Mastra AI AYUSH Traditional Medicine Knowledge Routing Agent
Public health systems struggle to harmonize traditional AYUSH clinical evidence with modern clinical terminology and citizen triage workflows. You will construct a TypeScript agentic workflow that parses traditional medicine research repositories and maps interventions to standardized ICD-11 codes.
What you are building
Build a Mastra AI workflow with dynamic RAG memory and graph mapping tools to translate traditional medicine advisory requests into standardized healthcare pathways.
How work is evaluated
Evaluates medical terminology mapping accuracy and safety policy adherence.
Datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
Safety Warning Enforcer
Must output mandatory safety warning for drug-herb interactions
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Mapping Precision
Accuracy of ICD-11 code attribution • target: 0.94 • range: 0.85-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Learning goals
Build Mastra AI agent and step-based workflows in TypeScript/Node.js
Map AYUSH herbal formulations to standardized WHO ICD-11 extension codes
Configure Mastra AI memory and vector search tools for medical corpus query
Implement safety guardrails for integrative healthcare advice routing
Resources
Curated corpus of traditional medicine clinical literature mapped to WHO ICD-11 code categories.
Challenge setup
Evaluates medical terminology mapping accuracy and safety policy adherence.
Challenge input
JSON with symptom description and traditional formulation name
Mastra AI
Provides TypeScript workflows, agents, and RAG integration.
Evaluated output
JSON with primary_icd11_code, integrative_recommendation, and safety_warning
- Must output mandatory safety warning for drug-herb interactions
- Accuracy of ICD-11 code attribution • target: 0.94 • range: 0.85-1
- Benchmark: HealthRAG-Bench
- Mapping Precision target: 0.94
- 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
- Zed · Optional
- Distyl · Optional
- Mastra AI · Required
Evaluation contract
- Safety Warning Enforcer · Weight 1
- Mapping Precision · Weight 1
Metrics
- Mapping Precision · Target 0.94
Benchmarks
- HealthRAG-Bench
- biotech
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON with symptom description and traditional formulation name
Output: JSON with primary_icd11_code, integrative_recommendation, and safety_warning
Execution harness: JavaScript
Evaluation tools
- Mastra AI · Agent Framework
Recipe freeze marker
No recipe freeze time is recorded.