Working-with-AI Fundamentals
Use this page to revise the fundamentals of using AI tools responsibly in development work.
Using AI tools responsibly
- AI assistants differ from traditional automation: they generate a plausible answer rather than following a fixed set of rules, which is powerful but means their output must always be checked.
- Good prompting gives context, a clear role/task, constraints, and (where useful) examples — and treats the first response as a draft to refine, not a final answer.
- Known limitations to watch for: hallucinations (confidently wrong output), outdated knowledge, and sensitivity to how a prompt is worded.
- Responsible use means never pasting secrets or confidential data into a prompt, staying aware of your organisation's data-handling policies, and keeping a human in the loop for anything security- or compliance-sensitive.
Starting Points
- LeMaire, C., & Abshire, B. (2025). AI for Everyday IT: Accelerate Workplace Productivity. Manning.
- Working with AI
Key Points
- You can explain how AI assistants differ from traditional automation.
- You can list the elements of a well-structured prompt (context, task, constraints, examples).
- You can name common AI limitations (hallucinations, outdated knowledge, prompt sensitivity) and what responsible use requires.