Build a Pydantic AI VC Portfolio Liquidity Predictor
Venture capital firms tracking startup investment rounds require structured runway and liquidity analysis. Construct a Pydantic AI investment analyst agent that processes funding updates, calculates runway projections, and enforces explicit type constraints with 100% schema validation accuracy.
What you are building
Develop a Pydantic AI investment analyst agent that evaluates funding round telemetry and projects venture portfolio runway.
How work is evaluated
Evaluates portfolio model accuracy and Pydantic output validation success.
Datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
runway_math_check
Verifies accuracy of runway division math
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
schema_conformance
Validation rate against target Pydantic models • target: 1 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Learning goals
Utilize Pydantic AI agent models to process investment round announcements
Calculate quarterly burn rates and post-money valuation metrics
Enforce strict numeric schemas for financial metric models
Output standardized portfolio vulnerability reports for investors
Resources
Synthetic venture capital funding round summaries and financial metrics.
Challenge setup
Evaluates portfolio model accuracy and Pydantic output validation success.
Challenge input
JSON funding event payload
Pydantic AI
Type-safe financial analysis framework
Evaluated output
Pydantic model JSON object with runway_months and status
- Verifies accuracy of runway division math
- Validation rate against target Pydantic models • target: 1 • range: 0-1
- Benchmark: Financial Modeling Agent Benchmark
- Schema Conformance target: 1
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
Shows the first task, up to three tools, and up to three evidence items.
View technical recipe
Configured tools
- Pydantic AI · Required
- RAI · Optional
- ZenML · Optional
- Pydantic AI · Required
Evaluation contract
- runway_math_check · Weight 1
- schema_conformance · Weight 1
Metrics
- schema_conformance · Target 1
Benchmarks
- Financial Modeling Agent Benchmark
- general
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON funding event payload
Output: Pydantic model JSON object with runway_months and status
Execution harness: Python
Evaluation tools
- Pydantic AI · Agent Framework
Recipe freeze marker
No recipe freeze time is recorded.