Skip to main content
Back to challenges
Challenge

Build a Multifamily Demand Intake Agent with Mastra AI in TypeScript

Multifamily leasing teams lose qualified tenants due to slow inquiry handling and fragmented communication channels during peak leasing periods. Build a TypeScript Mastra AI agent workflow that automates lead qualification and tour scheduling, maintaining response latency under two minutes.

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.

Deploy an asynchronous TypeScript workflow using Mastra AI to process tenant leasing inquiries, score lead intent, and auto-book property tours.

Delivery guide

How work is evaluated

Evaluation

Tests lead scoring accuracy and valid tour scheduling output for incoming tenant messages.

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

Qualification Logic Test

Validates correct qualification flag based on budget and timeline constraints.

Binary check

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

Dimension 2

Processing Latency

Execution latency in milliseconds. • target: 800 • range: 0-2000

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

  • Create stateful Mastra AI agent workflows in TypeScript to ingest raw email and SMS leasing leads.

  • Implement automated lead qualification scoring based on move-in date, budget, and unit preference.

  • Integrate calendar availability tools to automatically schedule physical or virtual tours.

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic multi-channel tenant inquiry dataset with move-in dates, unit requirements, and calendar availability.

Challenge setup

Tests lead scoring accuracy and valid tour scheduling output for incoming tenant messages.

Challenge input

JSON with raw_message and calendar_slots

Mastra AI

Assigned TypeScript agent framework with built-in workflow engine.

Evaluated output

JSON with lead_score (0-100), qualified (boolean), scheduled_slot

Evaluation checks
  • Validates correct qualification flag based on budget and timeline constraints.
  • Execution latency in milliseconds. • target: 800 • range: 0-2000
Configured evaluation evidence
  • Benchmark: Leasing_Operations_Eval
  • Processing Latency target: 800
  • 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
  • Mastra AI · Required
  • Traceloop · Optional
  • Deepgram · Optional
Orchestration
  • Mastra AI · Required

Evaluation contract

  • Qualification Logic Test · Weight 1
  • Processing Latency · Weight 1

Metrics

  • Processing Latency · Target 800

Benchmarks

  • Leasing_Operations_Eval
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with raw_message and calendar_slots

    Output: JSON with lead_score (0-100), qualified (boolean), scheduled_slot

    Execution harness: JavaScript

Evaluation tools

  • Mastra AI · Agent System Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Multifamily Demand Intake Agent with Mastra AI in TypeScript