Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 35 hours
Course Outline
LangGraph Fundamentals in Finance
- A refresher on LangGraph architecture and stateful execution mechanisms.
- Key finance use cases, including research copilots, trade support, and customer service agents.
- Considerations for regulatory constraints and auditability.
Financial Data Standards and Ontologies
- Overview of ISO 20022, FpML, and FIX protocols.
- Techniques for mapping schemas and ontologies into graph states.
- Best practices for data quality, lineage, and PII management.
Workflow Orchestration for Financial Processes
- Designing KYC and AML onboarding workflows.
- Managing trade lifecycles, exceptions, and case handling.
- Structuring credit adjudication and decisioning paths.
Compliance, Risk, and Controls
- Strategies for policy enforcement and model risk management.
- Implementing guardrails, approval processes, and human-in-the-loop interventions.
- Maintaining audit trails, data retention, and explainability.
Integration and Deployment
- Connecting LangGraph systems to core infrastructure, data lakes, and external APIs.
- Best practices for containerization, secrets management, and environment configuration.
- Establishing CI/CD pipelines, staged rollouts, and canary deployments.
Observability and Performance
- Utilizing structured logs, metrics, traces, and cost monitoring tools.
- Conducting load testing and managing SLOs and error budgets.
- Developing incident response, rollback, and resilience patterns.
Quality, Evaluation, and Safety
- Building unit, scenario, and automated evaluation harnesses.
- Performing red teaming, adversarial prompting, and safety checks.
- Curating datasets and monitoring drift for continuous improvement.
Summary and Next Steps
Requirements
- A solid understanding of Python and LLM application development
- Practical experience with APIs, containers, or cloud services
- Foundational knowledge of financial domains or data models
Audience
- Domain technologists
- Solution architects
- Consultants developing LLM agents within regulated industries