Most posts here are part of a series, so if one is useful, the one before it probably is too. The SQL for Python Developers series is the place to start if you came for SQL; I Vibe Coded and Lived to Tell if you came for the AI stories.
It's not either/or. Use ORMs for CRUD and migrations; use raw SQL for analytics and complex queries. A practical decision guide.
After extracting a shared library, starting a new tool went from a day of boilerplate to two imports. The queue got longer, not shorter. Here's what's next.
String formatting in SQL is dangerous. Learn parameterized queries to keep user input safe and prevent SQL injection attacks.
I ran out of Claude tokens and handed my six-repo codebase to Gemini CLI. It made some mistakes and had one genuinely good idea.
Build a complete pipeline - fetch from an API, load into DuckDB, transform with SQL, export results. A capstone putting it all together.
Your AI writes Bash. If VS Code opens PowerShell, you translate every command by hand. Four clicks make Bash the default, and one command proves it worked.
Read EXPLAIN output to understand why queries are slow. Learn when to add indexes and when to stop worrying about performance.
INSERT, UPDATE, and DELETE with guardrails. Always use WHERE, test with SELECT first, and use transactions to undo mistakes.
Giving an LLM the keys to your wiki is not a dramatic handoff. It looks like maintenance done quietly, completely, every time.
One keystroke opens the VS Code terminal on every platform. That shortcut is the gap between what the AI said and knowing the code actually runs.