I explored multi-agent architectures, refined my AI coding workflows using MCP and Cursor, and experimented with GPT 4.1 prompting. I also learned handy uv and jq tricks while investigating application-specific LLM evaluations.
Vibe coding lets people build software by describing what they want and iterating on results, even if they do not understand or inspect the generated code.
Coding agents let humanities students build software without becoming programmers. The valuable skill is expressing intent clearly and critically evaluating what the machine produces.
AI performance depends less on clever prompts than on context. Give models the right goals, examples, constraints, history, and tools so they can act effectively.
With coding agents, specifications become the product and code becomes cheap. Work faster by delegating implementation, testing aggressively, and optimizing for review.
