tessera.kbates9611.chatgpt.site
Tessera turns governed monthly data into decision-ready dashboards.
First seen 2026-11-05 · Last seen 2026-11-05 · Source: webmcp.com
Answer 5 · Act 59 · Transact 0 · Score: Not yet scored
Tool inspector
propose_dataset_month_outline
Persist labelled outlines and source-to-canonical variables for a pending workbook. Outline every region the sheet contains: the table that feeds this dataset (kind table, confidence 1), any secondary tables (kind table, lower confidence), and the titles, notes, and footers people should see were deliberately skipped (kind narrative or footnote). Every region is drawn and labelled on the worksheet with its name. Prioritize exact fields already used by charts. Put every uncertain semantic choice into questions so Tessera can ask the user instead of guessing. MODEL GUIDANCE: Define table boundaries, headers, types, keys, and canonical fields. Surface ambiguous mappings as user questions rather than guessing.
Input schema
| Property | Type | Required | Description |
|---|---|---|---|
datasetId |
string | yes | Dataset ID |
period |
string | yes | Month in YYYY-MM format |
regions |
array | yes | Every labelled region in the workbook; at least one must be kind table |
variableMappings |
array | yes | Source variables matched to stable canonical variables |
questions |
array | no | Ambiguous choices that require a user answer |
Raw JSON schema
{
"type": "object",
"properties": {
"datasetId": {
"type": "string",
"description": "Dataset ID",
"maxLength": 8000
},
"period": {
"type": "string",
"description": "Month in YYYY-MM format",
"maxLength": 8000
},
"regions": {
"type": "array",
"description": "Every labelled region in the workbook; at least one must be kind table",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Stable region ID",
"maxLength": 8000
},
"sheet": {
"type": "string",
"description": "Exact worksheet name",
"maxLength": 8000
},
"name": {
"type": "string",
"description": "Short label shown on the worksheet outline, such as Facility detail or Ops notes",
"maxLength": 8000
},
"kind": {
"type": "string",
"description": "table for rows and columns to clean; narrative for titles, commentary, or prose; footnote for footers, sources, or totals",
"enum": [
"table",
"narrative",
"footnote"
]
},
"confidence": {
"type": "number",
"description": "1 for the table that feeds this dataset; lower for secondary tables and non-table regions",
"minimum": 0,
"maximum": 1
},
"canonicalName": {
"type": "string",
"description": "Dataset name for the primary table; otherwise the region name",
"maxLength": 8000
},
"range": {
"type": "object",
"properties": {
"startRow": {
"type": "number",
"description": "One-based inclusive start row",
"minimum": 1
},
"startColumn": {
"type": "number",
"description": "One-based inclusive start column",
"minimum": 1
},
"endRow": {
"type": "number",
"description": "One-based inclusive end row",
"minimum": 2
},
"endColumn": {
"type": "number",
"description": "One-based inclusive end column",
"minimum": 1
}
},
"required": [
"startRow",
"startColumn",
"endRow",
"endColumn"
],
"additionalProperties": false
}
},
"required": [
"name",
"kind",
"confidence",
"canonicalName",
"range"
],
"additionalProperties": false
},
"maxItems": 1000
},
"variableMappings": {
"type": "array",
"description": "Source variables matched to stable canonical variables",
"items": {
"type": "object",
"properties": {
"source": {
"type": "string",
"description": "Exact source variable",
"maxLength": 8000
},
"canonical": {
"type": "string",
"description": "Stable canonical variable",
"maxLength": 8000
},
"confidence": {
"type": "number",
"description": "Mapping confidence",
"minimum": 0,
"maximum": 1
},
"matchedFromPrevious": {
"type": "string",
"description": "Prior approved variable that established the match",
"maxLength": 8000
},
"usedByCharts": {
"type": "boolean",
"description": "Whether an existing chart or KPI depends on this variable"
},
"confirmed": {
"type": "boolean",
"description": "Whether the user explicitly confirmed it"
}
},
"required": [
"source",
"canonical",
"confidence"
],
"additionalProperties": false
},
"maxItems": 1000
},
"questions": {
"type": "array",
"description": "Ambiguous choices that require a user answer",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Stable question ID",
"maxLength": 8000
},
"prompt": {
"type": "string",
"description": "Short user-facing question",
"maxLength": 8000
},
"detail": {
"type": "string",
"description": "Context explaining why the choice matters",
"maxLength": 8000
},
"choices": {
"type": "array",
"description": "Two or more mutually exclusive choices",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Choice ID",
"maxLength": 8000
},
"label": {
"type": "string",
"description": "Short choice label",
"maxLength": 8000
},
"description": {
"type": "string",
"description": "Impact of choosing this option",
"maxLength": 8000
}
},
"required": [
"id",
"label"
],
"additionalProperties": false
},
"maxItems": 1000
},
"recommendedChoiceId": {
"type": "string",
"description": "Recommended choice ID",
"maxLength": 8000
},
"answerChoiceId": {
"type": "string",
"description": "User-selected choice ID",
"maxLength": 8000
}
},
"required": [
"id",
"prompt",
"choices"
],
"additionalProperties": false
},
"maxItems": 1000
}
},
"required": [
"datasetId",
"period",
"regions",
"variableMappings"
],
"additionalProperties": false
}
Similar websites
econsor.de
German digital agency building portals, e-commerce sites and online marketing, combining strategy, design and AI to grow clients' visibility and customer base.
inkframe-eta.vercel.app
Browser-native Elah video editor for 9:16 and 16:9 exports
agentdesk-demo.vercel.app
Meridian Ops
eworker.ca
E-Worker is business infrastructure powered by AI, with focused apps and connected business work.