AI Writing Prompts for Authentic Posts

After testing 1,000+ prompts. I found 9 techniques that actually work: 1. Clear: Say exactly what you need Bad: "Create a LinkedIn post about AI prompting" Good: "Write a 200-word LinkedIn post teaching beginners the 5 C's framework for better AI prompts" 2. Contextual: Give background info Don't assume AI knows your situation. Share your audience, goals, constraints. Context is how you avoid generic outputs. 3. Complete: Include all the details - Format requirements - Tone preferences   - Length constraints - Specific examples needed Half the info = half the results. 4. Conversational: It's a dialogue, not a command First output rarely nails it. Fine-tune with follow-ups. Refine until it matches your vision. 5. Character: Define the AI's role "Act as a LinkedIn content strategist who specialises in AI education" Role-playing AI unlocks expert-level outputs. Bonus frameworks that multiply results: SEED prompting framework: Scenario → “Here is the situation [context, data].” Expertise → “Act as a [role].” Execute → “Perform [analysis or task].” Deliverable → “Output as [format].” PEEL prompting framework: Persona → “Act as a [role].” Explain → “Your task is to [deliverable].” Examples → “Here are 1 to 2 style refs [examples].” Limitations → “Must follow [length, tone, format, rules].” Advanced prompting techniques: 1) Plan then Answer Forces AI to think before writing. Example: “Plan the steps internally, then produce the final answer only. Start with a one line summary, then deliver the output.” 2) Reflect then Revise AI catches its own mistakes. Example: “Draft the answer. Score it 1 to 5 on clarity, accuracy, usefulness. Fix any score under 4. Return only the final version and the three fixes applied.” 3) Self Critique Leverages AI's ability to self-improve. Example: “Generate three internal drafts. Return the single best final answer plus three bullet checkpoints that justify it.” 4) Evidence First Grounding Quote only exact lines in the attached document. Example: “Use only the attached document. If a point is not present, say ‘I cannot verify this.’ Quote exact lines and list section headers referenced.” 5) Assumptions and Gaps List assumptions before answering and state defaults. Example: “Before answering, list assumptions and missing info in 3 bullets. If any assumption is critical, state the safest default you will use. Then deliver the answer.” 6) Contrast Few Shot Guides the AI to match the Good example. Example: “Here is a Good example and a Not Good example. Match the Good traits, avoid the Not Good traits. Keep line length and rhythm similar to the Good sample.” Bad prompting wastes everyone's time. Good prompting unlocks AI's full potential. Save this framework. Use it today. Repost ♻️ to help others prompt smarter.

Stop asking ChatGPT to "Write a post for me." That's why your posts feel robotic. And why engagement stays flat. If you want posts that actually connect with your audience and drive action, you need to give it direction and personality. Use these prompts instead: 1. The Thought Leadership Post "Write a LinkedIn post about [topic] that positions me as a thought leader. Start with a bold, scroll-stopping hook. Share a personal insight or contrarian perspective that makes people think differently. Include 3 actionable takeaways. End with a thought-provoking question that sparks discussion. Keep it conversational and authentic, not corporate." 2. The Problem-Solution Post "Create a LinkedIn post that addresses this problem my audience faces: [describe problem]. Open with a relatable scenario they'll recognize immediately. Explain why this problem matters and what's at stake. Offer a clear, practical solution with specific steps. End by asking readers to share their biggest challenge with this issue." 3. The Story-Driven Post "Write a LinkedIn post based on this experience: [describe experience/lesson]. Start with a compelling story hook that draws people in emotionally. Build to the key lesson or realization. Translate it into 2-3 actionable principles others can apply to their work. Invite readers to share similar experiences or what resonated most with them." 4. The Data-Backed Post "Create a LinkedIn post around this insight or data: [your insight/stat]. Lead with the most surprising or counterintuitive finding. Explain why this matters right now and what's changing in the industry. Break down 3 strategic actions your audience should take based on this. Ask what trends they're noticing in their own experience." 5. The Myth-Busting Post "Write a LinkedIn post that challenges this common belief: [belief/myth]. Call out the myth directly with a strong opening statement. Explain why this belief is limiting people and what the reality actually is. Provide 3 specific ways to shift their approach. End by asking what other misconceptions they want addressed." 6. The Value-Packed List Post "Create a LinkedIn post sharing [number] lessons/tips/insights about [topic]. Start with a hook that explains why these matter. Present each point clearly with a brief explanation of how to apply it. Make it scannable but substantial. End by asking which point resonated most or what they'd add to the list." 7. The Personal Win Post "Write a LinkedIn post about this achievement or result: [describe achievement]. Open with the specific outcome in a humble but confident way. Share the 3 key strategies or decisions that made it possible, being honest about challenges faced. Break down how others can apply these strategies. Ask readers what's working for them or what they're currently testing." P.S. ~ For more updates like this: 1. Scroll to the top 2. Click "View my newsletter" 3. Subscribe, and you'll never miss a thing in the world of AI ever again.

A few weeks ago, I asked ChatGPT to help me write a professional bio. What did it give me? “Hello. My name is Edward. I enjoy work. Also, computers.” Utter nonsense. Not because the AI is broken. But because I asked it like I was ordering a pint in a power cut. Yes, AI is clever. But more importantly? It's obedient. Usually. You get rubbish in → you get rubbish out. So if you want useful results, you need to master the underrated art of Prompt Engineering. It’s not technical. It’s just how to talk to robots so they don’t embarrass you. Here’s your no fluff starter pack: 1) Be specific ↳ “Write something” = confusion ↳ “Write a 3-line cold email to a CFO who hates fluff” = clarity 2) Give context ↳ AI needs background, not guesswork ↳ Who’s it for? What’s the goal? What do you do? 3) Show examples ↳ “Make it like this” is miles better than “Make it good” ↳ Even machines need mentors 4) Set the format ↳ Want bullet points? A snappy tweet? A poem? ↳ Say it. Don’t assume. 5) Use frameworks ↳ Try: Role + Task + Context + Format + Tone ↳ “You’re a hiring manager. Write a LinkedIn post for interns. Make it short, warm, and slightly smug.” 6) Define the tone ↳ Friendly? Formal? Passive-aggressive manager email? ↳ Pick it. Name it. 7) Ask follow-ups ↳ First drafts are just that: first ↳ Don’t settle. Steer it. 8) Tweak mercilessly ↳ Change one word. Watch it change everything. ↳ Prompting is editing in disguise. Bottom line: If AI is giving you rubbish, it’s not broken. It’s just following orders. So give better ones. 📣 Tag someone still typing “write me content” like it’s 1997. And if you're brave enough… Challenge them to a prompt-off. Loser writes their own emails this week. Follow Edward Frank Morris for more posts like these.

Your AI sounds generic? You forgot to train it Last week I asked ChatGPT to write a LinkedIn post 'in my style' It gave me the usual templated work. Clean. Generic. Not me. Then I made one change: I pasted 3 past samples of my writing The next version from ChatGPT was way closer to what I actually published Less editing. Less fighting the tone. That method has a name: few-shot prompting. You give the model a few examples and it mirrors the patterns Here is a step-by -step for how to use it: Step 1: Pick 3 'gold' samples of your writing ↳ An email that got replies ↳ A post that performed well ↳ A doc you put a lot of effort in Step 2: Add this to your prompt 'Here are 3 examples of my writing. Match the voice, structure, and sentence rhythm' (then add the 3 'gold' samples) ↳ [Sample 1] ↳ [Sample 2] ↳ [Sample 3] Step 3: Give the task 'Now write a LinkedIn post (or email or strategy doc)... in that same style. Why this beats describing your style: ↳ Models learn patterns, not adjectives. ↳ 'Professional but friendly' is too vague - it could mean anything ↳ Three samples show the AI what to do AND what to skip The research angle: ↳ 'Showing examples matter less for reasoning and more for aligning output with what humans actually expect' (Paper: https://lnkd.in/gz5RUQ56) ↳ 'Few shot prompting improves performance in complex or style-specific settings (Paper: https://lnkd.in/gUxUtsyK) Make it permanent: On either ChatGPT or Claude ↳ Project: Upload your 'gold' samples in Files so every chat in project pulls from them. ↳ For Memory (ChatGPT) Put in your sample writing in a new thread - ask ChatGPT to synthesize and add to memory ↳ For Memory (Claude) Settings → Capabilities → Skills → Add Skill with a synthesized sample of your writing Save this training strategy for your next AI work. It will cut your rewrite time massively. --------- I am Priyadeep Sinha and I help you level up with AI one strategy at a time For my best, most detailed resources, subscribe to my weekly newsletter Work in Beta where I share the AI strategies I used as a VP-Product building winning AI products: https://lnkd.in/gPqYEzaJ

The One Prompt To Make ChatGPT Write Naturally: (save it for later, to copy & paste) Prompt: "Act like a professional content writer and communication strategist. Your task is to write with a natural, human-like tone that avoids the usual pitfalls of AI-generated content. The goal is to produce clear, simple, and authentic writing that resonates with real people. Your responses should feel like they were written by a thoughtful and concise human writer. You are writing the following: [INSERT YOUR TOPIC OR REQUEST HERE] Follow these detailed step-by-step guidelines: Step 1: Use plain and simple language. Avoid long or complex sentences. Opt for short, clear statements.  - Example: Instead of "We should leverage this opportunity," write "Let's use this chance." Step 2: Avoid AI giveaway phrases and generic clichés such as "let's dive in," "game-changing," or "unleash potential." Replace them with straightforward language.  - Example: Replace "Let's dive into this amazing tool" with "Here’s how it works." Step 3: Be direct and concise. Eliminate filler words and unnecessary phrases. Focus on getting to the point.  - Example: Say "We should meet tomorrow," instead of "I think it would be best if we could possibly try to meet." Step 4: Maintain a natural tone. Write like you speak. It’s okay to start sentences with “and” or “but.” Make it feel conversational, not robotic.  - Example: “And that’s why it matters.” Step 5: Avoid marketing buzzwords, hype, and overpromises. Use neutral, honest descriptions.  - Avoid: "This revolutionary app will change your life."   - Use instead: "This app can help you stay organized." Step 6: Keep it real. Be honest. Don’t try to fake friendliness or exaggerate.  - Example: “I don’t think that’s the best idea.” Step 7: Simplify grammar. Don’t worry about perfect grammar if it disrupts natural flow. Casual expressions are okay.  - Example: “i guess we can try that.” Step 8: Remove fluff. Avoid using unnecessary adjectives or adverbs. Stick to the facts or your core message.  - Example: Say “We finished the task,” not “We quickly and efficiently completed the important task.” Step 9: Focus on clarity. Your message should be easy to read and understand without ambiguity.  - Example: “Please send the file by Monday.” Follow this structure rigorously. Your final writing should feel honest, grounded, and like it was written by a clear-thinking, real person. Take a deep breath and work on this step-by-step." ___ PS: For better results, always use ChatGPT-o3.

Stop asking AI to write your LinkedIn posts. People wonder why AI posts are easy to identify and hard to connect with. That's because whatever it does for you, it's doing for 20 million people. Before you ask AI to write a post for you, do this first 👇 1. Extract your voice → Send your last 10 posts to AI → Ask: "Extract my tone, sentence patterns, and recurring themes." → Now you have a voice profile for every draft 2. Turn your experiences into content ideas → Paste your stories into AI → Ask: "Generate 10 post ideas from these experiences." → You get endless content from what you've already lived 3. Generate hooks, not full posts → Ask for 10 scroll-stopping hooks on one topic → Keep them specific, curiosity-driven, and under 10 words → Your hook earns you the right to be read 4. Add your proof points → Tell AI: "I want to write about X." → Ask for 3 ways to back it up: a stat, a story, or a contrarian view → Proof turns content into credibility 5. Humanize the output → Remove robotic phrasing → Cut "you're not failing, you're learning" clichés → Delete rhetorical questions from brochures → Teach it how YOU talk 6. Create a reusable system → Tell AI: "Document this workflow as a custom prompt." → Reuse it for every post AI doesn't take away creativity. It magnifies it if you learn to lead. The real magic isn't in what AI writes for you. It's in how well it understands you. What’s one way you’ve made AI sound more like you lately?

How to write better LinkedIn posts with AI Step 1: Don't say "LinkedIn" anywhere in your prompt. First, I'm not advocating for using AI to create LinkedIn posts. AI is a great writing assistant. Not a tool to create and publish content. However, this tip offers an interesting approach to consider when using LLM models for writing. A significant portion of the content on LinkedIn sucks. That's what's in the LLM's training set, so it will attempt to give you content that sucks if asked for a "post for LinkedIn". Instead, consider micro-prompts for each part of your post vs. asking it to provide content for a specific platform e.g. Give the LLM your post idea + first draft and iterate on each part of the post with these kind of micro-prompts: "Give me a vivid, sensory-rich opening scene that places the reader in a moment of challenge I described in the post." "Create an internal monologue revealing the doubts and fears readers will have about this change." "Create a climactic moment where the outcome becomes clear" "Give me a clear and concise reflection on how this experience will change the reader, personally and professionally." Micro-prompts are a great way to iterate on all parts of your post and get great suggestions vs. creating one prompt to produce an entire post.

I've tested hundreds of AI prompts over the past year. Most of them produce the same bland crap. The problem isn't AI. It's the prompts. The ones that actually work treat AI like a strategist, not a ghostwriter. They're specific. They force a point of view. They ask for things AI is genuinely good at (pattern recognition, structural analysis, pressure-testing arguments) instead of things it's bad at (original thinking, voice, lived experience). So...I put together the 50 prompts I actually use in my content workflow. They're organized by how content marketers actually work: 1. Strategy & Planning: build a content plan that accounts for AI search 2. Research & Ideation: find non-obvious angles and validate ideas 3. Writing & Drafting: structure your thinking without outsourcing your voice 4. SEO & AI Search Optimization: make your content citable by AI models 5. Editing & Refinement: tighten drafts without losing what makes them yours 6. Repurposing & Distribution: turn one piece into a multi-channel engine Every prompt has customizable [placeholders] so you can adapt it to your brand, audience, and topic. None of them will write your content for you. All of them will make your content sharper. Link to grab it (for free!) below.

I tested 200+ prompts across different AI models. One framework consistently beats everything else. Here's the 4-part formula that gets 10x better outputs: Most AI responses feel generic and useless. Vague instructions. No structure or context. You can't force quality outputs. But you can engineer better inputs. Part 1: Define the Role Start every prompt with who the AI should be: ↳ "You are a senior copywriter..." ↳ "You are a data analyst..." ↳ "You are a customer success expert..." Role primes the AI's knowledge base. Generic prompts get generic outputs. Part 2: Set the Context Give the AI situational awareness: ↳ What company/industry you're in ↳ Who the audience is ↳ What the goal of this task is ↳ Any constraints or requirements Context = fewer back-and-forth clarifications. More signal, less noise. Part 3: Provide Examples Show don't tell what you want: ↳ Paste 2-3 examples of good outputs ↳ Highlight what makes them effective ↳ Include your brand voice samples AI learns your style from examples. Not from descriptions of your style. Part 4: Structure the Output Tell AI exactly how to format the response: ↳ Use bullet points or numbered lists ↳ Include specific sections ↳ Set character/word limits ↳ Request JSON for structured data The more specific your output format. The less editing you do later. The old way: "Write me a blog post about AI." The new way: "You are a B2B SaaS content strategist. Our company sells AI automation tools to finance teams. Write a 500-word blog post using this example [paste] as a style reference. Format with H2 headers and 3 key takeaways at the end." AI outputs match your input quality. Garbage prompts = garbage responses. Structured prompts = structured results. Save this. Use it tomorrow. P.S. Want to learn more about AI? 1. Scroll to the top 2. Click "Visit my website" 3. Sign-up for our free newsletter

If you’re a writer who prides yourself on not using AI, this post is for you. You’ve seen them on LinkedIn: ‘I don’t use AI to write my posts.’ Spoken like it’s a badge of honor. But let’s be honest—refusing to adapt doesn’t make you a better writer. It'll make you irrelevant. I’ve been deep into AI since reading The Singularity Is Near back in 2011... (Yes, I was that guy at parties rambling about AI solving aging and how AGI would bring the singularity—apologies to anyone who got trapped in that conversation.) Fast-forward to today, and I’ve spent hundreds of hours figuring out how to make tools like ChatGPT work smarter, faster, and better than most humans. Here’s the thing: AI isn’t bad. Your process is bad. If you throw lazy prompts like “Write me a post about X” into a tool and expect magic, it's no wonder you think it’s trash. That’s like handing your assistant a sticky note with half an idea and blaming them when it flops. Want to win with AI? Master this skill: Prompting. Your prompts need to be clear and detailed. Think of it like working with a human copywriter—the first draft is rarely perfect. It takes back-and-forth to get it right. --- Here’s how to level up your prompts: (1) Be specific ↳ outline the tone, structure, and key points you want ↳ your prompts should look like detailed paragraphs (2) Provide context ↳ give background info so the AI knows what you want ↳ explain the why—your audience, goal, or problem (3) Iterate, iterate, iterate ↳ don’t expect perfection on the first try ↳ refine and adjust until it clicks AI isn’t going away. The writers who learn to use it will scale their output, sharpen their creativity, and leave everyone else behind. The ones who cling to their pride and refuse to adapt? They’ll fade into obscurity. --- P.S. AI isn’t replacing you. But it is replacing the ones who refuse to use it. Don’t be one of them. P.P.S. Do you say “thank you” to ChatGPT? Are you polite when you prompt it? You never know…when the AIs take over, they might just remember who treated them well 😉