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.
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.
How work is evaluated
Evaluates streaming JSON formatting and proposal scoring consistency against advisory rubric criteria.
Challenge datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
Valid Streamed JSON
Checks that complete output parses as valid JSON object.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Scoring Consistency
Pearson correlation of awarded scores across repeated identical inputs. • target: 0.95 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
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.
Reference links and supporting material
Dataset of biomedical research proposals submitted for federal advisory review with ground-truth expert scores and strategic domain tags.
Challenge setup
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 that complete output parses as valid JSON object.
- Pearson correlation of awarded scores across repeated identical inputs. • target: 0.95 • range: 0-1
- Benchmark: GrantEval-Bench
- Scoring Consistency target: 0.95
- 1 public reference case
- 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
- Troj AI · Required
- CodeAnt AI · Optional
- Grok 4 Heavy · Optional
Evaluation contract
- Valid Streamed JSON · Weight 1
- Scoring Consistency · Weight 1
Metrics
- Scoring Consistency · Target 0.95
Benchmarks
- GrantEval-Bench
- general
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON proposal object containing title, budget, strategic_alignment, preliminary_data_score
Output: JSON scorecard object with overall_score, recommended_funding_usd, rationale
Execution harness: JavaScript
Evaluation tools
- AI SDK · Streaming Agent Framework
Recipe freeze marker
No recipe freeze time is recorded.