What this prompt does
This prompt asks Claude or ChatGPT to design a patient-facing lab results and health metrics dashboard. You define [product_name] and [platform_type], then describe the [data_sources], the [health_metrics] tracked, the [user_demographics], the [literacy_level], the [framework], and the [chart_library]. The model designs a health overview, a lab results viewer, a vital signs tracker, an insights and education section, a sharing and coordination layer, and the framework implementation.
The structure works because medical data is unforgiving — a confusing chart can scare a patient or hide a real problem. By forcing the model to honor [literacy_level] (for example a 6th-grade reading level with an optional clinical view) and to design reference-range bands and plain-language explanations, it produces output that tells the patient clearly whether a result is good or bad. The [chart_library] variable shapes the accessible, colorblind-safe visualizations.
When to use it
- You're building a patient portal and need lab results displayed without confusing or alarming users.
- You want reference-range bands, trend charts, and status indicators (normal, borderline, out of range) specified.
- You need plain-language "what does this mean?" explanations tuned to a target reading level.
- You're integrating wearable or EHR data and want a vital signs tracker with device sync laid out.
- You need accessible, colorblind-safe charts with tabular alternatives for screen readers.
- You want a sharing layer for caregivers, other providers, or an emergency info card.
Example output
The model returns a structured design document covering each view in order. The lab results viewer is specified down to grouping by panel, per-test status dots, shaded reference-range trend charts, and tap-to-explain plain-language text. The vital signs tracker covers manual entry plus device sync and pattern-detection alerts. The closing [framework] section translates everything into chart-library choices, accessibility requirements, lazy-loading, and offline access. You get a detailed, accessibility-first spec rather than finished code.
Pro tips
- Set
[literacy_level]deliberately; it controls the reading level of every auto-generated insight and explanation. - List
[health_metrics]precisely so the lab viewer groups results into the right panels (CBC, lipids, A1C, and so on). - Match
[data_sources]to reality — EHR plus wearable plus manual entry each implies different sync and trust indicators. - Pin
[chart_library]to one you'll actually use so the colorblind-safe palette and tabular-alternative notes apply. - Ask the model to expand the insights section if you want medication-impact and lifestyle-correlation visuals detailed.
- Stress that no result display should leave the patient guessing — re-prompt any section that omits clear good/bad status.
