Back to challenges
Challenge

Automated Multifamily Lead Qualification Agent with Mastra AI & Bito AI

Multifamily operators struggle with high lead volumes and slow response times, resulting in missed lease opportunities. Build a TypeScript lead-handling agent with Mastra AI and Bito AI assistants to process tenant inquiries, score credit compliance, and schedule property tours with 95% automated accuracy.

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 automated tenant inquiry workflow using Mastra AI step execution, tool calling, and Bito AI assistance interface integration.

Delivery guide

How work is evaluated

Evaluation

Evaluates tenant lead qualification accuracy and calendar tour scheduling action triggers.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

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

correct_qualification_flag

Correctly flags lead qualification based on 3x rent income policy

Binary check

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

Dimension 2

qualification_accuracy

Percentage of correctly classified leads • target: 0.95 • 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

  • Design a Mastra AI workflow that ingests tenant inquiries and extracts intent.

  • Implement a credit score and income verification rule check.

  • Integrate Bito AI assistant context to dynamically craft personalized tour scheduling responses.

  • Achieve 95% classification accuracy across varied tenant communication styles.

Resources and assets

Reference links and supporting material

Dataset notes

100 simulated tenant inbound inquiries across email, SMS, and portal messages with ground-truth income and lease preferences.

How this agent runs

Evaluates tenant lead qualification accuracy and calendar tour scheduling action triggers.

Challenge input

JSON containing lead_id, message, income_monthly, desired_move_in

Mastra AI

Framework assignment for building TypeScript workflows.

Bito AI

Tool required for response synthesis and developer assistance.

Evaluated output

JSON with qualified boolean, target_unit_type, follow_up_action

Checks for
  • Correctly flags lead qualification based on 3x rent income policy
  • Percentage of correctly classified leads • target: 0.95 • range: 0-1
Proof of success
  • Benchmark: AgentOps-Leasing-Bench
  • Qualification Accuracy target: 0.95
  • 1 public reference case
Runtime evidence
  • JavaScript execution harness
  • javascript sandbox (unavailable on Versalist)
View technical recipe

Configured tools

Action Space
  • Bito AI · Required
  • Mastra AI · Optional
  • Metaflow · Optional
Orchestration
  • Mastra AI · Optional

Evaluation contract

  • correct_qualification_flag · Weight 1
  • qualification_accuracy · Weight 1

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Frequently Asked Questions about Automated Multifamily Lead Qualification Agent with Mastra AI & Bito AI