Scenario: Code Generation with Claude Code You are using Claude Code to accelerate software development. Your team uses it for code generation, refactoring, debugging, and documentation. You need to integrate it into your development workflow with custom slash commands, CLAUDE.md configurations, and understand when to use plan mode vs direct execution. Your team is using Claude Code to explore a large legacy e-commerce platform with over 200 interconnected modules. You assign Claude a broad task: "Map the entire checkout flow, including all payment processors, tax calculation services, and fraud detection integrations." After about 30 minutes of exploration, Claude has produced detailed findings about the payment subsystem, but the session's context window is nearly full of verbose discovery output. You still need Claude to investigate the tax and fraud detection subsystems with the same level of depth. What is the most effective approach for continuing this investigation without losing the findings already gathered?
The Context Engineering Stack
Loading lesson content...
Scenario: Customer Support Resolution Agent You are building a customer support resolution agent using the Claude Agent SDK. The agent handles high-ambiguity requests like returns, billing disputes, and account issues. It has access to backend systems through MCP tools (get_customer, lookup_order, process_refund, escalate_to_human). Your target is 80%+ first-contact resolution while knowing when to escalate. A customer starts a chat with: "I don't want to go through a bot. Put me through to a person about order 8421." The message includes enough details that your normal automation would probably resolve the delayed-shipment issue in one or two tool calls. You are tuning the escalation policy and want to avoid both unnecessary deflection and unnecessary automation. What should the agent do next?