A developer shares their journey from AI skepticism to pragmatic adoption after months of hands-on experience with LLMs and AI coding assistants. Key learnings include the importance of providing structured context (who, what, why, how), treating AI as a collaborator rather than magic, using git commits as save points, switching between models for different tasks, and creating MCP servers for framework-specific knowledge. The author emphasizes that AI requires a learning curve and intentional practice to use effectively, advocating for industry discussions that acknowledge AI's utility while addressing ethical concerns.
Table of contents
The Learning CurveA Mindset ShiftRate of ChangeEffective Use of AIPrompt RulesSwitch Models as NeededAgent Mode vs Ask ModeDon’t Trust the AIUse Git Commit like “Save Game”Create and Use MCP ServersConclusionSort: