Skip to main content
Loading navigation
Back to challenges

Pydantic AI Account Aggregator Consent Pipeline with Agno Engine

Financial information providers need strictly validated, consent-aware underwriting pipelines for micro-loans. Build a type-safe financial consent and data extraction engine using Pydantic AI and Agno to guarantee schema compliance and audit compliance.

Business OperationsHosted by Vera
Sign in free to start

What you are building

Construct a strict type-safe Account Aggregator payload validation pipeline using Pydantic AI and Agno execution runtime.

How work is evaluated

Evaluation

Validates schema adherence and accurate consent verification in financial payloads.

Datasets

Public datasets, plus the private datasets you have access to.

How submissions are scored

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

schema_validation_pass

Ensures output conforms strictly to Pydantic model.

Binary check

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

Dimension 2

extraction_accuracy

Accuracy of financial attribute calculation • target: 1 • 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

  • Define strict Pydantic AI data models for Account Aggregator payloads

  • Incorporate Agno runtime features for multi-step financial extraction

  • Validate user consent artifacts against RBI Account Aggregator guidelines

Resources

Dataset notes

Anonymized Account Aggregator consent receipts and sample banking ledgers.

Challenge setup

Validates schema adherence and accurate consent verification in financial payloads.

Challenge input

JSON consent payload

Pydantic AI

Mandatory requirement

Agno

Assigned tool

Evaluated output

Validated structured credit summary JSON

Evaluation checks
  • Ensures output conforms strictly to Pydantic model.
  • Accuracy of financial attribute calculation • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: AA-Schema-Bench
  • Extraction Accuracy target: 1
  • 1 public reference case
Configured runtime
  • 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

Action Space
  • Agno · Required
  • Pydantic AI · Optional
  • Sarvam AI · Optional
Orchestration
  • Agno · Required
  • Pydantic AI · Optional

Evaluation contract

  • schema_validation_pass · Weight 1
  • extraction_accuracy · Weight 1

Metrics

  • extraction_accuracy · Target 1

Benchmarks

  • AA-Schema-Bench
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON consent payload

    Output: Validated structured credit summary JSON

    Execution harness: Python

Evaluation tools

  • Pydantic AI · Agent Framework
  • Agno · Agent Systems Runtime

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Pydantic AI Account Aggregator Consent Pipeline with Agno Engine