Build a Smart Commercial Real Estate Optimizer with Pydantic AI and DeepSeek R1
Construct a type-safe office occupancy optimization pipeline for Southeast Asian tech hubs. Powered by Pydantic AI validation and DeepSeek R1 reasoning models, your agent will process floorplan sensor streams, model spatial utilization, and execute energy savings plans reliably.
What you are building
The core problem, expected build, and operating context for this challenge.
Build a type-safe agent with Pydantic AI and DeepSeek R1 reasoning to optimize office space utilization and energy consumption in regional commercial real estate.
How work is evaluated
Evaluate output validation against Pydantic schema and accuracy of HVAC adjustment instructions.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
pydantic_validation_pass
Output strictly parses through Pydantic schema without error
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
energy_savings_score
Estimated percentage power reduction from strategy • target: 25 • range: 0-100
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Implement structured type validation using Pydantic AI and DeepSeek R1 model integration
Parse IoT telemetry streams from commercial office floorplan sensors
Formulate spatial reallocation and HVAC adjustments based on occupancy trends
Guarantee strict schema adherence for facility automated system commands
Reference links and supporting material
IoT building telemetry dataset containing zone occupancy, temperature, and power utilization metrics.
How this agent runs
Evaluate output validation against Pydantic schema and accuracy of HVAC adjustment instructions.
Challenge input
JSON with zone_id, current_occupancy, max_capacity, temperature_c
Pydantic AI
Type-safe structured AI outputs using Pydantic.
DeepSeek R1
Open-weight deep reasoning model for complex optimization.
Evaluated output
JSON validated by Pydantic schema containing target_temp_c, fan_speed, and rationale
- Output strictly parses through Pydantic schema without error
- Estimated percentage power reduction from strategy • target: 25 • range: 0-100
- Benchmark: SmartBuilding_Pydantic_Eval
- Energy Savings Score target: 25
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
View technical recipe
Configured tools
- Pydantic AI · Required
- DeepSeek · Optional
- Weights & Biases · Optional
- Pydantic AI · Required
Evaluation contract
- pydantic_validation_pass · Weight 1
- energy_savings_score · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.