UK Planning Permission Auto-Audit Workflow with Mastra AI
Planning applications in the UK must strictly comply with local council development plans and conservation zone constraints. Construct an end-to-end automated planning permission compliance workflow using Mastra AI in TypeScript to parse proposal summaries and cross-reference UK Planning Portal rules. Achieve 92% precision in identifying required environmental and heritage impact assessments.
What you are building
Build an automated TypeScript planning audit workflow using Mastra AI to evaluate UK planning permission applications for missing compliance documents.
How work is evaluated
Evaluates detection of required statutory documents based on UK planning application criteria.
Datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
flags_match
Verifies correct setting of compliance assessment requirement flags.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
doc_precision
Precision of required document recommendations. • target: 0.92 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Learning goals
Set up Mastra AI workflow step definitions and agent configurations in TypeScript
Parse UK planning application metadata (building height, conservation status, flood zone)
Determine required statutory submission documents (Heritage Impact, Flood Risk Assessment)
Generate automated compliance status reports for municipal planning officers
Resources
Dataset of UK planning application summaries, location attributes, conservation zone statuses, and local authority document checklists.
Challenge setup
Evaluates detection of required statutory documents based on UK planning application criteria.
Challenge input
JSON object with proposal_text, in_conservation_area (boolean), flood_zone_level (1-3)
Mastra AI
Mandatory assigned framework.
Evaluated output
JSON object with requires_heritage_impact (boolean), requires_flood_assessment (boolean), missing_docs (array of strings)
- Verifies correct setting of compliance assessment requirement flags.
- Precision of required document recommendations. • target: 0.92 • range: 0-1
- Benchmark: UKPlanningPolicyBench
- Doc Precision target: 0.92
- 1 public reference case
- 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
- Mastra AI · Required
- RAI · Optional
- Vercel AI Gateway · Optional
- Vercel AI Gateway · Optional
- Mastra AI · Required
Evaluation contract
- flags_match · Weight 1
- doc_precision · Weight 1
Metrics
- doc_precision · Target 0.92
Benchmarks
- UKPlanningPolicyBench
- general
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON object with proposal_text, in_conservation_area (boolean), flood_zone_level (1-3)
Output: JSON object with requires_heritage_impact (boolean), requires_flood_assessment (boolean), missing_docs (array of strings)
Execution harness: JavaScript
Evaluation tools
- Mastra AI · TypeScript Workflow Engine
Recipe freeze marker
No recipe freeze time is recorded.