Skip to main content
Back to challenges
Challenge

Google ADK Multimodal Traditional Medicine Diagnostic Assistant

Integrating traditional medicine taxonomy with modern clinical diagnostic frameworks requires rich multimodal reasoning over clinical text and herbal imagery. Build an agent using Google ADK and Gemini 1.5 Pro to standardize clinical research records.

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.

Develop an AI assistant for traditional medicine taxonomy using Google Agent Development Kit and Gemini.

Delivery guide

How work is evaluated

Evaluation

Evaluates accuracy of herbal mapping and medical terminology alignment.

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

valid_standard_name

Ensures output maps to correct botanical entity.

Binary check

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

Dimension 2

botanical_accuracy

Accuracy of botanical mapping • target: 0.92 • 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

  • Utilize Google ADK to structure multimodal analysis tasks

  • Leverage Gemini vision capabilities for herbal sample identification

  • Map traditional formulations onto WHO ICD-11 global standards

Resources and assets

Reference links and supporting material

Dataset notes

Annotated corpus of traditional medicine texts and botanical classifications.

Challenge setup

Evaluates accuracy of herbal mapping and medical terminology alignment.

Challenge input

JSON containing query and image descriptor

Google ADK

Mandatory framework requirement

Evaluated output

JSON mapped diagnostic record

Evaluation checks
  • Ensures output maps to correct botanical entity.
  • Accuracy of botanical mapping • target: 0.92 • range: 0-1
Configured evaluation evidence
  • Benchmark: Health-Taxonomy-Bench
  • Botanical Accuracy target: 0.92
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python 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

Environment
  • Modal · Optional
Action Space
  • Google ADK · Required
  • Google · Optional
Policy Serving
  • Modal · Optional

Evaluation contract

  • valid_standard_name · Weight 1
  • botanical_accuracy · Weight 1

Metrics

  • botanical_accuracy · Target 0.92

Benchmarks

  • Health-Taxonomy-Bench
  • biotech

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing query and image descriptor

    Output: JSON mapped diagnostic record

    Execution harness: Python

Evaluation tools

  • Google ADK · Agent SDK

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Google ADK Multimodal Traditional Medicine Diagnostic Assistant