Skip to main content
Back to challenges
Challenge

Automate Data Breach Analysis with LangGraph and Gemini 3.1 Pro

Create a multi-agent system using LangChain and LangGraph to analyze complex data sets following corporate security breaches. The system employs Gemini 3.1 Pro for high-throughput analysis and structured extraction. By leveraging Claude Code for rapid iterative development and Bito AI for conversational knowledge management, developers can build a graph-based workflow that classifies sensitive data leaks. The Vercel AI Gateway acts as the routing layer to manage model latency and performance across the agent ensemble.

Workflow AutomationHosted by Vera
Sign in free to start
Challenge brief

What you are building

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

Implement a stateful agent graph with LangGraph and Gemini 3.1 Pro for autonomous data analysis.

Delivery guide

How work is evaluated

Evaluation

Validation of analytical accuracy on synthesized breach datasets.

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

Graph Completion

Agent must complete all nodes in graph

Binary check

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

Dimension 2

Latency

Inference time in ms • target: 1200 • range: 0-5000

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

  • Master LangGraph primitives for maintaining state across agent nodes

  • Implement multi-agent cooperation using LangChain specialized tool agents

  • Configure Vercel AI Gateway to handle model fallbacks and performance telemetry

  • Leverage Claude Code to accelerate the implementation of complex parsing logic

  • Design a Bito AI interaction pattern for technical assistance during development

  • Optimize Gemini 3.1 Pro usage for high-speed unstructured data extraction

Resources and assets

Reference links and supporting material

Dataset notes

Sample data for 1 tasks

Challenge setup

Validation of analytical accuracy on synthesized breach datasets.

Challenge input

Unstructured text corpus

LangGraph

Runtime for stateful agent workflows.

Google Gemini

Google's multimodal AI model

Bito AI

AI assistant for dev tasks

Evaluated output

Categorized impact report

Evaluation checks
  • Agent must complete all nodes in graph
  • Inference time in ms • target: 1200 • range: 0-5000
Configured evaluation evidence
  • Latency target: 1200
  • 1 public reference case
Configured runtime
  • Python execution harness

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
  • LangGraph · Required
  • Google Gemini · Optional
  • Bito AI · Optional
Orchestration
  • LangGraph · Required

Evaluation contract

  • Graph Completion · Weight 1
  • Latency · Weight 1

Metrics

  • Latency · Target 1200

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: Unstructured text corpus

    Output: Categorized impact report

    Execution harness: Python

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Automate Data Breach Analysis with LangGraph and Gemini 3.1 Pro