How to write a good prompt: a simple recipe
Better answers don’t come from clever wording. They come from telling the AI what you’d tell a helpful colleague. Here’s a four-part recipe that works in any assistant.
Search
Find it on Unjargoned
Stories and guides, the Learning Hub, prompts, AI tools, the AI certificate and live events, in one place.
124 results for “Prompts”
Learning Hub
23 results. The best 5 first.
Follow-up prompts: turn an OK answer into a great one
The first answer is only a draft. A short, specific reply is often all it needs. Here are the follow-ups worth knowing, and when to start a fresh chat instead.
Break big jobs into steps: prompt chaining explained
One giant prompt gives you something that looks finished but is hard to check. Break the job into steps with checkpoints and you get better work you can trust and reuse.
The AI words you keep hearing, explained
Tokens, hallucinations, agents, AGI: a friendly guide to the AI words that keep cropping up, what they mean and why they matter to you.
Your first ten minutes with an AI assistant
Never used one? Here’s how to pick a free AI assistant, check four settings and try three useful first chats, plus what to keep to yourself.
Prompts
96 results. The best 5 first.
Write a prompt for an AI image
Builds a detailed image prompt from a rough idea.
Reply to an email in your own words
Turns what you want to say into a clear, polite reply that sounds like you.
Say no without burning a bridge
Writes a warm, clear no to a request, with something else to offer if you have it.
Summarise a long email thread
Pulls out what’s been decided, what’s still open and what you need to do.
Chase a reply without sounding pushy
Writes a friendly nudge for an email that hasn’t had an answer.
The AI certificate
5 results
Asking well: prompts that work
A simple recipe for clear prompts, and how to improve an answer when the first one misses.
Prompting techniques that hold up
Roles, audiences, constraints and examples; breaking work into steps; and getting AI to critique and improve its own work.
Evaluating AI: test before you trust
Defining success, building a test set, comparing fairly, and keeping watch when models and prompts change.
Automation and agents
Chains, workflows and agents; tools and connectors; where people approve; and the risks, from prompt injection to runaway actions.
AI in Practice
Get reliable, high-quality results from AI, at work and at home.