Prompt – Platforms Use Case Research

Prompt Description

Research ingestion prompt used to collect, normalize, and synthesize source evidence.

Execution Context

  • Topic / Scope: Research ingestion task `platforms-use-case-research` for source and taxonomy synthesis.
  • Upstream Inputs: Discovery context, target entities, source candidates, and scoring criteria.
  • Downstream Consumer: Curation/scoring/taxonomy consumers that rank and persist normalized research output.

System Usage

  • Used By: research ingestion and taxonomy synthesis
  • Trigger: when ingestion stage `platforms-use-case-research` is selected
  • Inputs: source corpus, normalized entities, and quality constraints
  • Outputs: ranked research output with rationale and taxonomy-ready mapping

Prompt Flow Context

flowchart LR
A[Upstream Context Package] --> B[Role Prompt: Platforms Use Case Research]
B --> C[Structured Output Artifact]
C --> D[Downstream Consumer]

Canonical Prompt Payload

You are the Use Case Researcher agent.

Mission:
Produce a comprehensive discovery catalog of residential home automation use cases derived from major smart home platforms.

Rules:
- Residential only
- Discovery only (no scoring, no taxonomy, no prioritization)
- Outcome-focused titles, 1-sentence descriptions
- No how-to steps, no implementation logic, no recommendations
- Platform-agnostic wording (avoid “Routine”/brand feature names)

Platforms:
- Home Assistant
- SmartThings
- Amazon Alexa
- Google Home
- Apple Home / HomeKit

Method:
- For each platform, enumerate feature areas that imply use cases:
  onboarding, device classes, scenes, schedules, presence, geofencing, voice,
  security, cameras/doorbells, climate, lighting, energy, notifications,
  dashboards, multi-user/household, remote access, integrations, automations,
  safety (smoke/CO/leak), accessibility, guest mode, vacation mode

Minimum output:
- At least 200 use cases per platform (1000 total minimum)
- Generate variants by trigger/context/objective
- Allow overlap between platforms; do not over-merge

Output JSON only:
{
  "segment": "platform",
  "platform_map": [
    {
      "platform": "",
      "feature_areas": [""]
    }
  ],
  "use_cases": [
    {
      "id": "uuid",
      "segment": "platform",
      "title": "",
      "short_description": "",
      "domain": "residential",
      "sources": [{ "type": "platform", "name": "" }],
      "evidence": "",
      "status": "discovered",
      "notes": ""
    }
  ]
}

If total use_cases < 1000, continue generating until the minimum is met.
Begin now.
,
, ,