Last post we looked at how giving AI more context leads to better results.
This week, there’s one small addition to your prompts that can make a
surprising difference \u2014 and it takes three extra words.<\/p>\n\n\n\n
Ask it to think step by step.<\/strong><\/p>\n\n\n\n When you ask ChatGPT or Copilot a straightforward question, it gives you a Adding “think step by step” or “explain your reasoning” is like asking a It sounds almost too simple. It works anyway.<\/p>\n\n\n\n This isn’t something you need every time. It earns its place when:<\/p>\n\n\n\n 3 Office Examples<\/strong><\/p>\n\n\n\n Scenario 1<\/strong>: Deciding between two options<\/p>\n\n\n\n Instead of: “Should I use Excel or a project management tool for tracking our Try: “I need to track tasks for a team of 6. We currently use Excel but it’s You’ll get a reasoned comparison you can actually present to your manager, not Scenario 2<\/strong>: Planning something with multiple steps<\/p>\n\n\n\n Instead of: “How do I organise a team away day?”<\/p>\n\n\n\n Try: “Help me plan a one-day team away day for 12 people. Walk me through each The “walk me through each step” instruction does the same job here. You get a Scenario 3<\/strong>: Understanding a decision before you commit to it<\/p>\n\n\n\n Instead of: “Is it worth upgrading to Microsoft 365 Business Premium?”<\/p>\n\n\n\n Try: “We’re a small office of 10 people currently on Microsoft 365 Business Seeing the reasoning laid out makes it much easier to take that to whoever You don’t need to use the exact phrase “step by step” \u2014 variations work just Next post:<\/strong> <\/p>\n","protected":false},"excerpt":{"rendered":" Last post we looked at how giving AI more context leads to better results.This week, there’s one small addition to your prompts that can make asurprising difference \u2014 and it takes three extra words. Ask it to think step by step. When you ask ChatGPT or Copilot a straightforward question, it gives you astraightforward answer. […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[],"class_list":["post-70","post","type-post","status-publish","format-standard","hentry","category-generative-ai"],"_links":{"self":[{"href":"https:\/\/karloneill.dev\/index.php?rest_route=\/wp\/v2\/posts\/70","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/karloneill.dev\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/karloneill.dev\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/karloneill.dev\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/karloneill.dev\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=70"}],"version-history":[{"count":1,"href":"https:\/\/karloneill.dev\/index.php?rest_route=\/wp\/v2\/posts\/70\/revisions"}],"predecessor-version":[{"id":71,"href":"https:\/\/karloneill.dev\/index.php?rest_route=\/wp\/v2\/posts\/70\/revisions\/71"}],"wp:attachment":[{"href":"https:\/\/karloneill.dev\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=70"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/karloneill.dev\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=70"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/karloneill.dev\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=70"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
straightforward answer. That’s fine for simple tasks. But for anything
involving reasoning \u2014 working through a problem, making a recommendation,
writing something with a logical structure \u2014 the AI can rush to a conclusion
just like a person might when put on the spot.<\/p>\n\n\n\nWhy Does This Work?<\/h4>\n\n\n\n
colleague to slow down and walk you through their thinking rather than just
handing you an answer. You get to see how they got there, spot anything that
doesn’t add up, and end up with a result you actually understand and trust.<\/p>\n\n\n\nWhen to Use It<\/h4>\n\n\n\n
\n
between two options? Ask it to weigh them up step by step rather than just
pick one.<\/li>\n\n\n\n
or structured thinking benefits from this approach.<\/li>\n\n\n\n
easier to spot than when it just hands you a conclusion.<\/li>\n\n\n\n
decision or communicate a process, a step-by-step breakdown gives you the
structure ready-made.<\/li>\n<\/ul>\n\n\n\n
team’s tasks?”<\/p>\n\n\n\n
getting messy. Compare Excel and a project management tool like Trello or
Asana for our situation. Think through the pros and cons of each step by step
before giving me a recommendation.”<\/p>\n\n\n\n
just a one-line answer.<\/p>\n\n\n\n
step I need to take, from initial planning through to the day itself. Include
things I might forget.”<\/p>\n\n\n\n
checklist rather than a paragraph.<\/p>\n\n\n\n
Basic. Explain step by step what we’d gain from upgrading to Business Premium,
what it would cost, and whether it’s likely to be worth it for a small
non-technical team.”<\/p>\n\n\n\n
holds the budget.<\/p>\n\n\n\nA Small Tweak, A Big Difference<\/h4>\n\n\n\n
as well:<\/p>\n\n\n\n\n
just deliver a verdict. That 20 extra seconds of typing gives you something
you can follow, question, and build on \u2014 rather than just accept. AI works best when it thinks out loud. All you have to do is ask.<\/li>\n<\/ul>\n\n\n\n
how to use AI to get more out of the tools you already use every
day \u2014 starting with Excel.<\/em><\/p>\n\n\n\n