Вход

ZeroWidth Prism

Удалённый MCP

Позволяет исследовать идеи в полях Prism, проводить исследования и читать результаты. Инструменты помогают искать документацию, управлять узлами исследований и генерировать вариации идей по семантическим осям.

нужен ключ Удалённый · Streamable HTTP API-ключ Разработка Веб и поиск ИИ и модели Официальный реестр · 10 просмотров

Что умеет

Позволяет исследовать идеи в полях Prism, проводить исследования и читать результаты. Инструменты помогают искать документацию, управлять узлами исследований и генерировать вариации идей по семантическим осям.

Перевод каталога (LLM) · показать оригинал автора

Explore ideas in Prism fields, run studies, and read research findings.

Подключение

Удалённый сервер: клиент обращается по адресу, код на вашей машине не запускается.

Claude Desktop

claude_desktop_config.json

Cursor

~/.cursor/mcp.json

Windsurf

~/.codeium/windsurf/mcp_config.json

Вставьте блок mcpServers в файл конфигурации своего клиента. Ключи не входят в файл: вместо SET_LOCALLY подставьте свои значения.

{
    "mcpServers": {
        "ai-zerowidth-prism": {
            "url": "https://api.zerowidth.ai/mcp/x/prism",
            "headers": {
                "Authorization": "Bearer SET_LOCALLY"
            }
        }
    }
}

Вызов без установки — через шлюз

Агент вызывает инструменты этого сервера через https://www.n2j.ru/mcphub/mcp: hub_call_tool {"server":"ai-zerowidth-prism","tool":"…","arguments":{…}} Сервер требует авторизации — ключ задаётся на стороне каталога.

https://api.zerowidth.ai/mcp/x/prism

Инструменты

52 схем · ≈ 14 254 условных токенов

search_docs

Search ZeroWidth product documentation. Returns matching pages with title, slug, public URL, and a query-relevant snippet. Use this when the user asks about a ZeroWidth product (Compass, Workbench, Caliper, Prism, Ledger, Napkin, the assistant), an API behavior, or a policy. No authentication required — the docs corpus is public.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "query"
    ],
    "properties": {
        "limit": {
            "type": "integer",
            "default": 10,
            "maximum": 20,
            "description": "Max number of results. Defaults to 10.",
            "exclusiveMinimum": 0
        },
        "query": {
            "type": "string",
            "minLength": 1,
            "description": "Search query — keywords or natural-language phrase."
        }
    }
}

get_doc

Fetch the full Markdown body of a specific docs page by its slug. Use this after search docs when the user needs the complete content of a page. No authentication required.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "slug"
    ],
    "properties": {
        "slug": {
            "type": "string",
            "minLength": 1,
            "description": "Page slug. Accepts 'compass/api', '/compass/api', or 'docs/compass/api'."
        }
    }
}

list_docs

Enumerate all available docs pages, optionally filtered by product (e.g. 'compass', 'legal', 'overview'). Use this to discover what slugs exist before calling get doc . No authentication required.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
        "product": {
            "type": "string",
            "description": "Optional product slug filter (e.g. 'compass', 'legal', 'overview')."
        }
    }
}

prism_fields_list

Lists Prism fields (idea-exploration canvases) in the active workspace: name, origin idea, node count. Fetch one with prism fields get for its nodes.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        }
    }
}

prism_fields_get

One field's full tree: every node (id, parent, axis, description, pinned, color, whether it has an image / desk research) plus the AI-clustered groups. The origin node has parentId=null; children sit along named axes. Use node ids with the expand / research / study tools.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "fieldId"
    ],
    "properties": {
        "fieldId": {
            "type": "string",
            "description": "Field id (from prism_fields_list)."
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        }
    }
}

research_findings_list

Cross-instrument findings for one subject (today: a Prism node) — attached feedback studies with response counts + theme counts, and whether desk research exists. (Interviews are study-level now — read them per study with prism interviews list.) THE PLACE TO LOOK before proposing new research: cite what already exists.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "subjectType",
        "subjectId"
    ],
    "properties": {
        "subjectId": {
            "type": "string",
            "description": "Subject id (e.g. a Prism node id)."
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "subjectType": {
            "enum": [
                "prism_node"
            ],
            "type": "string",
            "description": "Subject type."
        }
    }
}

prism_fields_create

Creates a field from an origin idea — the seed of an exploration canvas. Counts against the workspace's field quota. May return needs confirmation — tell the user what you're proposing and wait for approval.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "originIdea"
    ],
    "properties": {
        "name": {
            "type": "string",
            "maxLength": 200,
            "description": "Display name (defaults to the idea)."
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string",
            "description": "Approval id from a prior needs_confirmation envelope."
        },
        "originIdea": {
            "type": "string",
            "maxLength": 4000,
            "minLength": 1,
            "description": "The idea at the center — a product, concept, sentence."
        },
        "visibility": {
            "enum": [
                "PRIVATE",
                "WORKSPACE",
                "SHARED"
            ],
            "type": "string",
            "description": "Who can see it: PRIVATE (only the user), WORKSPACE (every member, the default), or SHARED (specific people, granted afterwards). Say 'make it private' → PRIVATE."
        }
    }
}

prism_nodes_expand

THE core Prism gesture: generate variations of a node along a named semantic axis ('more visceral', 'for the skeptic', 'stripped to essentials'…) in one of four directions. Runs generation against the workspace's inference credit. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "fieldId",
        "parentId",
        "axis"
    ],
    "properties": {
        "axis": {
            "type": "string",
            "maxLength": 200,
            "minLength": 1,
            "description": "The lens for the variations — short, evocative."
        },
        "count": {
            "type": "integer",
            "maximum": 10,
            "minimum": 1,
            "description": "How many (default 3)."
        },
        "fieldId": {
            "type": "string",
            "description": "Field id."
        },
        "parentId": {
            "type": "string",
            "description": "Node to branch from."
        },
        "direction": {
            "enum": [
                "up",
                "down",
                "left",
                "right"
            ],
            "type": "string",
            "description": "Canvas direction (default right; pick a free side)."
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string"
        }
    }
}

prism_nodes_update

Sets pinned state and/or the color tag on a node. Pins are the cross-field shortlist. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "fieldId",
        "nodeId"
    ],
    "properties": {
        "color": {
            "anyOf": [
                {
                    "type": "string",
                    "pattern": "^#[0-9a-fA-F]{6}$"
                },
                {
                    "type": "null"
                }
            ],
            "description": "Hex color, or null to clear."
        },
        "nodeId": {
            "type": "string"
        },
        "pinned": {
            "type": "boolean"
        },
        "fieldId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string"
        }
    }
}

prism_nodes_research

Web-sourced secondary research on a node's idea — market context with citations, stored on the node. depth 'thorough' runs three angled passes (market, evidence, shifts) at ~3× the credit. focus steers what it goes after; without one it answers a generic brief off the node's own description, so pass it whenever the user has said what they actually want to know. Runs against the workspace's inference credit. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "fieldId",
        "nodeId"
    ],
    "properties": {
        "depth": {
            "enum": [
                "quick",
                "thorough"
            ],
            "type": "string"
        },
        "focus": {
            "type": "string",
            "maxLength": 1000,
            "description": "What to concentrate on, e.g. 'pricing and who already pays for this' or 'regulatory constraints in the EU'."
        },
        "nodeId": {
            "type": "string"
        },
        "fieldId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string"
        }
    }
}

prism_studies_list

Feedback studies attached to one Prism node: title, question count, response count, open/closed.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "fieldId",
        "nodeId"
    ],
    "properties": {
        "nodeId": {
            "type": "string"
        },
        "fieldId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        }
    }
}

prism_studies_get

One study's questions, response count, open/closed state, and the STORED analysis (summary + themes with strength; insights.activeRun set = an analysis is running right now — wait for it before citing). participantUrl is the live share link to forward when the study is open and one has been minted. Cite theme strengths when reporting results.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId"
    ],
    "properties": {
        "studyId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        }
    }
}

prism_studies_draft

Generates a short study (5-8 questions probing the node's problem space — respondents never see the idea itself) and creates it as a DRAFT. The user reviews, previews, and opens it for responses from the study page (or via prism studies update publish). Runs generation against inference credit. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "fieldId",
        "nodeId"
    ],
    "properties": {
        "nodeId": {
            "type": "string"
        },
        "fieldId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string"
        }
    }
}

prism_studies_draft_standalone

Generates and creates a DRAFT study that isn't tied to any canvas node — brand tracking, workspace-level research, anything you can describe in a sentence. It appears on Prism's Studies page; the user previews and opens it for responses there (or via prism studies update publish). Runs generation against inference credit. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "about"
    ],
    "properties": {
        "about": {
            "type": "string",
            "maxLength": 4000,
            "minLength": 1,
            "description": "What the study should probe — a topic, question, or problem space in plain language."
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string"
        }
    }
}

prism_studies_draft_from_interviews

Qual-first design: drafts a survey GROUNDED in the study's completed interviews — the recurring claims become measurable questions, the tensions become the choices, in the interviewees' own words. Replaces the study's current questions with the draft (nothing fields until publish). Needs at least one completed interview (see prism interviews list). An optional steer biases the instrument ('focus on pricing'). Runs generation against inference credit. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId"
    ],
    "properties": {
        "steer": {
            "type": "string",
            "maxLength": 2000
        },
        "studyId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string"
        }
    }
}

prism_studies_update

publish: true takes a draft live (one-way — the participant link starts working). closed toggles whether a live study accepts responses. Also edits the study: title, the questions instrument (whole replacement — read prism studies get first; LOCKED once responses exist, the server refuses with invalid and the answer is a new study), adaptiveFollowUps (AI probes on curious answers), the closing chat ( endChatEnabled + endChatFocus ), completionRedirectUrl for a BYO panel (null clears), and autoAnalyzeTarget (null = manual only). Study ids come from prism studies list workspace. May return needs

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId"
    ],
    "properties": {
        "title": {
            "type": "string",
            "maxLength": 300,
            "minLength": 1
        },
        "closed": {
            "type": "boolean"
        },
        "publish": {
            "type": "boolean",
            "const": true
        },
        "studyId": {
            "type": "string"
        },
        "questions": {
            "type": "array",
            "items": {
                "type": "object",
                "required": [
                    "type"
                ],
                "properties": {
                    "qid": {
                        "type": "string",
                        "maxLength": 40
                    },
                    "type": {
                        "enum": [
                            "word",
                            "text",
                            "choice",
                            "multi",
                            "rank",
                            "maxdiff",
                            "scale",
                            "number",
                            "completion"
                        ],
                        "type": "string"
                    },
                    "probe": {
                        "type": "string",
                        "maxLength": 500
                    },
                    "loopId": {
                        "type": "string",
                        "maxLength": 40
                    },
                    "prefix": {
                        "type": "string"
                    },
                    "prompt": {
                        "type": "string"
                    },
                    "rotate": {
                        "type": "boolean"
                    },
                    "showIf": {
                        "type": "object",
                        "required": [
                            "qid"
                        ],
                        "properties": {
                            "gte": {
                                "type": "number"
                            },
                            "lte": {
                                "type": "number"
                            },
                            "qid": {
                                "type": "string",
                                "maxLength": 40
                            },
                            "anyOf": {
                                "type": "array",
                                "items": {
                                    "type": "string",
                                    "maxLength": 200
                                },
                                "maxItems": 20
                            }
                        }
                    },
                    "vwRole": {
                        "enum": [
                            "too_cheap",
                            "cheap",
                            "expensive",
                            "too_expensive"
                        ],
                        "type": "string"
                    },
                    "options": {
                        "type": "array",
                        "items": {
                            "type": "string"
                        }
                    },
                    "kanoRole": {
                        "enum": [
                            "functional",
                            "dysfunctional"
                        ],
                        "type": "string"
                    },
                    "loopItem": {
                        "type": "string",
                        "maxLength": 200
                    },
                    "lowLabel": {
                        "type": "string"
                    },
                    "scaleMax": {
                        "type": "integer",
                        "maximum": 20,
                        "minimum": 2
                    },
                    "scaleMin": {
                        "type": "integer",
                        "maximum": 10,
                        "minimum": 0
                    },
                    "susIndex": {
                        "type": "integer",
                        "maximum": 10,
                        "minimum": 1
                    },
                    "highLabel": {
                        "type": "string"
                    },
                    "maxdiffId": {
                        "type": "string",
                        "maxLength": 40
                    },
                    "numberMax": {
                        "type": "number"
                    },
                    "numberMin": {
                        "type": "number"
                    },
                    "allowOther": {
                        "type": "boolean"
                    },
                    "anchorLast": {
                        "type": "integer",
                        "maximum": 5,
                        "minimum": 1
                    },
                    "loopRotate": {
                        "type": "boolean"
                    },
                    "otherLabel": {
                        "type": "string",
                        "maxLength": 60
                    },
                    "contextText": {
                        "type": "string",
                        "maxLength": 2000
                    },
                    "placeholder": {
                        "type": "string"
                    },
                    "exclusiveLast": {
                        "type": "boolean"
                    },
                    "maxSelections": {
                        "type": "integer",
                        "maximum": 20,
                        "minimum": 1
                    },
                    "contextImageUrl": {
                        "type": "string",
                        "maxLength": 1000
                    },
                    "loopPresentation": {
                        "enum": [
                            "paged",
                            "grid"
                        ],
                        "type": "string"
                    },
                    "screenOutOptions": {
                        "type": "array",
                        "items": {
                            "type": "string",
                            "maxLength": 200
                        },
                        "maxItems": 10
                    }
                },
                "additionalProperties": []
            },
            "maxItems": 40,
            "description": "Replacement instrument (drafts only): ordered list of { type, prompt, options?, … } — read prism_studies_get for the shape."
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string"
        },
        "endChatFocus": {
            "anyOf": [
                {
                    "type": "string",
                    "maxLength": 200
                },
                {
                    "type": "null"
                }
            ],
            "description": "What the closing chat should be about; null clears."
        },
        "endChatEnabled": {
            "type": "boolean"
        },
        "adaptiveFollowUps": {
            "type": "boolean"
        },
        "autoAnalyzeTarget": {
            "anyOf": [
                {
                    "type": "integer",
                    "maximum": 1000,
                    "minimum": 2
                },
                {
                    "type": "null"
                }
            ]
        },
        "completionRedirectUrl": {
            "anyOf": [
                {
                    "type": "string"
                },
                {
                    "type": "null"
                }
            ],
            "description": "http(s) URL respondents land on after submitting ({pid} = participant id); null clears."
        }
    }
}

prism_studies_results

Everything the Results tab shows, as numbers you can trust without counting raw rows: fielding funnel (opens → starts → completes, median completion time, sources, per-question drop-off), per-question aggregates (scale distributions + means + NPS on 0–10, choice/multi counts, rank first-place + mean ranks, MaxDiff set scores, word frequencies, text samples), and quality flags (speeders, duplicate participant ids). ALWAYS use this for quantitative questions about a study — never tally answers yourself.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId"
    ],
    "properties": {
        "studyId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "panelRunId": {
            "type": "string",
            "description": "Read one synthetic panel run's answers instead of people's (ADR 0083). Synthetic results are never people's — say so whenever you report them."
        }
    }
}

prism_research_digest

A cross-study digest: every study with responses — title, origin (standalone / canvas node / tracker wave), response count, latest analysis summary, top themes, and which insights were kept in Ledger. The starting point for 'what have we learned about X?' — follow up with prism studies get (insights) or prism studies results on the studies that matter.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        }
    }
}

prism_studies_report

An AI research analyst writes the report's narrative layer — executive summary, key findings with their numbers, recommendations — from the study's computed record (funnel, per-question aggregates, themes, quotes). Stored on the study; the printable report at the study page renders it above the charts. Runs against inference credit. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId"
    ],
    "properties": {
        "studyId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string"
        }
    }
}

prism_series_list

Recurring research programs (ADR 0031): name, cadence, enabled state, next wave time, wave count, and the metric + score rule when the series posts readings. Waves themselves are ordinary studies.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        }
    }
}

prism_series_launch_wave

CLOSES the current wave (no more responses; it scores and posts to Ledger if bound) and fields the next one from the series' frozen instrument, readying its participant link. Fielding spends credit for follow-ups, closing chats, and analysis, and closing a live wave can't be undone — say both plainly before proposing. Manual launches don't move the schedule clock. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "seriesId"
    ],
    "properties": {
        "seriesId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string"
        }
    }
}

prism_interviews_list

The study's one-on-one qual conversations: guest, status, focus, and — once completed — the structured memo (summary, key claims, tensions, verbatim quotes). Raw transcript included only while no memo exists. inviteUrl is the link to forward for interviews still waiting on their guest.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId"
    ],
    "properties": {
        "studyId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        }
    }
}

prism_studies_segments

The stored k-means segmentation over the study's numeric answers: named segments with size, share, and the distinguishing features (segment mean vs overall). Null when none computed yet — prism studies segments compute discovers them (needs 30+ responses and 2+ numeric questions).

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId"
    ],
    "properties": {
        "studyId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        }
    }
}

prism_studies_cut

Server-computed banner cut with significance: a target question (scale/number → group means + NPS on 0–10; choice/multi → per-option shares) split by acquisition source or by any single-choice question, each group tested against its complement at 95% (Welch t / two-proportion z). vsRest says higher/lower/not significant — or not tested when either side is under the 30-response floor; never present not tested as 'no difference'. Use this for every 'does X differ by Y?' question instead of eyeballing raw rows.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId",
        "targetIndex"
    ],
    "properties": {
        "studyId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "cutBySource": {
            "type": "boolean",
            "description": "Cut by acquisition source (?src= tags)."
        },
        "targetIndex": {
            "type": "integer",
            "maximum": 9007199254740991,
            "minimum": 0,
            "description": "0-based index of the question to measure."
        },
        "cutByQuestionIndex": {
            "type": "integer",
            "maximum": 9007199254740991,
            "minimum": 0,
            "description": "0-based index of a single-choice question to cut by."
        }
    }
}

prism_studies_analyze

Kicks the theme analysis (incremental — reads only responses and interviews since the last run; the previous themes carry forward). Returns immediately with the run's phase; the run continues server-side, so wait a moment and re-read prism studies get — findings are fresh once its insights stop reporting an active run. upToDate: true means there was nothing new (a healthy no-op, not an error). Runs against inference credit. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId"
    ],
    "properties": {
        "studyId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string"
        },
        "reanalyzeAll": {
            "type": "boolean",
            "description": "Full clean-slate re-read of every response (costlier)."
        }
    }
}

prism_interviews_create

Creates a one-on-one AI-led interview on a study and returns the invite link to forward — the guest needs no account. The transcript stays on the study and joins the next analysis run (it never lands in Compass). focusPrompt briefs the interviewer on what to dig into; omitted, it explores the study's territory. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId"
    ],
    "properties": {
        "studyId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string"
        },
        "focusPrompt": {
            "type": "string",
            "maxLength": 2000
        },
        "intervieweeName": {
            "type": "string",
            "maxLength": 120
        }
    }
}

prism_insights_promote

Promotes an analysis theme (or, with no themeId, the analysis summary) into the workspace's Ledger as a belief, carrying the supporting verbatims as evidence with links back to the study. THE step that turns a finding into workspace memory — use when the user says an insight matters. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId"
    ],
    "properties": {
        "studyId": {
            "type": "string"
        },
        "themeId": {
            "type": "string",
            "description": "A theme id from prism_studies_get; omit for the summary."
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string"
        }
    }
}

prism_studies_segments_compute

Runs k-means over the study's numeric answers (silhouette-picked k) and names the discovered segments from their computed profiles. Needs 30+ responses and 2+ numeric questions; recompute overwrites. Runs naming against inference credit. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId"
    ],
    "properties": {
        "studyId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string"
        }
    }
}

prism_fields_update

Edits a field's name (null reverts to the origin idea), description, or visibility. Nodes are untouched. Field ids come from prism fields list. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "fieldId"
    ],
    "properties": {
        "name": {
            "anyOf": [
                {
                    "type": "string",
                    "maxLength": 200
                },
                {
                    "type": "null"
                }
            ]
        },
        "fieldId": {
            "type": "string",
            "description": "Field id (from prism_fields_list)."
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string",
            "description": "Approval id from a prior needs_confirmation envelope."
        },
        "visibility": {
            "enum": [
                "PRIVATE",
                "WORKSPACE",
                "SHARED"
            ],
            "type": "string",
            "description": "Who can see it: PRIVATE (only the user), WORKSPACE (every member, the default), or SHARED (specific people, granted afterwards). Say 'make it private' → PRIVATE."
        },
        "description": {
            "type": "string",
            "maxLength": 2000
        }
    }
}

prism_fields_delete

Removes a field and its whole canvas (soft delete; frees the workspace's field quota). Use when the user is done with an exploration or one was created by mistake — studies attached to its nodes are not deleted. Field ids come from prism fields list. May return needs confirmation — name the field and wait.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "fieldId"
    ],
    "properties": {
        "fieldId": {
            "type": "string",
            "description": "Field id (from prism_fields_list)."
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string",
            "description": "Approval id from a prior needs_confirmation envelope."
        }
    }
}

prism_studies_list_workspace

All studies regardless of origin — standalone, canvas-node, and series waves — newest first: title, question count, response count, draft / live / closed state, and the field / node / series it hangs off. The starting point for 'which studies do we have?'; prism studies list is the per-node view, prism research digest the findings view. Read one with prism studies get.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        }
    }
}

prism_studies_delete

Permanently deletes a study with its responses, interviews, analysis, and share links. Right for a draft that won't be fielded or a duplicate; for a live study the user just wants to stop, prefer prism studies update closed: true — that keeps the data. Study ids come from prism studies list workspace. May return needs confirmation — name the study and its response count, then wait.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId"
    ],
    "properties": {
        "studyId": {
            "type": "string",
            "description": "Study id (from prism_studies_list_workspace)."
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string",
            "description": "Approval id from a prior needs_confirmation envelope."
        }
    }
}

prism_series_create

Creates a research program that fields the SAME instrument on a schedule — brand tracking, a weekly pulse — each wave an ordinary study. The questions freeze once the first wave fields (that's the trendline), so get them right with the user first. Optionally bind a Ledger metric + score rule so every wave posts a reading (a scorer needs a metricId ). Waves launch on schedule, or on demand with prism series launch wave. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "name",
        "questions",
        "interval"
    ],
    "properties": {
        "name": {
            "type": "string",
            "maxLength": 200,
            "minLength": 1
        },
        "scorer": {
            "anyOf": [
                {
                    "type": "object",
                    "required": [
                        "kind",
                        "questionIndex"
                    ],
                    "properties": {
                        "kind": {
                            "enum": [
                                "scale_mean",
                                "nps",
                                "top_2_box",
                                "choice_share"
                            ],
                            "type": "string"
                        },
                        "minN": {
                            "type": "integer",
                            "default": 5,
                            "maximum": 1000,
                            "minimum": 1
                        },
                        "option": {
                            "type": "string",
                            "maxLength": 200
                        },
                        "questionIndex": {
                            "type": "integer",
                            "maximum": 39,
                            "minimum": 0
                        }
                    }
                },
                {
                    "type": "null"
                }
            ],
            "description": "How a wave becomes one number: { kind, questionIndex, option?, minN? }."
        },
        "interval": {
            "enum": [
                "daily",
                "weekly"
            ],
            "type": "string",
            "description": "daily or weekly."
        },
        "metricId": {
            "anyOf": [
                {
                    "type": "string"
                },
                {
                    "type": "null"
                }
            ],
            "description": "Ledger metric the waves post readings to (from ledger_metrics_list)."
        },
        "dayOfWeek": {
            "anyOf": [
                {
                    "type": "integer",
                    "maximum": 6,
                    "minimum": 0
                },
                {
                    "type": "null"
                }
            ],
            "description": "Weekly only: 0 = Sunday … 6 = Saturday."
        },
        "questions": {
            "type": "array",
            "items": {
                "type": "object",
                "required": [
                    "type"
                ],
                "properties": {
                    "qid": {
                        "type": "string",
                        "maxLength": 40
                    },
                    "type": {
                        "enum": [
                            "word",
                            "text",
                            "choice",
                            "multi",
                            "rank",
                            "maxdiff",
                            "scale",
                            "number",
                            "completion"
                        ],
                        "type": "string"
                    },
                    "probe": {
                        "type": "string",
                        "maxLength": 500
                    },
                    "loopId": {
                        "type": "string",
                        "maxLength": 40
                    },
                    "prefix": {
                        "type": "string"
                    },
                    "prompt": {
                        "type": "string"
                    },
                    "rotate": {
                        "type": "boolean"
                    },
                    "showIf": {
                        "type": "object",
                        "required": [
                            "qid"
                        ],
                        "properties": {
                            "gte": {
                                "type": "number"
                            },
                            "lte": {
                                "type": "number"
                            },
                            "qid": {
                                "type": "string",
                                "maxLength": 40
                            },
                            "anyOf": {
                                "type": "array",
                                "items": {
                                    "type": "string",
                                    "maxLength": 200
                                },
                                "maxItems": 20
                            }
                        }
                    },
                    "vwRole": {
                        "enum": [
                            "too_cheap",
                            "cheap",
                            "expensive",
                            "too_expensive"
                        ],
                        "type": "string"
                    },
                    "options": {
                        "type": "array",
                        "items": {
                            "type": "string"
                        }
                    },
                    "kanoRole": {
                        "enum": [
                            "functional",
                            "dysfunctional"
                        ],
                        "type": "string"
                    },
                    "loopItem": {
                        "type": "string",
                        "maxLength": 200
                    },
                    "lowLabel": {
                        "type": "string"
                    },
                    "scaleMax": {
                        "type": "integer",
                        "maximum": 20,
                        "minimum": 2
                    },
                    "scaleMin": {
                        "type": "integer",
                        "maximum": 10,
                        "minimum": 0
                    },
                    "susIndex": {
                        "type": "integer",
                        "maximum": 10,
                        "minimum": 1
                    },
                    "highLabel": {
                        "type": "string"
                    },
                    "maxdiffId": {
                        "type": "string",
                        "maxLength": 40
                    },
                    "numberMax": {
                        "type": "number"
                    },
                    "numberMin": {
                        "type": "number"
                    },
                    "allowOther": {
                        "type": "boolean"
                    },
                    "anchorLast": {
                        "type": "integer",
                        "maximum": 5,
                        "minimum": 1
                    },
                    "loopRotate": {
                        "type": "boolean"
                    },
                    "otherLabel": {
                        "type": "string",
                        "maxLength": 60
                    },
                    "contextText": {
                        "type": "string",
                        "maxLength": 2000
                    },
                    "placeholder": {
                        "type": "string"
                    },
                    "exclusiveLast": {
                        "type": "boolean"
                    },
                    "maxSelections": {
                        "type": "integer",
                        "maximum": 20,
                        "minimum": 1
                    },
                    "contextImageUrl": {
                        "type": "string",
                        "maxLength": 1000
                    },
                    "loopPresentation": {
                        "enum": [
                            "paged",
                            "grid"
                        ],
                        "type": "string"
                    },
                    "screenOutOptions": {
                        "type": "array",
                        "items": {
                            "type": "string",
                            "maxLength": 200
                        },
                        "maxItems": 10
                    }
                },
                "additionalProperties": []
            },
            "maxItems": 40,
            "minItems": 1,
            "description": "The instrument: an ordered list of questions ({ type, prompt, options?, … } — read an existing study with prism_studies_get for the shape)."
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string",
            "description": "Approval id from a prior needs_confirmation envelope."
        },
        "scheduleTime": {
            "type": "string",
            "description": "HH:MM local to scheduleTimezone (default 09:00)."
        },
        "scheduleTimezone": {
            "type": "string",
            "description": "IANA zone (default UTC)."
        },
        "adaptiveFollowUps": {
            "type": "boolean",
            "description": "AI follow-up questions on curious answers (default true)."
        },
        "autoAnalyzeTarget": {
            "anyOf": [
                {
                    "type": "integer",
                    "maximum": 1000,
                    "minimum": 2
                },
                {
                    "type": "null"
                }
            ],
            "description": "Analyze each wave automatically at this many completes."
        }
    }
}

prism_series_update

Edits a series: enabled: false pauses the schedule (true resumes), interval / scheduleTime / scheduleTimezone / dayOfWeek move the cadence, name and follow-up / auto-analyze settings change any time. The instrument (questions, scorer) is editable only while no wave has fielded — after that the server refuses with invalid , and the answer is a new series. Series ids come from prism series list. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "seriesId"
    ],
    "properties": {
        "name": {
            "type": "string",
            "maxLength": 200,
            "minLength": 1
        },
        "scorer": {
            "anyOf": [
                {
                    "type": "object",
                    "required": [
                        "kind",
                        "questionIndex"
                    ],
                    "properties": {
                        "kind": {
                            "enum": [
                                "scale_mean",
                                "nps",
                                "top_2_box",
                                "choice_share"
                            ],
                            "type": "string"
                        },
                        "minN": {
                            "type": "integer",
                            "default": 5,
                            "maximum": 1000,
                            "minimum": 1
                        },
                        "option": {
                            "type": "string",
                            "maxLength": 200
                        },
                        "questionIndex": {
                            "type": "integer",
                            "maximum": 39,
                            "minimum": 0
                        }
                    }
                },
                {
                    "type": "null"
                }
            ]
        },
        "enabled": {
            "type": "boolean",
            "description": "false pauses, true resumes."
        },
        "interval": {
            "enum": [
                "daily",
                "weekly"
            ],
            "type": "string"
        },
        "metricId": {
            "anyOf": [
                {
                    "type": "string"
                },
                {
                    "type": "null"
                }
            ]
        },
        "seriesId": {
            "type": "string",
            "description": "Series id (from prism_series_list)."
        },
        "dayOfWeek": {
            "anyOf": [
                {
                    "type": "integer",
                    "maximum": 6,
                    "minimum": 0
                },
                {
                    "type": "null"
                }
            ]
        },
        "questions": {
            "type": "array",
            "items": {
                "type": "object",
                "required": [
                    "type"
                ],
                "properties": {
                    "qid": {
                        "type": "string",
                        "maxLength": 40
                    },
                    "type": {
                        "enum": [
                            "word",
                            "text",
                            "choice",
                            "multi",
                            "rank",
                            "maxdiff",
                            "scale",
                            "number",
                            "completion"
                        ],
                        "type": "string"
                    },
                    "probe": {
                        "type": "string",
                        "maxLength": 500
                    },
                    "loopId": {
                        "type": "string",
                        "maxLength": 40
                    },
                    "prefix": {
                        "type": "string"
                    },
                    "prompt": {
                        "type": "string"
                    },
                    "rotate": {
                        "type": "boolean"
                    },
                    "showIf": {
                        "type": "object",
                        "required": [
                            "qid"
                        ],
                        "properties": {
                            "gte": {
                                "type": "number"
                            },
                            "lte": {
                                "type": "number"
                            },
                            "qid": {
                                "type": "string",
                                "maxLength": 40
                            },
                            "anyOf": {
                                "type": "array",
                                "items": {
                                    "type": "string",
                                    "maxLength": 200
                                },
                                "maxItems": 20
                            }
                        }
                    },
                    "vwRole": {
                        "enum": [
                            "too_cheap",
                            "cheap",
                            "expensive",
                            "too_expensive"
                        ],
                        "type": "string"
                    },
                    "options": {
                        "type": "array",
                        "items": {
                            "type": "string"
                        }
                    },
                    "kanoRole": {
                        "enum": [
                            "functional",
                            "dysfunctional"
                        ],
                        "type": "string"
                    },
                    "loopItem": {
                        "type": "string",
                        "maxLength": 200
                    },
                    "lowLabel": {
                        "type": "string"
                    },
                    "scaleMax": {
                        "type": "integer",
                        "maximum": 20,
                        "minimum": 2
                    },
                    "scaleMin": {
                        "type": "integer",
                        "maximum": 10,
                        "minimum": 0
                    },
                    "susIndex": {
                        "type": "integer",
                        "maximum": 10,
                        "minimum": 1
                    },
                    "highLabel": {
                        "type": "string"
                    },
                    "maxdiffId": {
                        "type": "string",
                        "maxLength": 40
                    },
                    "numberMax": {
                        "type": "number"
                    },
                    "numberMin": {
                        "type": "number"
                    },
                    "allowOther": {
                        "type": "boolean"
                    },
                    "anchorLast": {
                        "type": "integer",
                        "maximum": 5,
                        "minimum": 1
                    },
                    "loopRotate": {
                        "type": "boolean"
                    },
                    "otherLabel": {
                        "type": "string",
                        "maxLength": 60
                    },
                    "contextText": {
                        "type": "string",
                        "maxLength": 2000
                    },
                    "placeholder": {
                        "type": "string"
                    },
                    "exclusiveLast": {
                        "type": "boolean"
                    },
                    "maxSelections": {
                        "type": "integer",
                        "maximum": 20,
                        "minimum": 1
                    },
                    "contextImageUrl": {
                        "type": "string",
                        "maxLength": 1000
                    },
                    "loopPresentation": {
                        "enum": [
                            "paged",
                            "grid"
                        ],
                        "type": "string"
                    },
                    "screenOutOptions": {
                        "type": "array",
                        "items": {
                            "type": "string",
                            "maxLength": 200
                        },
                        "maxItems": 10
                    }
                },
                "additionalProperties": []
            },
            "maxItems": 40,
            "minItems": 1,
            "description": "Replacement instrument — only before the first wave fields."
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string",
            "description": "Approval id from a prior needs_confirmation envelope."
        },
        "scheduleTime": {
            "type": "string",
            "description": "HH:MM."
        },
        "scheduleTimezone": {
            "type": "string",
            "description": "IANA zone."
        },
        "adaptiveFollowUps": {
            "type": "boolean"
        },
        "autoAnalyzeTarget": {
            "anyOf": [
                {
                    "type": "integer",
                    "maximum": 1000,
                    "minimum": 2
                },
                {
                    "type": "null"
                }
            ]
        }
    }
}

prism_panels_draft

Turns a plain description of an audience ("100 Midwest senior citizens") into a panel spec: filters on Census and General Social Survey fields, a size, and stated shares for traits with no data behind them (assumed). Saves nothing. Show the person the spec and assumedNotes, then pass the spec to prism panels create. poolSize is how many people in the population sample match.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "description"
    ],
    "properties": {
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "description": {
            "type": "string",
            "maxLength": 2000,
            "minLength": 3
        }
    }
}

prism_panels_list

Every synthetic panel the person can see: name, current version (people, status), runs so far, and fit (how far it sat from people the last time a study had both). Reuse an existing panel before drafting a new one.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        }
    }
}

prism_panels_get

One panel with its current version and the share of people by every field (assumed fields flagged). Use it to confirm a draw looks like the audience the person meant.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "panelId"
    ],
    "properties": {
        "panelId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        }
    }
}

prism_panel_runs_estimate

What running a study against a panel would cost: people, model calls, and approximate dollars of workspace credit. Starts nothing. Tell the person the cost before calling prism panels run.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId",
        "panelId"
    ],
    "properties": {
        "kind": {
            "enum": [
                "survey",
                "interview"
            ],
            "type": "string",
            "description": "survey (default) or interview."
        },
        "panelId": {
            "type": "string"
        },
        "samples": {
            "type": "integer",
            "maximum": 3,
            "minimum": 1,
            "description": "Answers per person for a survey run (default 3)."
        },
        "studyId": {
            "type": "string"
        },
        "budgetUsd": {
            "type": "number",
            "description": "Pause the run once it has spent this many dollars.",
            "exclusiveMinimum": 0
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "temperature": {
            "type": "number",
            "maximum": 1.5,
            "minimum": 0
        },
        "interviewFocus": {
            "type": "string",
            "description": "Interview runs: what the interviewer should explore."
        },
        "interviewPeople": {
            "type": "integer",
            "maximum": 50,
            "minimum": 1,
            "description": "Interview runs: how many people (default 10)."
        }
    }
}

prism_panel_runs_get

Status, progress, spend and the run's own analysis. For the numbers, call prism studies results with panelRunId. Synthetic answers are never people's: always say so when you report them.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "runId"
    ],
    "properties": {
        "runId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        }
    }
}

prism_panels_create

Saves a panel from a spec (usually from prism panels draft) and draws its people from population records in the background, which takes a few seconds. Visible to the workspace unless visibility is PRIVATE. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "name",
        "spec"
    ],
    "properties": {
        "name": {
            "type": "string",
            "maxLength": 120,
            "minLength": 1
        },
        "spec": {
            "type": "object",
            "required": [
                "size",
                "seed"
            ],
            "properties": {
                "seed": {
                    "type": "integer",
                    "maximum": 2147483647,
                    "minimum": 0
                },
                "size": {
                    "type": "integer",
                    "maximum": 2000,
                    "minimum": 10
                },
                "fields": {
                    "type": "array",
                    "items": {
                        "type": "string",
                        "pattern": "^[a-z][a-z0-9_]*$",
                        "maxLength": 60,
                        "minLength": 1
                    },
                    "maxItems": 120
                },
                "assumed": {
                    "type": "array",
                    "items": {
                        "type": "object",
                        "required": [
                            "field",
                            "shares"
                        ],
                        "properties": {
                            "note": {
                                "type": "string",
                                "maxLength": 300
                            },
                            "when": {
                                "type": "object",
                                "required": [
                                    "field"
                                ],
                                "properties": {
                                    "max": {
                                        "type": "number"
                                    },
                                    "min": {
                                        "type": "number"
                                    },
                                    "anyOf": {
                                        "type": "array",
                                        "items": {
                                            "type": "string",
                                            "maxLength": 200
                                        },
                                        "maxItems": 60
                                    },
                                    "field": {
                                        "type": "string",
                                        "pattern": "^[a-z][a-z0-9_]*$",
                                        "maxLength": 60,
                                        "minLength": 1
                                    }
                                }
                            },
                            "field": {
                                "type": "string",
                                "pattern": "^[a-z][a-z0-9_]*$",
                                "maxLength": 60,
                                "minLength": 1
                            },
                            "shares": {
                                "type": "object",
                                "propertyNames": {
                                    "type": "string",
                                    "maxLength": 200
                                },
                                "additionalProperties": {
                                    "type": "number",
                                    "minimum": 0
                                }
                            }
                        }
                    },
                    "default": [],
                    "maxItems": 60
                },
                "filters": {
                    "type": "array",
                    "items": {
                        "type": "object",
                        "required": [
                            "field"
                        ],
                        "properties": {
                            "max": {
                                "type": "number"
                            },
                            "min": {
                                "type": "number"
                            },
                            "anyOf": {
                                "type": "array",
                                "items": {
                                    "type": "string",
                                    "maxLength": 200
                                },
                                "maxItems": 60
                            },
                            "field": {
                                "type": "string",
                                "pattern": "^[a-z][a-z0-9_]*$",
                                "maxLength": 60,
                                "minLength": 1
                            }
                        }
                    },
                    "default": [],
                    "maxItems": 20
                },
                "targets": {
                    "type": "array",
                    "items": {
                        "type": "object",
                        "required": [
                            "field",
                            "shares"
                        ],
                        "properties": {
                            "field": {
                                "type": "string",
                                "pattern": "^[a-z][a-z0-9_]*$",
                                "maxLength": 60,
                                "minLength": 1
                            },
                            "shares": {
                                "type": "object",
                                "propertyNames": {
                                    "type": "string",
                                    "maxLength": 200
                                },
                                "additionalProperties": {
                                    "type": "number",
                                    "minimum": 0
                                }
                            }
                        }
                    },
                    "default": [],
                    "maxItems": 8
                },
                "population": {
                    "enum": [
                        "us-adults"
                    ],
                    "type": "string",
                    "default": "us-adults"
                },
                "presentation": {
                    "enum": [
                        "narrative",
                        "structured"
                    ],
                    "type": "string",
                    "default": "narrative"
                }
            }
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string",
            "description": "Approval id from a prior needs_confirmation envelope."
        },
        "visibility": {
            "enum": [
                "PRIVATE",
                "WORKSPACE"
            ],
            "type": "string"
        },
        "description": {
            "type": "string",
            "maxLength": 2000
        }
    }
}

prism_panels_run

Starts a background run: every person on the panel answers the study (or, for kind interview, sits with the study's interviewer). Spends workspace credit — give the person the estimate from prism panel runs estimate first. Works on draft studies. Answers land as their own result set, labeled synthetic, never counted as responses. Follow with prism panel runs get. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId",
        "panelId"
    ],
    "properties": {
        "kind": {
            "enum": [
                "survey",
                "interview"
            ],
            "type": "string",
            "description": "survey (default) or interview."
        },
        "panelId": {
            "type": "string"
        },
        "samples": {
            "type": "integer",
            "maximum": 3,
            "minimum": 1,
            "description": "Answers per person for a survey run (default 3)."
        },
        "studyId": {
            "type": "string"
        },
        "budgetUsd": {
            "type": "number",
            "description": "Pause the run once it has spent this many dollars.",
            "exclusiveMinimum": 0
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string",
            "description": "Approval id from a prior needs_confirmation envelope."
        },
        "temperature": {
            "type": "number",
            "maximum": 1.5,
            "minimum": 0
        },
        "interviewFocus": {
            "type": "string",
            "description": "Interview runs: what the interviewer should explore."
        },
        "interviewPeople": {
            "type": "integer",
            "maximum": 50,
            "minimum": 1,
            "description": "Interview runs: how many people (default 10)."
        }
    }
}

prism_panel_runs_cancel

Stops a queued, running or paused panel run. Answers already in stay. May return needs confirmation .

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "runId"
    ],
    "properties": {
        "runId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string",
            "description": "Approval id from a prior needs_confirmation envelope."
        }
    }
}

prism_research_reports_list

Every desk-research report on a study, newest first: id, title, the focus it was asked, depth, status (running / ready / failed) and an excerpt. Read one in full with prism research reports get.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId"
    ],
    "properties": {
        "studyId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        }
    }
}

prism_research_reports_get

One desk-research report in full: the brief (markdown) and the sources it cites. Its claims are what public sources say, not what anyone at the company told you; when you put them on the Compass map, cite sourceKind 'prism report' with this report's id.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId",
        "reportId"
    ],
    "properties": {
        "studyId": {
            "type": "string"
        },
        "reportId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        }
    }
}

prism_research_run

Web-sourced desk research kept as a report on a study, with citations. Steer it with focus : research accumulates, a broad sweep first, then narrower runs as the questions sharpen. depth 'thorough' runs three angled passes at ~3× the credit. To research a company, make a standalone study about it (prism studies draft standalone) and run one report per area of the business, e.g. focus 'how finance closes the month and approves spend at , from job posts, filings and press'. It plans questions, searches, reads the pages and keeps only findings it can quote from them, so it takes a few minutes: th

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "studyId",
        "focus"
    ],
    "properties": {
        "depth": {
            "enum": [
                "quick",
                "thorough"
            ],
            "type": "string"
        },
        "focus": {
            "type": "string",
            "maxLength": 1000,
            "description": "What to concentrate on."
        },
        "title": {
            "type": "string",
            "maxLength": 200
        },
        "studyId": {
            "type": "string"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string"
        }
    }
}

comments_list

Lists the comment threads on one workspace entity (open first, then resolved) with authors and timestamps. Read this before weighing in on contested work — the threads are where disagreement lives before it becomes a decision.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "entityKind",
        "entityId"
    ],
    "properties": {
        "entityId": {
            "type": "string",
            "maxLength": 60,
            "minLength": 1
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "entityKind": {
            "enum": [
                "workbench_flow",
                "compass_page",
                "compass_opportunity",
                "caliper_review",
                "caliper_dataset",
                "caliper_rubric",
                "caliper_eval",
                "caliper_spec",
                "napkin_board",
                "napkin_diagram",
                "napkin_doc",
                "napkin_sheet",
                "napkin_interface",
                "ledger_entry",
                "prism_field",
                "workspace_file"
            ],
            "type": "string",
            "description": "What the thread hangs on."
        }
    }
}

comments_create

Posts a comment on a workspace entity — a new thread, or a reply when rootId is given. Use it to leave findings where the discussion already lives (an eval result on the flow being debated, a summary on a long thread). Mention people via mentionedUserIds (from workspace member ids) to ring their notification bell; never mention someone who didn't ask to be pulled in.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "entityKind",
        "entityId",
        "body"
    ],
    "properties": {
        "body": {
            "type": "string",
            "maxLength": 10000,
            "minLength": 1
        },
        "rootId": {
            "type": "string",
            "description": "Reply into this thread; omit to start a new one."
        },
        "entityId": {
            "type": "string",
            "maxLength": 60,
            "minLength": 1
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string"
        },
        "entityKind": {
            "enum": [
                "workbench_flow",
                "compass_page",
                "compass_opportunity",
                "caliper_review",
                "caliper_dataset",
                "caliper_rubric",
                "caliper_eval",
                "caliper_spec",
                "napkin_board",
                "napkin_diagram",
                "napkin_doc",
                "napkin_sheet",
                "napkin_interface",
                "ledger_entry",
                "prism_field",
                "workspace_file"
            ],
            "type": "string",
            "description": "What the thread hangs on."
        },
        "mentionedUserIds": {
            "type": "array",
            "items": {
                "type": "string"
            },
            "maxItems": 20
        }
    }
}

comments_resolve

Sets a comment thread's resolved state (rootId = the thread's root comment id). Resolve ONLY when the human asked or the thread's question is demonstrably settled — and say what settled it in a reply first. Reopening is for new evidence.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "rootId",
        "resolved"
    ],
    "properties": {
        "rootId": {
            "type": "string",
            "maxLength": 60,
            "minLength": 1
        },
        "resolved": {
            "type": "boolean"
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string"
        }
    }
}

search_workspace

Finds anything in the workspace in one call — uploaded files (searching the text inside them), folders, Workbench flows, shims, knowledge bases and tasks, Compass pages and changes, Caliper datasets, evals, rubrics, reviews, specs and sources, Ledger entries, Napkin sketches, decks, docs, sheets, diagrams and interfaces. The same search the person uses in Home. Use it FIRST whenever the user mentions something without saying where it lives ('the SOW', 'the dispatch interviews', 'that invoice'). The query is words in any order: each word must appear in the thing's name, its tags, the names of t

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "q"
    ],
    "properties": {
        "q": {
            "type": "string",
            "maxLength": 200,
            "minLength": 1,
            "description": "Words, any order, case-insensitive. Fewer words find more."
        },
        "kinds": {
            "type": "array",
            "items": {
                "enum": [
                    "flow",
                    "page",
                    "dataset",
                    "eval",
                    "entry",
                    "board",
                    "file",
                    "shim",
                    "knowledge_base",
                    "task",
                    "rubric",
                    "review",
                    "spec",
                    "source",
                    "doc",
                    "sheet",
                    "diagram",
                    "interface",
                    "change",
                    "field",
                    "study",
                    "metric",
                    "folder"
                ],
                "type": "string"
            },
            "minItems": 1,
            "description": "Restrict to these kinds (file, folder, flow, page, doc, dataset, …). Omit to search everything."
        },
        "limit": {
            "type": "integer",
            "default": 20,
            "maximum": 50,
            "minimum": 1
        },
        "folderId": {
            "type": "string",
            "maxLength": 100,
            "minLength": 1,
            "description": "Only search inside this folder and the folders under it (ids from workspace_folders_browse or a folder hit)."
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        }
    }
}

entity_tags_get

Returns the tags on a batch of entities of one kind — the labels galleries organize by. Ids come from the kind's list/get tool or from search workspace. Use it before entity tags set so you replace the full set knowingly, and to answer 'what is this filed under'. Entities the user can't see are omitted.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "entityKind",
        "ids"
    ],
    "properties": {
        "ids": {
            "type": "array",
            "items": {
                "type": "string",
                "maxLength": 100,
                "minLength": 1
            },
            "maxItems": 100,
            "minItems": 1
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "entityKind": {
            "enum": [
                "workbench_flow",
                "workbench_task",
                "workbench_kb",
                "compass_page",
                "compass_opportunity",
                "caliper_dataset",
                "caliper_rubric",
                "caliper_eval",
                "caliper_review",
                "caliper_spec",
                "caliper_source",
                "ledger_entry",
                "ledger_metric",
                "napkin_board",
                "napkin_deck",
                "napkin_doc",
                "napkin_sheet",
                "napkin_diagram",
                "prism_field",
                "prism_study"
            ],
            "type": "string",
            "description": "Which kind the ids belong to."
        }
    }
}

entity_tags_browse

Without a tag: every tag in use across the workspace with how many entities carry it, most-used first — the vocabulary the team already organizes by. With a tag: everything filed under it across every tool, each with its kind, id, title, and path. Use it to reuse existing labels instead of inventing near-duplicates, and to answer 'show me everything about X' when X is a label.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
        "tag": {
            "type": "string",
            "maxLength": 40,
            "minLength": 1,
            "description": "A tag to expand into its items. Omit to list tags."
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        }
    }
}

entity_tags_set

Replaces the FULL tag set on one entity (an empty list clears it). Read the current tags with entity tags get first and pass the merged list — this is not additive. Tags are lowercase letters, numbers, spaces, and hyphens; prefer labels already in use (entity tags browse) so the workspace's vocabulary stays small. The id comes from the kind's list/get tool or search workspace.

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "entityKind",
        "entityId",
        "tags"
    ],
    "properties": {
        "tags": {
            "type": "array",
            "items": {
                "type": "string",
                "pattern": "^[a-z0-9](?:[a-z0-9 -]*[a-z0-9])?$",
                "maxLength": 40
            },
            "maxItems": 50
        },
        "entityId": {
            "type": "string",
            "maxLength": 100,
            "minLength": 1
        },
        "workspace": {
            "type": "string",
            "description": "Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."
        },
        "approvalId": {
            "type": "string",
            "description": "Approval id from a prior needs_confirmation response. Omit on the first call."
        },
        "entityKind": {
            "enum": [
                "workbench_flow",
                "workbench_task",
                "workbench_kb",
                "compass_page",
                "compass_opportunity",
                "caliper_dataset",
                "caliper_rubric",
                "caliper_eval",
                "caliper_review",
                "caliper_spec",
                "caliper_source",
                "ledger_entry",
                "ledger_metric",
                "napkin_board",
                "napkin_deck",
                "napkin_doc",
                "napkin_sheet",
                "napkin_diagram",
                "prism_field",
                "prism_study"
            ],
            "type": "string"
        }
    }
}