Category: AI
Practical AI for analytics people — skills you can use at work.
Prompt injection for data people
Prompt injection is not only a chatbot prank. For data teams it rides in tickets, docs, CSV cells, and tool outputs. Here is how attacks show up in…
When a Custom GPT is the wrong solution
Part 4 closes Custom GPTs and the ChatGPT track on AMS. Use a chooser for when a GPT is wrong (one-offs, live systems, code, secrets, KPIs), recap all…
Prompt patterns for data work
Good data prompts are contracts, not vibes. Part 3 of Practical AI for analytics people covers role, spec, output shape, and refuse rules, plus SQL-then-explain patterns that block…
Quality control and avoiding workslop
Part 6 of the Claude Cowork tutorial. Catch workslop before it ships: skim structure, check numbers and names, verify scope, then human sign-off. Auto mode screens risky actions;…
Hosted open models vs download to your machine
Hosted open models and a download to your machine are different places for the same weights. This part splits Groq, Together, Fireworks, and chat UIs from Ollama, LM…
