CPN Learning Path CPN Connect On Demand Library All Courses Home

Claude Platform & Model Foundations

Course 1 of 8 in Claude Certified Associate - Foundations Prep Course

Master the four decisions that set the quality ceiling for every Claude session before you write a single prompt: entry point, capability features, model, and context.

rate limit

Code not recognized.

About this course

For recurring work, team projects, and deliverables that require a high-quality review, the feature decisions made before writing a prompt determine the quality ceiling for session outputs. This module builds the framework for the first four decisions that need to be made: which entry point to use, which capability features to activate, which model to select, and how to manage context across a session. These decisions determine whether session builds upon prior work or requires constant re-setup.

Learning objectives
By the end of this module, you will be able to:

  • Select the appropriate Claude entry point and feature set for a given professional task
  • Differentiate Haiku, Sonnet, and Opus models by their capability characteristics and task fit
  • Match model selection to task requirements, including quality, speed, and volume trade-offs
  • Manage context limitations and use memory features to maintain continuity across sessions

About this course

For recurring work, team projects, and deliverables that require a high-quality review, the feature decisions made before writing a prompt determine the quality ceiling for session outputs. This module builds the framework for the first four decisions that need to be made: which entry point to use, which capability features to activate, which model to select, and how to manage context across a session. These decisions determine whether session builds upon prior work or requires constant re-setup.

Learning objectives
By the end of this module, you will be able to:

  • Select the appropriate Claude entry point and feature set for a given professional task
  • Differentiate Haiku, Sonnet, and Opus models by their capability characteristics and task fit
  • Match model selection to task requirements, including quality, speed, and volume trade-offs
  • Manage context limitations and use memory features to maintain continuity across sessions