Skip to main content
Back to challenges
Challenge

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.

Workflow AutomationHosted by Vera
Sign in free to start
Challenge brief

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.

Delivery guide

How work is evaluated

Evaluation

Evaluate output validation against Pydantic schema and accuracy of HVAC adjustment instructions.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

pydantic_validation_pass

Output strictly parses through Pydantic schema without error

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

energy_savings_score

Estimated percentage power reduction from strategy • target: 25 • range: 0-100

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

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

Resources and assets

Reference links and supporting material

Dataset notes

IoT building telemetry dataset containing zone occupancy, temperature, and power utilization metrics.

Challenge setup

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

Evaluation checks
  • Output strictly parses through Pydantic schema without error
  • Estimated percentage power reduction from strategy • target: 25 • range: 0-100
Configured evaluation evidence
  • Benchmark: SmartBuilding_Pydantic_Eval
  • Energy Savings Score target: 25
  • 1 public reference case
Configured runtime
  • 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

Action Space
  • Pydantic AI · Required
  • DeepSeek · Optional
  • Weights & Biases · Optional
Orchestration
  • Pydantic AI · Required

Evaluation contract

  • pydantic_validation_pass · Weight 1
  • energy_savings_score · Weight 1

Metrics

  • energy_savings_score · Target 25

Benchmarks

  • SmartBuilding_Pydantic_Eval
  • energy

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with zone_id, current_occupancy, max_capacity, temperature_c

    Output: JSON validated by Pydantic schema containing target_temp_c, fan_speed, and rationale

    Execution harness: Python

Evaluation tools

  • Pydantic AI · Agent Framework
  • DeepSeek R1 · Reasoning Model

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Smart Commercial Real Estate Optimizer with Pydantic AI and DeepSeek R1