Frequently Asked
Questions
Duck Creek University provides each student with a virtual training environment for all hands-on classes. Some course materials are available in the training environment, and any printed materials will be given to attendees prior to class. Attendees may use their own laptops or DCU will provide laptops. Your welcome message will indicate the option that is selected for your session.
Business casual (including jeans) is encouraged, and we want each guest to dress comfortably while they attend DCU training.
Trainers are available during breaks and after class to answer questions and to help individual students.
Classes typically start at 8:30 a.m. and usually end at 4:30 p.m. You will receive a welcome message prior to class stating the times for your session. Classes can be dismissed early on their last day so that students can catch flights home. Please inform your instructor at the beginning of the week if you will need to leave early for a flight.
Any individual employed by a Duck Creek client or partner is invited to attend our boot camps and take an assessment. Master and Proficient levels of certification are available.
DCU not only educates attendees on how to configure our products, we teach best practices to help ensure a smooth implementation and provide ease of maintenance post-production. We leverage a combination of lecture, demo, and hands-on lab exercises so that attendees are well-prepared to contribute to their team.
AI explainability, interpretability, and responsible AI principles are built into the platform’s foundation. Our neuro-symbolic architecture combines the reasoning power of large language models with the precision of insurance-specific business rules to enable AI agents that can explain every decision, cite the rules they applied, and produce audit-ready traces.
AI actions are logged in an immutable decision ledger with full decision lineage, model version, inputs, and outputs available on demand. The platform offers built-in guardrails to enforce safety rails on every model call and bias detection monitors for drift post-deployment.
For carriers operating under NAIC, GDPR, CCPA, and state-level AI fairness laws, this means the platform is designed to enable compliance — not just support it.
The platform is designed to be model-agnostic, working with any foundation model including OpenAI, Google’s Gemini, Anthropic’s Claude, Meta Llama, and Mistral models. Carriers can also bring their own models.
The Agentic AI Platform supports Model Context Protocol (MCP) and Agent to Agent Protocol (A2A). By supporting these emerging standards, Duck Creek aims to be the preferred choice for orchestrating agents regardless of the protocols used.
Designed for global insurers who want to bring Agentic AI into core insurance workflows. The platform supports bringing your own AI infrastructure or using our Agentic AI Platform for agentic operations. It serves developers and enterprises who need robust infrastructure to support dynamic execution paths at runtime, controls to monitor behavior, powerful tools to enhance agents, and the flexibility to adapt as the landscape evolves.
The Duck Creek Agentic AI Platform is an insurance-native, purpose-built platform designed to build, connect, and optimize AI agents at scale. It is fully interoperable and extensible to compliment your existing AI investments.
Learn more about Duck Creek Agentic AI Platform