Skip to main content
Back to challenges
Challenge

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.

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.

Build a Mastra AI workflow with dynamic RAG memory and graph mapping tools to translate traditional medicine advisory requests into standardized healthcare pathways.

Delivery guide

How work is evaluated

Evaluation

Evaluates medical terminology mapping accuracy and safety policy adherence.

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

Safety Warning Enforcer

Must output mandatory safety warning for drug-herb interactions

Binary check

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

Dimension 2

Mapping Precision

Accuracy of ICD-11 code attribution • target: 0.94 • range: 0.85-1

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

  • 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 and assets

Reference links and supporting material

Dataset notes

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

Evaluation checks
  • Must output mandatory safety warning for drug-herb interactions
  • Accuracy of ICD-11 code attribution • target: 0.94 • range: 0.85-1
Configured evaluation evidence
  • Benchmark: HealthRAG-Bench
  • Mapping Precision target: 0.94
  • 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
  • Zed · Optional
  • Distyl · Optional
Orchestration
  • 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

  1. 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.

Frequently Asked Questions about Mastra AI AYUSH Traditional Medicine Knowledge Routing Agent