Skip to main content
Loading navigation
Back to challenges

Mastra AI Land Entitlement and Permit Risk Scoring Workflow with Claude Code

Suburban land developments suffer expensive timeline delays due to undetected municipal entitlement restrictions and zoning code conflicts. Construct a Mastra AI workflow with Claude Code integration to cross-evaluate local zoning codes against parcel geometry. Achieve automated zoning error detection across 100 test parcels with 90% precision.

Business OperationsHosted by Vera
Sign in free to start

What you are building

Implement a Mastra AI graph workflow utilizing Claude Code CLI execution to validate land parcel zoning regulations and generate municipal permit risk scores.

How work is evaluated

Evaluation

Evaluates accuracy of zoning risk scoring and restriction compliance logic across land parcels.

Datasets

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

How submissions are scored

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

far_compliance_check

Validates FAR calculation and compliance decision

Binary check

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

Dimension 2

risk_precision

Accuracy of permit risk score assignment • target: 0.9 • 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

  • Build workflow graphs in Mastra AI (`@mastra/core`) with sequential steps for zoning verification and risk calculation

  • Integrate Claude Code automated workspace execution tools to generate dynamic GeoJSON constraint checkers

  • Ingest municipal setback requirements, floor-area ratios (FAR), and allowed land use classifications

  • Produce structured permit risk scores and variance mitigation recommendations

Resources

Dataset notes

Suburban zoning district specification records mapped with land parcel geometry and building envelopes.

Challenge setup

Evaluates accuracy of zoning risk scoring and restriction compliance logic across land parcels.

Challenge input

JSON containing parcel_sqft, proposed_building_sqft, max_far, zoning_district

Mastra AI

TypeScript AI workflow framework for sequential agent graphs.

Claude Code

Automated AI engineering tooling for executing local CLI scripts.

Evaluated output

JSON containing compliant, calculated_far, permit_risk_score, violations

Evaluation checks
  • Validates FAR calculation and compliance decision
  • Accuracy of permit risk score assignment • target: 0.9 • range: 0-1
Configured evaluation evidence
  • Benchmark: Zoning Compliance Code Benchmark
  • Risk Precision target: 0.9
  • 1 public reference case
Configured runtime
  • JavaScript execution harness
  • javascript sandbox (unavailable on Versalist)

Shows the first task, up to three tools, and up to three evidence items.

View technical recipe

Configured tools

Action Space
  • Claude Code · Required
  • Mastra AI · Optional
  • Kore.ai · Optional
Observation
  • Claude Code · Required
Orchestration
  • Mastra AI · Optional

Evaluation contract

  • far_compliance_check · Weight 1
  • risk_precision · Weight 1

Metrics

  • risk_precision · Target 0.9

Benchmarks

  • Zoning Compliance Code Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing parcel_sqft, proposed_building_sqft, max_far, zoning_district

    Output: JSON containing compliant, calculated_far, permit_risk_score, violations

    Execution harness: JavaScript

Evaluation tools

  • Mastra AI · agent_framework
  • Claude Code · ai_engineering_tool

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Mastra AI Land Entitlement and Permit Risk Scoring Workflow with Claude Code