Agent as coder Challenge submission by Chandana H#39
Open
chandu1110 wants to merge 7 commits into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request introduces agent.py, a stateful, autonomous coding agent built to solve the "Agent-as-Coder" challenge. The agent is designed to analyze PDF bank statements, generate custom Python parsers, and iteratively self-correct its code based on empirical validation.
✨ Key Features
Autonomous Self-Correction: The agent uses a "generate, test, refine" loop. It analyzes test failures and uses that context to improve the code in subsequent attempts.
Stateful Workflow: Built with LangGraph, the agent maintains a stateful context throughout its execution, allowing it to learn and make decisions based on past actions.
Schema-Driven Design: The agent is not hardcoded for any specific bank. It dynamically adapts its parsing strategy based on the schema of the provided ground-truth CSV file.
Robust Error Handling: The agent is designed to handle PDF parsing errors, code execution errors, and data validation failures, using them as feedback for its correction loop.