Get in Touch
 Duration 35 hours

Course Outline

Core LangGraph Concepts for Finance

  • A review of LangGraph architecture and the mechanics of stateful execution.
  • Exploring finance use cases, including research copilots, trade support systems, and customer service agents.
  • Addressing regulatory constraints and the importance of auditability.

Financial Data Standards and Ontologies

  • Foundations of ISO 20022, FpML, and FIX protocols.
  • Techniques for mapping schemas and ontologies into the graph state.
  • Managing data quality, lineage, and Personally Identifiable Information (PII).

Orchestrating Financial Process Workflows

  • Designing KYC and AML onboarding workflows.
  • Managing trade lifecycles, exceptions, and case management.
  • Structuring credit adjudication and decisioning paths.

Compliance, Risk Management, and Controls

  • Enforcing policies and managing model risk.
  • Implementing guardrails, approval chains, and human-in-the-loop interventions.
  • Maintaining audit trails, data retention, and model explainability.

System Integration and Deployment

  • Connecting LangGraph to core banking systems, data lakes, and external APIs.
  • Managing containerisation, secrets, and environment configurations.
  • Utilising CI/CD pipelines, staged rollouts, and canary releases.

Observability and Performance Management

  • Implementing structured logging, metrics, tracing, and cost monitoring.
  • Conducting load testing and managing Service Level Objectives (SLOs) and error budgets.
  • Establishing incident response, rollback strategies, and resilience patterns.

Quality Assurance, Evaluation, and Safety

  • Building unit, scenario, and automated evaluation harnesses.
  • Applying red teaming techniques, adversarial prompt testing, and safety checks.
  • Curation of datasets, monitoring for drift, and continuous improvement cycles.

Wrap-up and Future Directions

Requirements

  • A working knowledge of Python and the development of LLM applications.
  • Practical experience with APIs, container technologies, or cloud services.
  • Foundational familiarity with financial domains or data models.

Target Audience

  • Domain technologists.
  • Solution architects.
  • Consultants developing LLM agents within regulated industries.

Number of participants


Price per participant

Provisional Upcoming Courses (Require 5+ participants)

Related Categories