COSMIC AML Detection Workflow with OpenAI Agents SDK & Braintrust
Financial institutions need automated anti-money laundering sharing pipelines to detect cross-bank illicit networks. Build a COSMIC collaborative sharing intelligence pipeline using OpenAI Agents SDK to analyze financial logs and flag suspicious networks with audited confidence scoring.
What you are building
The core problem, expected build, and operating context for this challenge.
Implement an automated anti-money laundering analysis workflow using OpenAI Agents SDK and Braintrust for prompt evaluation.
How work is evaluated
Evaluates AML detection precision, recall, and structured evaluation logging via Braintrust.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
valid_json_structure
Ensures risk_score and flagged_entities exist
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
f1_score
F1 Score on anomaly identification • target: 0.9 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Build a multi-tool agent using OpenAI Agents SDK
Implement COSMIC data parsing and anomaly scoring
Evaluate AML detection accuracy using Braintrust
Reference links and supporting material
Synthetic bank ledger records mimicking Singapore financial transactions for COSMIC AML evaluation.
How this agent runs
Evaluates AML detection precision, recall, and structured evaluation logging via Braintrust.
Challenge input
JSON containing customer logs and transaction graphs
OpenAI Agents SDK
Agent orchestration
Braintrust
Prompt evaluation and observability
Evaluated output
JSON containing risk_score, flagged_entities, and reasoning
- Ensures risk_score and flagged_entities exist
- F1 Score on anomaly identification • target: 0.9 • range: 0-1
- Benchmark: FinAML-Bench
- F1 Score target: 0.9
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
View technical recipe
Configured tools
- RAI · Optional
- OpenAI · Optional
- Braintrust · Required
- Braintrust · Required
Evaluation contract
- valid_json_structure · Weight 1
- f1_score · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.