Challenge

Build an Automated Cyber Incident Triage System with AutoGen and Pydantic AI

Financial institutions face persistent advanced threat tactics from state-sponsored cyber campaigns targeting core banking infrastructure. Build an AutoGen multi-agent system using Pydantic AI to ingest threat feeds, map IOCs against MITRE ATT&CK patterns, and generate actionable remediation playbooks. Achieve automated incident triage with under two-minute latency and high classification accuracy.

CybersecurityHosted by Vera
Challenge brief

What you are building

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

Develop an AutoGen multi-agent conversational framework paired with Pydantic AI validation to process threat intelligence feeds and map attacks against banking assets.

Delivery guide

How work is evaluated

Evaluation

Evaluates the incident response agent's capacity to accurately map threat indicators to MITRE tactics and output structured playbooks.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

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

valid_mitre_code_test

Checks if returned technique ID is a valid MITRE code

Binary check

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

Dimension 2

triage_precision

Precision in identifying correct threat severity and technique • target: 0.9 • 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

What you should walk away with

  • Construct multi-agent AutoGen conversations for security incident orchestration

  • Integrate Pydantic AI for type-safe alert structured parsing and validation

  • Automate mapping of raw log indicators (IOCs) to MITRE ATT&CK enterprise tactics

  • Generate context-aware remediation playbooks for SOC tier-2 analysts

Resources and assets

Reference links and supporting material

Dataset notes

Dataset of 200 synthetic SOC log alerts simulating credential dumping and lateral movement targeting core banking servers.

How this agent runs

Evaluates the incident response agent's capacity to accurately map threat indicators to MITRE tactics and output structured playbooks.

Challenge input

Unstructured text payload containing firewall and system execution logs

AutoGen

Allows back-and-forth negotiation between analyst and supervisor agents.

Pydantic AI

Ensures output structured data adheres strict cybersecurity alert schemas.

Evaluated output

JSON object with threat_actor_class, mitre_technique_id, severity, and remediation_action

Checks for
  • Checks if returned technique ID is a valid MITRE code
  • Precision in identifying correct threat severity and technique • target: 0.9 • range: 0-1
Proof of success
  • Benchmark: SOC Cyber Automation Benchmark
  • Triage Precision target: 0.9
  • 1 public reference case
Runtime evidence
  • Python execution harness
  • Python sandbox (unavailable on Versalist)
View technical recipe

Configured tools

Action Space
  • AutoGen · Required
  • Pydantic AI · Optional
  • Microsoft AutoGen · Optional
Orchestration
  • Pydantic AI · Optional

Evaluation contract

  • valid_mitre_code_test · Weight 1
  • triage_precision · Weight 1

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Frequently Asked Questions about Build an Automated Cyber Incident Triage System with AutoGen and Pydantic AI