Skip to main content
Back to challenges
Challenge

Built Environment Autonomous Work Dispatch Orchestrator

The physical built environment requires continuous operational monitoring and multi-trade work order routing. Build an asynchronous agent event loop using Celery and Redis to continuously monitor sensor streams, classify fault conditions, and dispatch trade specialized vendors automatically. Maintain continuous uptime processing over 10,000 daily telemetry events.

Business OperationsHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Construct an asynchronous worker architecture using Celery and Redis for autonomous smart building dispatch workflows.

Delivery guide

How work is evaluated

Evaluation

Evaluates task queue execution latency and correct trade vendor dispatch routing.

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

Trade Routing Verification

Chiller failure must be routed to HVAC Mechanical trade

Binary check

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

Dimension 2

Dispatch Task Latency

Average task processing time in milliseconds • target: 50 • range: 1-500

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

  • Build asynchronous Celery task queues backed by Redis message brokers

  • Parse incoming building sensor telemetry events concurrently

  • Route critical fault tickets to appropriate maintenance vendors based on trade taxonomy

  • Implement automatic retry policies and dead-letter queues for unhandled faults

Resources and assets

Reference links and supporting material

Dataset notes

Telemetry event payloads and maintenance work order logs from real estate operations.

Challenge setup

Evaluates task queue execution latency and correct trade vendor dispatch routing.

Challenge input

JSON with fault_type, building_id

Celery

Enables asynchronous background worker processing for IoT dispatches

Evaluated output

JSON with assigned_trade, dispatch_status, task_latency_ms

Evaluation checks
  • Chiller failure must be routed to HVAC Mechanical trade
  • Average task processing time in milliseconds • target: 50 • range: 1-500
Configured evaluation evidence
  • Benchmark: TaskQueueBench
  • Dispatch Task Latency target: 50
  • 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
  • Zed · Required
  • Lindy · Optional
  • Voiceflow · Optional

Evaluation contract

  • Trade Routing Verification · Weight 1
  • Dispatch Task Latency · Weight 1

Metrics

  • Dispatch Task Latency · Target 50

Benchmarks

  • TaskQueueBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with fault_type, building_id

    Output: JSON with assigned_trade, dispatch_status, task_latency_ms

    Execution harness: Python

Evaluation tools

  • Celery · Distributed Task Queue

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Built Environment Autonomous Work Dispatch Orchestrator