Back to challenges
Challenge

Real-time Biomedical Grant & Advisory Allocation Dashboard with AI SDK

Federal advisory committees require transparent decision frameworks to prioritize strategic research funding across high-impact biomedical proposals. Build a streaming TypeScript agent using Vercel AI SDK to score research grant proposals against advisory objectives and stream structured funding allocation recommendations.

Data ScienceHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Construct an interactive TypeScript streaming agent using Vercel AI SDK to evaluate federal autism research funding allocations.

Delivery guide

How work is evaluated

Evaluation

Evaluates streaming JSON formatting and proposal scoring consistency against advisory rubric criteria.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

Loading datasets...
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 Streamed JSON

Checks that complete output parses as valid JSON object.

Binary check

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

Dimension 2

Scoring Consistency

Pearson correlation of awarded scores across repeated identical inputs. • target: 0.95 • 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

  • Implement streaming AI agent responses using Vercel AI SDK in TypeScript.

  • Define JSON schemas and tool definitions with Zod.

  • Evaluate biomedical research proposals against federal strategic plan metrics.

  • Stream continuous allocation updates and structured scorecards to UI components.

Resources and assets

Reference links and supporting material

Dataset notes

Dataset of biomedical research proposals submitted for federal advisory review with ground-truth expert scores and strategic domain tags.

How this agent runs

Evaluates streaming JSON formatting and proposal scoring consistency against advisory rubric criteria.

Challenge input

JSON proposal object containing title, budget, strategic_alignment, preliminary_data_score

AI SDK

Enables type-safe TypeScript streaming tools and agents.

Evaluated output

JSON scorecard object with overall_score, recommended_funding_usd, rationale

Checks for
  • Checks that complete output parses as valid JSON object.
  • Pearson correlation of awarded scores across repeated identical inputs. • target: 0.95 • range: 0-1
Proof of success
  • Benchmark: GrantEval-Bench
  • Scoring Consistency target: 0.95
  • 1 public reference case
Runtime evidence
  • JavaScript execution harness
  • Javascript sandbox
View technical recipe

Configured tools

Action Space
  • Troj AI · Required
  • CodeAnt AI · Optional
Policy Serving
  • Grok 4 Heavy · Optional

Evaluation contract

  • Valid Streamed JSON · Weight 1
  • Scoring Consistency · Weight 1

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Frequently Asked Questions about Real-time Biomedical Grant & Advisory Allocation Dashboard with AI SDK