Writing Clear Instructions for Projects

Found this 1980 ad about writing clearly. 65 years later, it's still the best writing advice I've ever seen: 1) Know exactly what you want to say before you start Most people start writing and figure it out as they go. That's why most writing sucks. Thompson says outline first, write second. Revolutionary concept, apparently. 2) Start where your readers are, not where you are Don't assume people know what you know. Meet them at their level of understanding, then bring them along. Most "experts" write for other experts and wonder why nobody gets it. 3) Use familiar word combinations Thompson's example: A scientist wrote "The biota exhibited a one hundred percent mortality response." Translation: "All the fish died." Stop trying to sound smart. Start trying to be clear. 4) Arrange your points logically Put the most important stuff first. Then the next most important. Then the least important. Seems obvious, but most people do it backwards. 5) Use "first-degree" words Thompson says some words bring immediate images to mind. Others need to be "translated" through first-degree words before you see them. "Precipitation" => "Rain" "Utilize" => "Use" "Facilitate" => "Help" 6) Cut the jargon Thompson warns against words and phrases "known only to people with specific knowledge or interests." If your mom wouldn't understand it, rewrite it. 7) Think like your reader, not like yourself Thompson asks: "Do they detract from clarity?" Most writers ask: "Do I sound professional?" Wrong question. TAKEAWAY: This ad is from 1960. The internet didn't exist. Social media wasn't even a concept. But the principles of clear communication haven't changed. Most people still can't write clearly because they're trying to impress instead of express.

STOP asking ChatGPT to "make it better". Here's how to better prompt it instead: ☑ Clearly Identify the Issue Rather than a vague “make it better,” specify the exact element that needs change. For example: "Rewrite the second paragraph so it includes three concrete examples of our product’s benefits. The tone must be formal and persuasive. Remove any informal language or redundant phrases." ☑ Divide the Task into Discrete Steps Break the overall revision into a sequence of manageable tasks. For example: "Go through my instructions, step by step. – Step 1: Summarize it in one sentence. – Step 2: Identify two specific weaknesses. – Step 3: Rewrite the text to address these weaknesses, incorporating specific data or examples." ☑ Specify the Format and Level of Detail Define exactly how the final output should look. For example: "Provide the final revised text as a numbered list where each item contains 2–3 sentences. Each item must include at least one statistical fact or concrete example, and the overall response should not exceed 250 words." ☑ Request a Chain-of-Thought Explanation Ask the model to detail its reasoning process before giving the final output. For example: "Before providing the final revised text, explain your reasoning step-by-step. Identify which parts need improvement and how your changes will enhance clarity and professionalism. Then, present the final revised version." ☑ Conditional Instructions to Enforce Compliance Add if/then conditions to ensure all requirements are met. For example: "If the revised text does not include at least two concrete examples, then add a sentence with a real-world statistic. Otherwise, finalize the response as is." ☑ Consolidate All Instructions into One Prompt Integrate all the detailed instructions into a single, comprehensive prompt. For example: "First, identify the section of the text that needs improvement and explain why it is lacking. Next, summarize the current text in one sentence and list two specific weaknesses. Then, rewrite the text to address these weaknesses, ensuring the revised version includes three concrete examples, uses a formal and persuasive tone, and is structured as a numbered list with each item containing 2–3 sentences. Each list item must include at least one statistical fact or example, and the overall response must be no longer than 250 words. Before providing the final text, explain your reasoning step-by-step. If the revised text does not include at least two concrete examples, add an additional sentence with a real-world statistic." ___ Why This Works People never give enough context. And once ChatGPT answers, they never correct it enough. Think about it like an intern. Deep prompting is all about precision: give clear instructions, context & the right corrections. PS: Don't forget to use the new o3-mini model. It's crushing any other one. Yes – even DeepSeek.

𝐒𝐭𝐞𝐚𝐥 𝐭𝐡𝐢𝐬: 𝐦𝐲 𝐞𝐱𝐚𝐜𝐭 𝐞𝐦𝐚𝐢𝐥 𝐭𝐞𝐦𝐩𝐥𝐚𝐭𝐞 𝐟𝐨𝐫 𝐜𝐥𝐞𝐚𝐫 𝐜𝐨𝐦𝐦𝐮𝐧𝐢𝐜𝐚𝐭𝐢𝐨𝐧. I didn’t realize how many problems were coming from “okay” emails until I started working on fast-moving projects. Delays, confusion, back-and-forth, most of it wasn’t complexity. It was unclear communication. So I started using a simple structure that works almost every time. Here’s the template: 📍Start with context (1–2 lines): Why are you writing this email? “Following up on our discussion on X…” “Sharing an update on Y…” This aligns the reader instantly. 📍State the purpose clearly What do you want from this email? “Objective: Finalize vendor selection for Phase 1.” No guessing. No ambiguity. 📍Add key points (3–5 bullets max) Only what matters. • Current status • Key issue/blocker • Relevant data/decision point If it’s longer, it’s not clear enough. 📍Call out the action required This is where most emails fail. “Action required: Please confirm Option A or B by EOD Friday.” Be specific on who, what, and by when. 📍Close with clarity, not politeness fluff Avoid: “Let me know your thoughts.” Instead: “Once confirmed, we will proceed with implementation.” This one change reduced back-and-forth significantly for me. Because most communication problems aren’t about intelligence. They’re about structure. People don’t need more information. They need clarity on what matters and what to do next. Before sending your next email, ask yourself: Can someone read this in 30 seconds and know exactly what to do? If not, rewrite it. #Communication #Productivity #WorkplaceSkills #Consulting #ProfessionalGrowth #CareerTips #EmailWriting

There are dozens of AI prompt frameworks that lawyers are being told to use. But giving good instructions is already a core legal skill. We don't need another acronym. We just need to draw on those same principles: 1️⃣ Role Tell the AI who it is and what expertise to draw on. Being specific is good, but like all things legal, there’s a balance with being too specific as the data might be too limited. In my example, I’ve referenced professional athletes, but within the broader category of high net worth individuals. 2️⃣ Purpose Identify the client and state what they're trying to achieve. Try to provide as much context as possible. It can also help to refer to any notes you may already have. 3️⃣ Task State the specific deliverable that we need to prepare. If the draft email is going to a client or a supervisor, state that. It’s helpful also to include any examples, checklists, risk matrices etc. that should be followed. Same as if you were giving a junior a precedent to use instead of making them start from scratch. 4️⃣ Key facts Set out the info that isn’t publicly available or that the AI should focus on. In this case, we are asking them to consider 2 specific options instead of every contract extension variant. 5️⃣ Constraints Here we build in guardrails. For example, the format, word count, tone, house styles, things to avoid etc. The more key constraints we can include, the more relevant the final output will be. 6️⃣ Iterations This bit is something I like to do whenever I give instructions to people, and I’ve found it helpful when prompting AI. It’s best to think of prompting as an iterative process instead of something you need to get perfect in one go. NB: This guide is tool-agnostic. Follow your organisation's rules for AI use. What’s your prompting approach? Do you just give instructions like you would to a human, or do you have a system that works better? ---------- I'm building an e-library with the 110+ how-to guides I've written over 6 years. If you want early access when it launches, sign up to the free newsletter on my website / profile.

Neuroinclusive email etiquette ensures our digital communications are accessible to everyone, including neurodivergent colleagues 😊. Confusion can lead to waste effort.. e.g. doing the wrong work without the intent to do so.. By crafting clear, concise emails, we not only share information effectively but also create a more inclusive work environment. Start with a descriptive subject line and use simple, direct language. Break your content into short paragraphs or bullet points to help guide the reader’s eye 👀. A brief summary at the beginning can also provide clarity and reduce cognitive load. Also try these and more.... • Use clear, jargon‐free language. • Structure your message with bullet points or numbered lists. • Keep sentences short and to the point. • Allow for extra time when expecting responses, recognising diverse processing speeds 🤝. Adopting these practices makes our communication friendlier and more effective for everyone. Let’s lead by example and foster a workplace where digital correspondence is both respectful and accessible 😊.

Let’s just start and see where it goes. It sounds agile. It feels lean. But for SMBs, it’s often the reason projects stall When you're working with limited time and team capacity, direction matters more than speed. That’s why I borrow a principle from Amazon’s playbook: Working backwards. At Amazon, before any team writes a line of code, they write a press release. Not for marketing. For focus It forces one hard question upfront: If this succeeds, what will the customer actually experience? Now imagine what that unlocks for your business: → No more “building for the sake of building” → Clear decisions anchored to outcomes → Alignment without 50 meetings How do we adapt it for smaller teams: ✔️We skip the fluff, no decks, no endless planning ✔️We write a simple customer story that defines success clearly ✔️We avoid corporate jargon, just real language and real outcomes ✔️We reverse-engineer from the goal to decide what’s actually needed ✔️We align fast, so small teams don’t waste time chasing the wrong thing Example:Project: Improve client handoff process →Instead of “Improve client handoff,” We write: “Clients say the new handoff is so smooth, they felt taken care of from day one. Suddenly, everyone knows what we’re aiming for. And what not to waste time on. Because when you're small, clarity isn’t a luxury. It's your strategy. 👉 Want to test this with your next project? DM me, I’ll show you how we do it 

I haven't seen anyone talk about this. But the No.1 reason I have seen legal issues happen... It is because of a simple fact. Miscommunication. That's it. That's all there it is. -> Miscommunication leads to misunderstandings. -> Misunderstandings lead to disputes. -> Disputes lead to legal issues. I read a lot of case laws on the commercial/contract side. And they could all have been easily avoided had the parties communicated properly. Now you might be wondering, why does this happen? Couple of reasons: • Assumptions are made. One party assumes the other knows what they mean. But the other party might have a different interpretation. • Expectations aren't clear. One party expects certain features or services. But if it's not documented, it's just an expectation, not an agreement. • Deliverables aren't defined. What exactly is being delivered? Are the deliverables defined in detail? • Deadlines aren't realistic. Are the timelines realistic? What happens if deadlines aren't met? Now lucky for you, if you want to avoid this. There are a couple of steps I recommend. I normally share this with my clients. 1) Clearly define the scope of the project. Outline what is included and what is not. Example: "The website will include a homepage, about page, contact page, and blog section. E-commerce functionality is not included." 2) Specify each deliverable. Provide details for each one. Example: "The homepage will feature a hero image, a brief introduction, and links to the about and contact pages." 3) Set realistic deadlines. Include buffer time for revisions. Example: "The homepage design will be delivered by August 1st. The about and contact pages will follow by August 10th. The blog section will be completed by August 15th." 4) Be clear on how and when you'll communicate. Regular updates and check-ins. Example: "Weekly status calls every Monday at 10 AM. Daily progress updates via Slack." 5) Be clear about payment schedules. Include milestones and due dates. Example: "50% upfront, 25% upon delivery of the homepage, 25% upon final approval." 6) Define how changes will be handled. Include a process for approving and documenting changes. Example: "Any changes to the project scope must be submitted in writing and approved by both parties. Additional charges may apply." Once you start doing this, you remove a lot of "assumptions" from the contract. Point is - don't leave anything to chance. Because miscommunication can kill a project. I have seen it happen. Tldr: -> Assumptions can cost you. -> Clarity can save you. -> Document everything. That's all -- ✍️ Have you ever lost a project because of miscommunication? 📌 Web Agencies, if you need a good contract that properly communicates your offerings, then DM me the word "CONTRACT" and let's talk #Startups #Founders #Contract #Law #Business #website

🔬 #ArtificialIntelligence 𝗧𝗿𝗮𝗶𝗻𝗶𝗻𝗴: 𝗧𝗲𝗮𝗰𝗵 𝗬𝗼𝘂𝗿 𝗧𝗲𝗮𝗺 𝗜𝗻𝗯𝗼𝘅 𝗠𝗮𝗻𝗮𝗴𝗲𝗺𝗲𝗻𝘁! 𝗦𝘁𝗼𝗽 𝗱𝗿𝗼𝘄𝗻𝗶𝗻𝗴 𝗶𝗻 𝗲𝗺𝗮𝗶𝗹. 𝗛𝗲𝗿𝗲'𝘀 𝗵𝗼𝘄 𝘁𝗼 𝘁𝗿𝗮𝗶𝗻 𝘆𝗼𝘂𝗿 𝘁𝗲𝗮𝗺 𝘁𝗼 𝗯𝘂𝗶𝗹𝗱 𝗟𝗟𝗠 𝗽𝗿𝗼𝗺𝗽𝘁𝘀 𝘁𝗵𝗮𝘁 𝗮𝗰𝘁𝘂𝗮𝗹𝗹𝘆 𝘁𝗮𝗺𝗲 𝘁𝗵𝗲 𝗶𝗻𝗯𝗼𝘅. You know the feeling. 100+ emails a day, half of them need sorting, three need immediate action, and the rest? Noise. Your employees waste hours on inbox triage that an AI could handle in seconds—if they knew how to ask it the right way. That's where Context Engineering for Email comes in. 𝗕𝗮𝗱 𝗣𝗿𝗼𝗺𝗽𝘁 𝗘𝘅𝗮𝗺𝗽𝗹𝗲 Most people don't realize that a bad prompt sounds like this: ==> "Organize my emails" 𝗕𝗲𝘁𝘁𝗲𝗿 𝗣𝗿𝗼𝗺𝗽𝘁 𝗘𝘅𝗮𝗺𝗽𝗹𝗲 But a good prompt sounds like this: "Review my inbox and categorize each email as: (1) Urgent—needs response today (2) Action—do this week, or (3) FYI—read later. For each, list the sender and main ask in one sentence. Output as a table." 𝗔𝗻𝗮𝗹𝘆𝘀𝗶𝘀 See the difference? The second one tells the AI exactly what you want, how to structure it, and how to deliver it. Start with the 3-step framework: 1.     What: Name the exact task ("Summarize this thread so I only read the key points") 2.     How: Tell the AI how to structure the output ("Use bullet points, max 3 bullets") 3.     Why: Give context so it understands the intent ("I need this to spot action items quickly") Then give them a real-world email prompt they can use today: "I receive 50+ emails a day. Create a daily digest that: lists emails needing my direct response (with sender name and action), groups FYI updates by topic (no more than 3 lines per group), and flags anything urgent in red. Sort by priority. Use a simple table format." 𝗧𝗵𝗲 𝗠𝗮𝗴𝗶𝗰 Your team writes this prompt once, reuses it daily, and suddenly has three hours back each week. They'll see immediately how specificity beats vagueness, how structure beats rambling, and how context beats guessing. 𝗧𝗵𝗲 𝗥𝗲𝗮𝗹 𝗪𝗶𝗻 Once they nail email, they use these same skills for proposals, reports, brainstorms, and customer responses. Prompt engineering becomes a career skill, not a party trick. Start this week. Pick one person on your team, walk them through the framework with their actual inbox, and let them build the prompt together with you. Watch them light up when the AI nails it on the first try because they asked the right way. Please follow me for more tips! T. Scott Clendaniel

NASA kept these photos from Apollo astronauts’ cuff‑checklists under “Restricted” access for years. No, it’s not proof that the moon landing was faked. What they hid from the public eye was far more sly. On Apollo missions, each astronaut wore a multi‑page cuff checklist. It’s the ultimate cheat‑sheet for their moonwalks. Hidden between the pages? A surprise the ground crew preferred taxpayers never saw. That stunt proves two things: Memory buckles under pressure. A well‑curated checklist can keep you on task and make you laugh. When the pressure is on, even highly trained astronauts rely on simple checklists. That same humble implement saved pilots and patients back on Earth. In 1935,  Boeing B‑17 crashed at the first test flight. A simple mistake from the pilot who missed to disengage a lock led to the  first 19‑item pre‑flight checklist. That practice transformed the aviation industry for the better and saved many lives throughout the decades. Fast forward to 2008, Harvard Prof and Surgeon Atul Gawande did a study in 8 countries to implement a 1 page checklist before every surgery. Surgical deaths got cut by 47 %. The WHO officials adopted this checklist as the gold standard to save lives globally. 5 tips for making your checklists bullet-proof 1. Make every item deterministic.  Obvious to say yes or no. When two different people read it, they must interpret it the same way.  Don’t say “Check analytics”.  Say “Analytics tested in GA Extension. Confirm equivalent behavior for control and test paths” 2. Aim for the Goldilocks scope.  Too generic “How to start a business” = junk.  Too narrow “How to add this specific button in this bespoke web page” = can’t reuse.  3. Engage the doers.  Early engagement creates ownership and gets natural compliance.  4. Update after every use Make it a team habit to update the checklist after every execution. 5. Use the right type of checklist. Read-Do for things that must be done and confirmed at each step (eg. Payroll Checklist) Do-Cofirm for multiple party checklists that need checkpoints (eg. Product Launch Checklist) At Boomerang, we use: *Product‑launch checklist – born during Boomerang for Yahoo (RIP) and still evolving 13 years later. *Pre‑ & Post‑flight experiment – our Year of Experiments yielded 7 pre and 5 post-flight items that rescued us *New‑hire onboarding – Google’s 5‑item checklist study shows 25% boost in productivity *Off‑site playbook – 28 retreats in, we know every power‑strip, Sharpie and lunch menu counts. Comment “Checklists” if you want the Boomerang checklists mentioned. Are you still waiting for what the secret NASA was hiding in the cuff checklists? You will have to listen to the episode 6 of Less Busy Lab linked in the comments. P.S. The first commenter who guesses the hidden Apollo photo gets a virtual coffee.  P.P.S. Hint: The time has changed and you can’t do that in this day and age.  P.P.P.S. Sharing this NASA story doesn’t mean I approve of what they did. 

This writing advice is 45 years old. And it still beats AI by a mile... Since this article was published, the world has become a very different place. We can now generate anything we can imagine in mere seconds. But faster rarely means better. When it comes to writing, AI defaults to jargon-filled, abstract, cookie-cutter language.  (The exact kind of writing this article advises against.) So, whether you're writing from scratch or using AI to speed up the process, these principles are still the gold standard for producing clear, effective content. Here's what Edward T. Thompson (former Editor-in-Chief of Reader's Digest) identified in 1980: 1. Outline what you want to say Know where you're going before you start writing.  Use index cards, bullet points, whatever works. 2. Start where your readers are Consider how much they already know about the subject.  Don't write over their heads or beneath their intelligence. 3. Avoid jargon Don't use phrases that only people with specific knowledge will understand.  If you can say it simply, say it simply. 4. Use familiar combinations of words Don't invent awkward phrases when clear ones already exist.  But remember: Bad grammar can be just as unclear. 5. Use "first-degree" words Choose words that immediately bring an image to mind.  Concrete will always beat abstract. The fundamentals of clear writing haven't changed a bit. These principles were true in 1980, and they're still true now. In fact, they matter even more today. AI can generate thousands of words in seconds.  But it defaults to abstract, corporate language. If you don't know what clear writing looks like, you won't catch it. You'll edit for grammar and call it done.  But the writing will still feel empty. So in a world where AI slop is ruining the internet... Let clear, articulate writing be your competitive advantage. What's your best piece of timeless writing advice? --- I'm fascinated by writing and creativity in the era of AI.  If you are too, give me a follow Katharine Gordon! And repost to share this article with your network!