pathfinder-decision-space.tak8.chatgpt.site
An agent-first workspace for exploring engineering programs, comparing colleges, and making a choice you can explain.
First seen 2026-11-05 · Last seen 2026-11-05 · Source: webmcp.com
Answer 7 · Act 8 · Transact 0 · Score: Not yet scored
Tool inspector
compose_workspace
Change presentation only; never mutate the canonical decision or scenario values. Use frontier for attention, compare for differences/why, place for geography and climate, and scenario only when a scenario is active. In Place mode, set climateLens to match a cold or heat question and include every school the user wants located in mapCandidateIds. In Compare cost views, set affordabilityBand to open the published family-income band relevant to the question. Include 2–3 concise annotations with type question after every composition; they appear as polished Explore next suggestions. Other annotation types become one consolidated takeaway. Candidate IDs come from get_decision_state or search_candidates; version guards are optional. This clears any working state started with begin_agent_activity.
Input schema
| Property | Type | Required | Description |
|---|---|---|---|
mode |
string | yes | — |
primaryCandidateIds |
array | yes | Use 3–5 serious schools when possible; six is the practical comparison maximum. |
secondaryCandidateIds |
array | no | Keep alternatives compressed; primary plus secondary may not exceed eight schools. |
dimensions |
array | yes | — |
emphasis |
array | no | — |
annotations |
array | no | Use non-question annotations for one main takeaway. Include 2–3 type=question annotations as concise, actionable next questions for the student or parent. |
plot |
object | no | — |
climateLens |
string | no | For Place mode, choose the weather detail that answers the user's question. Use nightsBelow40F or nightsBelow32F for cold concerns; use daysAbove90F or daysAbove100F for heat concerns. |
affordabilityBand |
string | no | Published family-income range to open in the cost card. This is a presentation focus, not a personal aid estimate. |
mapCandidateIds |
array | no | Use 3–5 serious schools when possible; six is the practical comparison maximum. |
excludedGroups |
array | no | — |
expectedDecisionVersion |
integer | no | — |
expectedScenarioId |
string | no | — |
Raw JSON schema
{
"type": "object",
"additionalProperties": false,
"properties": {
"mode": {
"type": "string",
"enum": [
"frontier",
"compare",
"place",
"scenario"
]
},
"primaryCandidateIds": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 48
},
"minItems": 1,
"maxItems": 6,
"uniqueItems": true,
"description": "Use 3–5 serious schools when possible; six is the practical comparison maximum."
},
"secondaryCandidateIds": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 48
},
"minItems": 0,
"maxItems": 5,
"uniqueItems": true,
"description": "Keep alternatives compressed; primary plus secondary may not exceed eight schools."
},
"dimensions": {
"type": "array",
"items": {
"type": "string",
"enum": [
"mechanicalEngineering",
"outcomes",
"cost",
"climate",
"walkability",
"campusScale"
]
},
"minItems": 1,
"maxItems": 6,
"uniqueItems": true
},
"emphasis": {
"type": "array",
"items": {
"type": "string",
"enum": [
"mechanicalEngineering",
"outcomes",
"cost",
"climate",
"walkability",
"campusScale"
]
},
"minItems": 1,
"maxItems": 6,
"uniqueItems": true
},
"annotations": {
"type": "array",
"maxItems": 6,
"description": "Use non-question annotations for one main takeaway. Include 2–3 type=question annotations as concise, actionable next questions for the student or parent.",
"items": {
"type": "object",
"additionalProperties": false,
"properties": {
"type": {
"type": "string",
"enum": [
"agent-insight",
"tradeoff",
"question",
"evidence"
]
},
"text": {
"type": "string",
"minLength": 1,
"maxLength": 240
},
"candidateIds": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 48
},
"minItems": 1,
"maxItems": 6,
"uniqueItems": true,
"description": "Use 3–5 serious schools when possible; six is the practical comparison maximum."
},
"dimensionId": {
"type": "string",
"enum": [
"mechanicalEngineering",
"outcomes",
"cost",
"climate",
"walkability",
"campusScale"
]
}
},
"required": [
"type",
"text"
]
}
},
"plot": {
"type": "object",
"additionalProperties": false,
"properties": {
"x": {
"type": "string",
"enum": [
"mechanicalEngineering",
"outcomes",
"cost",
"climate",
"walkability",
"campusScale"
]
},
"y": {
"type": "string",
"enum": [
"mechanicalEngineering",
"outcomes",
"cost",
"climate",
"walkability",
"campusScale"
]
}
},
"required": [
"x",
"y"
]
},
"climateLens": {
"type": "string",
"enum": [
"daysAbove90F",
"daysAbove100F",
"nightsBelow40F",
"nightsBelow32F",
"annualMeanHighF"
],
"description": "For Place mode, choose the weather detail that answers the user's question. Use nightsBelow40F or nightsBelow32F for cold concerns; use daysAbove90F or daysAbove100F for heat concerns."
},
"affordabilityBand": {
"type": "string",
"enum": [
"under30k",
"30to48k",
"48to75k",
"75to110k",
"over110k"
],
"description": "Published family-income range to open in the cost card. This is a presentation focus, not a personal aid estimate."
},
"mapCandidateIds": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 48
},
"minItems": 0,
"maxItems": 6,
"uniqueItems": true,
"description": "Use 3–5 serious schools when possible; six is the practical comparison maximum."
},
"excludedGroups": {
"type": "array",
"maxItems": 6,
"items": {
"type": "object",
"additionalProperties": false,
"properties": {
"label": {
"type": "string",
"maxLength": 80
},
"candidateIds": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 48
},
"minItems": 1,
"maxItems": 6,
"uniqueItems": true,
"description": "Use 3–5 serious schools when possible; six is the practical comparison maximum."
},
"reason": {
"type": "string",
"maxLength": 160
}
},
"required": [
"label",
"candidateIds",
"reason"
]
}
},
"expectedDecisionVersion": {
"type": "integer",
"minimum": 1
},
"expectedScenarioId": {
"type": "string",
"minLength": 1,
"maxLength": 80
}
},
"required": [
"mode",
"primaryCandidateIds",
"dimensions"
]
}
Similar websites
pocketgull.app
Pocket Gull is a real-time clinical AI consult engine powered by Google Gemini. Features 10D multi-paradigm strategy, FHIR R4 export & 3D spatial anatomy.
webmcp-six-lac.vercel.app
AI Navigation Layer: Model Context Protocol (MCP) Semantic DOM integration for intelligent, safe, and observable web navigation.
ghqsandbox.net
Interactive math and physics tools an AI agent can drive directly through WebMCP.
app.formative.com
Formative classroom assessment and learning platform