: RUNS and draws credits.
Usage: ish study benchmark [id] [options]
Arguments
Study ID (defaults to active study) (optional)
Options
string
Reference id to benchmark against (repeatable; comma-separated accepted). At least one required. Default: []. Required.
string
Source-study iteration whose completed AI participant roster each round replicates. Required.
string
Screen format for every round: desktop | mobile_portrait (default desktop)
string
Per-participant step cap (default: unlimited)
string
Workspace ID; accepted for consistency (workspace is inferred from the study)
boolean
Skip the credit-spend confirmation (required in —json / non-TTY to proceed)
ish study comparison
Read the aggregated benchmark comparison: the source study’s iterations and each reference’s rounds, with metrics and the synthesis when one exists.
Usage: ish study comparison [id] [options]
Arguments
Study ID (defaults to active study) (optional)
Options
string
Workspace ID; accepted for consistency (workspace is inferred from the study)
Global flags
Every command accepts the global flags.boolean
output the version number
string
Auth token (or set ISH_TOKEN env var)
string
Read auth token from a file (preferred over —token / ISH_TOKEN)
string
Default workspace ID; per-subcommand —workspace overrides
boolean
Output as JSON (auto-enabled when piped)
string
Extract a single field from the JSON response and print only its value (implies —json internally; supports dotted paths e.g. person.name)
boolean
Force human-readable output even when stdout is piped (overrides JSON-when-piped auto-detection)
string
Comma-separated fields to include in JSON output (e.g. alias,name,status)
boolean
Print the projectable field names for the response instead of the data, then exit (also: —fields ?)
boolean
Include full UUIDs and timestamps in JSON output
boolean
Disable colored output (also honored: NO_COLOR env var)
boolean
Suppress progress messages on stderr (no-op for read commands that emit none)