Skip to main content
Back to challenges
Challenge

Mastra AI & Coplay AI Multifamily Demand Handling Assistant

Multifamily properties suffer from high lead-drop rates due to slow response times and uncoordinated tour bookings. Build an agentic workflow using Mastra AI and Coplay AI to automatically parse incoming prospect inquiries, score intent, and schedule tours dynamically.

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.

Develop an intelligent lead handling system using Mastra AI and Coplay AI to automate tenant onboarding and tour scheduling.

Delivery guide

How work is evaluated

Evaluation

Evaluates prospect intent extraction and scheduled appointment timing accuracy.

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

slot_booking_validation

Verifies selected tour slot exists in provided availability list.

Binary check

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

Dimension 2

intent_extraction_f1

F1 score of extracted lead criteria (budget, bedrooms, move-in date). • target: 0.92 • range: 0-1

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

  • Configure Mastra AI agents with custom TypeScript workflows for lead qualification

  • Integrate Coplay AI agentic interfaces for human-in-the-loop oversight

  • Implement memory and state retention across multi-channel tenant messages

  • Automate calendar availability queries and booking updates

Resources and assets

Reference links and supporting material

Dataset notes

200 simulated multifamily rental inquiries and associated property availability calendars.

Challenge setup

Evaluates prospect intent extraction and scheduled appointment timing accuracy.

Challenge input

JSON containing message history and available tour slots

Mastra AI

Provides TypeScript-native workflows and agent tool capabilities.

Coplay AI

Delivers human-in-the-loop assistant UI components for property managers.

Evaluated output

JSON with lead qualification score, move_in_date, and selected_slot

Evaluation checks
  • Verifies selected tour slot exists in provided availability list.
  • F1 score of extracted lead criteria (budget, bedrooms, move-in date). • target: 0.92 • range: 0-1
Configured evaluation evidence
  • Benchmark: TenantCRMAutomationBench
  • Intent Extraction F1 target: 0.92
  • 1 public reference case
Configured runtime
  • JavaScript execution harness
  • javascript 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
  • Coplay AI · Required
  • Mastra AI · Optional
  • Aim · Optional
Orchestration
  • Mastra AI · Optional

Evaluation contract

  • slot_booking_validation · Weight 1
  • intent_extraction_f1 · Weight 1

Metrics

  • intent_extraction_f1 · Target 0.92

Benchmarks

  • TenantCRMAutomationBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing message history and available tour slots

    Output: JSON with lead qualification score, move_in_date, and selected_slot

    Execution harness: JavaScript

Evaluation tools

  • Mastra AI · Agent Framework
  • Coplay AI · Interface Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Mastra AI & Coplay AI Multifamily Demand Handling Assistant