> ## 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. # study create > Command reference: ish study create. ## `ish study create` Create a new study (the persistent shape: modality, tasks, questionnaire). Optionally creates iteration A inline when --content-text, --url, --image-urls, --content-url, or --endpoint is passed. Usage: `ish study create [options]` ### Options Workspace ID Study name Required. Study description Study modality (interactive, video, audio, text, image, document, chat) Content type (per-modality enum - see 'Content types by modality' below). Changes how --title is presented to participants (e.g. content-type email renders --title as the Subject: line). Not used for interactive / chat. Assignment as 'Name:Instructions' (repeatable) Default: \[]. JSON file with assignments array Inline JSON array of assignments (escape hatch) Add a text question to the questionnaire (repeatable; type=text, timing=after) Default: \[]. Questionnaire as inline JSON array, @file, or a JSON file path - supports text, slider, likert, single-choice, multiple-choice, number; timing=before|after Text content to evaluate, or @filepath to read from file. Creates iteration A inline (text modality only) URL to test. Creates iteration A inline (interactive modality only) Screen format for interactive iterations: desktop (default) or mobile\_portrait (hyphen/underscore variants accepted) Public URL of the media file. Creates iteration A inline (video, audio, document modalities). For local files, use the 2-step `iteration create` flow. Comma-separated public image URLs. Creates iteration A inline (image modality). For local files, use the 2-step `iteration create` flow. Participant-facing content title - the headline participants read before the body (text + media modalities - image, video, audio, document; optional). With --content-type email it becomes the email Subject: line. Not an internal label. Not used for interactive / chat. Segmentation JSON for the inline iteration A - time\_based \{intervals\_seconds, labels?}, section\_based \{sections\[\{name,label,...}]}, or page\_based \{} (text + media). section\_based sections are SEMANTIC: group related paragraphs into a few coherent sections (a long article is usually 3-6 sections, not one per paragraph). Lets one `study create` build a complete segmented iteration - no separate `iteration create` needed. Content-config JSON for the inline iteration A (early\_termination, selected\_segment\_indices) - text + media. HTML version of the text, or @filepath - text modality (email rendering) Email 'From' display name - text modality (email rendering) Email sender address - text modality (email rendering) Hero image URL - text modality (email rendering) Saved chatbot endpoint id or alias. Creates iteration A inline (chat modality, external\_chatbot mode) ChatbotEndpointConfig JSON file (or `-` for stdin); embedded directly. Mutually exclusive with --endpoint (chat modality, external\_chatbot mode) Maximum conversation turns per participant (chat modality only; default 12) Chat mode: external\_chatbot (default) or participant\_pair (two AI groups talk to each other) - chat modality only Person IDs/aliases for group A (comma-separated or repeatable). Pass a single profile and N on --group-b to broadcast (1×N rehearsal: fix side A, vary side B) - chat participant\_pair mode Default: \[]. Person IDs/aliases for group B. When both sides are explicit they must be equal length, BUT if either side is a singleton it's auto-broadcast to match the other (1×N rehearsal) - chat participant\_pair mode Default: \[]. Side-A scenario + goal - chat participant\_pair mode Side-B scenario + goal - chat participant\_pair mode Which side speaks first (default: a) - chat participant\_pair mode RoleCriteria filter for side A (JSON object or @filepath). Keys: occupation\[], min\_age, max\_age, gender\[], country\[], education\_level\_in\[], household\_in\[], locale\_type\_in\[], income\_level\_in\[], employment\_status\_in\[], requires\_captions, uses\_screen\_reader, prefers\_reduced\_motion, prefers\_high\_contrast, has\_any\_accessibility\_need. The five \*\_in arrays accept snake\_case spec values; the five accessibility filters are booleans. Use INSTEAD of --group-a or alongside it. chat participant\_pair mode. RoleCriteria filter for side B - same shape as --role-criteria-a. chat participant\_pair mode. ## Global flags Every command accepts the global flags. output the version number Auth token (or set ISH\_TOKEN env var) Read auth token from a file (preferred over --token / ISH\_TOKEN) Default workspace ID; per-subcommand --workspace overrides Output as JSON (auto-enabled when piped) Extract a single field from the JSON response and print only its value (implies --json internally; supports dotted paths e.g. person.name) Force human-readable output even when stdout is piped (overrides JSON-when-piped auto-detection) Comma-separated fields to include in JSON output (e.g. alias,name,status) Include full UUIDs and timestamps in JSON output Disable colored output (also honored: NO\_COLOR env var) Suppress progress messages on stderr (no-op for read commands that emit none)