Skilljar is a learning management system that hosts our educational content. You're logging into it to access the Anthropic course materials. This separate platform allows us to provide interactive learning experiences, track your progress, and ensure you have access to all course resources in an organized way.
Claude Platform & Solution Design
Course 1 of 5 in Claude Certified Architect - Professional Prep Course
Master the design decisions that translate an ambiguous business problem into a defensible Claude solution architecture.
Designing solutions with Claude goes beyond choosing a model. Four decisions come before you build: what work Claude owns, what form it takes, which reference architecture to commit to, and which model and context strategy keep the solution accurate and affordable. This module builds the framework for making those decisions, translating a vague request into a proposed solution, and defending your choices against credible alternatives.
Learning objectives:
By the end of this module, you'll be able to:
- Break down a stakeholder's request into what Claude does, what existing systems do, and what humans do, using the four properties of generative AI as your decision lens
- Choose between an augmented call, a workflow, and an agent by naming what each choice costs
- Pick a reference architecture pattern for the problem shape in front of you and recognize when retrieval is doing a job that live-state should own
- Make defensible model, context-window, and context-strategy decisions, and use evaluations as the gate before any model swap
- Know where each platform entry point fits (Claude.ai, the API, an SDK, Claude Code, or an MCP server) and what customization belongs at each layer
- Distinguish between the Claude entry points a user sees, the build-time interfaces an engineer codes against, and the delivery routes an enterprise procures, and identify which are ruled out by governance or regulated-industry constraints before any other trade-off applies