Type-Safe Senior Living Site Selection and Care Demand Agent with Pydantic AI
Senior living healthcare operators misallocate capital when site selection models fail to cross-validate local aging demographics and medical proximity. Build a type-safe agent using Pydantic AI to validate census projections and healthcare travel times. Ensure 100% structured type validation and accurate target demographic scoring.
What you are building
The core problem, expected build, and operating context for this challenge.
Develop a type-safe Pydantic AI agent pipeline with Pydantic validation models to score target expansion locations for senior housing developments.
How work is evaluated
Evaluates schema compliance and suitability score accuracy for senior housing site selection.
Challenge datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
schema_type_check
Verifies all required Pydantic model fields are present and correctly typed
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
suitability_precision
Precision of suitability score evaluation • target: 0.95 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Build a type-safe agent using Pydantic AI (`pydantic_ai.Agent`) with structured output validation
Ingest zip-code level population demographics (age 75+ growth rate, median income)
Calculate healthcare access metrics (distance to nearest Grade-1 trauma hospital)
Output structured Pydantic models containing suitability score and bed capacity recommendations
Reference links and supporting material
Zip-code demographic data incorporating age 75+ cohort projections, median income, and healthcare facility distance.
Challenge setup
Evaluates schema compliance and suitability score accuracy for senior housing site selection.
Challenge input
JSON containing zip_code, senior_pop_75_plus, growth_rate_5yr, median_household_income, hospital_distance_miles
Pydantic AI
Type-safe Python agent framework with native Pydantic validation.
Evaluated output
JSON containing suitability_score, recommended_unit_count, care_type_priority
- Verifies all required Pydantic model fields are present and correctly typed
- Precision of suitability score evaluation • target: 0.95 • range: 0-1
- Benchmark: Type-Safe Site Selection Benchmark
- Suitability Precision target: 0.95
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.
View technical recipe
Configured tools
- Pydantic AI · Required
- LiveKit · Optional
- Ludwig · Optional
- Pydantic AI · Required
Evaluation contract
- schema_type_check · Weight 1
- suitability_precision · Weight 1
Metrics
- suitability_precision · Target 0.95
Benchmarks
- Type-Safe Site Selection Benchmark
- general
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON containing zip_code, senior_pop_75_plus, growth_rate_5yr, median_household_income, hospital_distance_miles
Output: JSON containing suitability_score, recommended_unit_count, care_type_priority
Execution harness: Python
Evaluation tools
- Pydantic AI · agent_framework
Recipe freeze marker
No recipe freeze time is recorded.