Skip to main content
Back to challenges
Challenge

Develop an OpenAI Agents SDK Runway Optimization Agent with Pydantic AI

Fintech start-ups face severe funding constraints requiring rigorous financial burn optimization. Build an autonomous agent using OpenAI Agents SDK alongside Pydantic AI validation to analyze corporate spending, project cash runway, and flag operational anomalies with 98% schema compliance.

CybersecurityHosted by Vera
Sign in free to start
Challenge brief

What you are building

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

Utilize OpenAI Agents SDK with Pydantic AI type-safe schemas to construct an automated cash runway and expenditure analysis pipeline.

Delivery guide

How work is evaluated

Evaluation

Measures runway projection accuracy and expense flag precision against historical fintech ledger baselines.

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

schema_validation_test

Output must conform 100% to Pydantic AI output schemas.

Binary check

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

Dimension 2

runway_error_margin

Absolute percentage error on predicted runway months. • target: 0.01 • range: 0-0.05

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

  • Construct structured financial agents using OpenAI Agents SDK

  • Enforce dynamic output validation with Pydantic AI models

  • Implement anomaly detection across recurring SaaS and operational expenses

  • Generate automated cost-reduction strategies based on burn rate metrics

Resources and assets

Reference links and supporting material

Dataset notes

Fintech cash flow dataset detailing monthly burn rates, SaaS subscriptions, and operational expenses.

Challenge setup

Measures runway projection accuracy and expense flag precision against historical fintech ledger baselines.

Challenge input

CSV payload containing 12-month corporate expenditures

OpenAI Agents SDK

Provides fast multi-turn execution and tool usage.

Pydantic AI

Guarantees strict type safety for agent outputs.

Evaluated output

JSON payload containing projected runway months and flag array

Evaluation checks
  • Output must conform 100% to Pydantic AI output schemas.
  • Absolute percentage error on predicted runway months. • target: 0.01 • range: 0-0.05
Configured evaluation evidence
  • Benchmark: Financial Modeling Benchmark v1
  • Runway Error Margin target: 0.01
  • 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

Action Space
  • Pydantic AI · Required
  • OpenAI · Optional
  • Azure OpenAI Service · Optional
Orchestration
  • Pydantic AI · Required

Evaluation contract

  • schema_validation_test · Weight 1
  • runway_error_margin · Weight 1

Metrics

  • runway_error_margin · Target 0.01

Benchmarks

  • Financial Modeling Benchmark v1
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: CSV payload containing 12-month corporate expenditures

    Output: JSON payload containing projected runway months and flag array

    Execution harness: Python

Evaluation tools

  • OpenAI Agents SDK · Agent Orchestrator
  • Pydantic AI · Schema Validator

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Develop an OpenAI Agents SDK Runway Optimization Agent with Pydantic AI