10 Inventive Methods to Write with AI (With out Dropping Your Soul)

So, after years of listening to the identical message, folks began associating AI-generated content material with low-effort, mass-produced slop. AI-assisted content material earned a nasty status earlier than it had an opportunity to mature.

This text is my try to reset the dialog.

I’ll share how we use AI at Ahrefs to create content material, together with some content material experiments we’ve been operating. To not exchange human considering, however to make attainable issues that was too tough, too costly, or just unattainable.

My aim isn’t to persuade you to automate extra. It’s that will help you see AI as a inventive device quite than a content material manufacturing unit.

And yet one more factor: I believe you’ll truly get pleasure from most of those concepts. Individuals typically say AI makes inventive work much less enjoyable. Used effectively, I believe it may well do the alternative.

There are occasions when you recognize what you wish to say, however you don’t wish to agonize over each sentence. That’s the place vibewriting comes in.

Vibewriting is steering AI with tough inputs and iterative suggestions quite than attempting to engineer the right immediate or get a completed piece in a single shot. You give it context, react to what it produces, and regularly form the output till it matches what you need.

Begin by letting AI produce a primary draft, then deal with it like one thing to edit, not one thing to publish. Ask it to make the writing punchier, lower the introduction, broaden a bit, tighten a paragraph, or rewrite a weak transition. Every spherical of suggestions strikes the draft nearer to what you had in thoughts.

Instance

I used this technique to jot down Agent-To-Agent Advertising Was Simply Born on Moltbook. I requested Letaido (AI advertising platform by Ahrefs) to get some knowledge on Moltbook.com, gave it some notes from my handbook analysis, and an arc of the story that I already had in my head, and requested it to mix every little thing collectively in an article.

Our Director of Content material Advertising, Ryan Legislation, tried out this technique and mentioned: “it was essentially the most enjoyable I’ve had writing for Ahrefs in ages.” Try his video:

Vibewriting additionally works with different kinds of content material, like presentation decks. Right here’s one I made for a webinar. You possibly can try the total interactive deck
right here, and right here’s the webinar the place I used it.

Beginning immediate

I wish to vibewrite a weblog publish about [topic]. This is my basic concept for the article [describe the idea]. I've gathered these supplies to this point [attach anything you'd like the AI to use and reference] and right here is the kind of article I am after https://ahrefs.com/weblog/creative-ways-to-write-with-ai/. Let's begin with the summary of the article and the define.

Strive with:

• Newsletters
• Opinion items
• Essays
• Quick analysis items

You’re circling a subject that received’t sit nonetheless. Concepts maintain touchdown at odd hours: a hyperlink a colleague sends, a screenshot, a thought in your commute you don’t wish to lose. None of it’s prepared for an overview but, and forcing construction this early would kill it.

So don’t. Hold one draft completely open and throw every little thing into it. Each time you add one thing, AI folds it in, and the piece thickens. Nothing is ever “began” or “completed.” It’s simply the perfect present synthesis of what you’ve collected. Construct that pile as soon as, and you’ll render it as an article at present, a chat subsequent month, three posts after that.

I name it the Dwelling Draft technique. It’s a bit much like vibewriting. The distinction is that with vibe writing, you steer a draft towards a vacation spot you have already got in thoughts, and with the residing draft, you don’t have a vacation spot but—you feed a subject over time and let the vacation spot reveal itself.

Instance

I wanted this workflow so badly that I ended up constructing a customized app for it with Letaido.

I’ve been utilizing it to doc every little thing that’s occurred in AI notion optimization since I revealed my experiment in December 2025: follow-up experiments, commentary, real-world case research, and milestone occasions—like Google being sued over the accuracy of its AI Overviews, to place it politely.

I begin with a working title and an issue assertion.

After which I simply drop in no matter materials I discover and watch AI unfold the story.

Beginning immediate:

Deal with this chat as a residing draft. At any time when I add new materials, combine it naturally into the article, take away repetition, enhance the construction, and level out gaps or contradictions with out rewriting my concepts.

And in order for you an app like mine, present this GitHub repo to your AI agent: https://github.com/mmakosiewicz/self-building-articles-app 

Strive with:

• Analysis-heavy articles
• Lengthy-term writing initiatives
• Matters you’re nonetheless exploring

Think about you wish to write about one thing you recognize inside out. You’ve performed the work, discovered the teachings, and have insights you genuinely suppose are value sharing.

Now the exhausting half: turning every little thing in your head into one thing that’s clear and fascinating for people who find themselves ranging from scratch.

That’s the place AI can assist.

As a substitute of asking it to jot down the article, ask it to interview you. Let it ask considerate questions, reply them as in case you’re speaking to a different individual, and use these solutions as the inspiration for the piece.

Instance

I’m utilizing this technique to jot down up an web optimization experiment on whether or not a structured FAQ will help AI assistants retrieve correct details about Ahrefs.

What I discover most helpful is that it helps me escape the curse of data. As a result of the AI doesn’t share all of the context that’s already in my head, it naturally exposes the gaps in my considering and forces me to clarify concepts extra clearly. The result’s often a greater article than if I’d tried to jot down it from reminiscence alone.

Beginning immediate

Interview me for an article about [topic]. Ask one query at a time like an skilled journalist. Problem obscure solutions, ask for examples, and maintain digging till you've got sufficient materials. Then flip the dialog into a sophisticated article whereas preserving my voice.

Strive with:

• Thought management
• Founder tales
• Case research and experiments
• Opinion items
• Classes discovered

I’ve observed that many questions don’t really need new solutions. Whether or not folks phrase them otherwise or ask from a barely totally different angle, the underlying reply is usually the identical. And most of the time, we’ve already written it someplace on our weblog.

The problem is extra about discovering the precise items and presenting them in a means that matches the query quite than creating new data

So after I run into this example, I level AI at our source-of-truth paperwork and let it do the digging. It finds the related passages, removes duplicate concepts, and assembles a draft that’s grounded in what we already know.

Instance

A minimum of 70% of this text is “recycled” from data we’ve already revealed. We already had every little thing we wished to say about AI chatbot visitors—it was simply scattered throughout dozens of weblog posts. So, as a substitute of writing it from scratch, I guided AI to tug these items collectively right into a coherent article.

If you happen to ask me, it turned out fairly effectively. It genuinely helps you perceive AI chatbot visitors, exhibits you tips on how to observe it, and it even ranks.

Higher but, it launched a special search intent into the highest 10. That’s simpler to tug off with low-KD key phrases, I do know—however I’ll take it.

The one cause I might put this text collectively so shortly was that I’d already constructed the infrastructure behind it: a “supply of fact” repository containing product documentation, Ahrefs how-tos, insights from our knowledge research, and different key sources.

At any time when I come throughout an vital inside web page, I add its URL to the app. It distills the important thing data and syncs it on GitHub, so later I can merely ask, “What do the SoTs say about this?” and immediately pull the related context right into a draft.

Beginning immediate

Search my documentation for every little thing associated to [topic]. Pull collectively essentially the most related data, determine recurring themes, take away overlap, and draft an article that builds on present data as a substitute of inventing new content material.

And in order for you an SOT app like mine, present this hyperlink to your AI agent:
https://github.com/mmakosiewicz/sots_webinar

Strive with:

• Product explainers
• Evergreen articles
• Documentation
• Guides and how-tos
• Updating previous content material

Among the finest content material begins with knowledge.

In these instances, the phrases are simply there to clarify what the numbers reveal. And likelihood is, you have already got useful knowledge sitting inside your enterprise: product utilization, buyer habits, marketing campaign efficiency, experiments, surveys, help tickets, or gross sales data.

The problem is discovering the tales hidden inside it. That’s the place AI shines.

Feed AI the info and ask it to analyze. Have it search for outliers, sudden patterns, shocking correlations, or questions value exploring. Then construct the article across the insights that emerge.

Instance

If you happen to’d prefer to see what data-driven content material seems to be like in apply, listed below are just a few latest examples written by Ryan Legislation and Louise Linehan.

We constructed these with Letaido, which has been an enormous unlock for working with Ahrefs knowledge. In contrast with a normal MCP setup, it provides us entry to extra knowledge endpoints, can work autonomously, and comes with native integrations like WordPress, so we will publish content material straight from the device.

Letaido dealt with the heavy lifting: connecting to Ahrefs knowledge, calling APIs for specialised databases, producing visualizations, and even serving to write components of the articles.

Si Quan from our content material group even constructed a customized Letaido app to automate the method of updating data-driven articles like these.

As a substitute of rebuilding every article from scratch every time the info modifications, the app refreshes the numbers and generates an up to date draft, making it a lot quicker to maintain our analysis present.

In this information, he explains how he constructed it, walks by the total course of, and exhibits the way it sends an e-mail notification when new knowledge is able to overview—so you possibly can observe the identical method your self.

Beginning immediate:

I am attaching a dataset from our enterprise. Do not write an article but.
First, analyze the info like an investigative journalist or analyst. Search for:
- shocking patterns or outliers
- traits over time
- correlations value exploring (do not assume causation)
- rankings and benchmarks
- something that contradicts frequent assumptions
- questions the info raises
- findings that may make a powerful headline As soon as you have analyzed it, suggest 10 article concepts primarily based on essentially the most attention-grabbing discoveries. For each, clarify why it is attention-grabbing and what further evaluation (if any) would strengthen the story.

Strive with:

• Unique analysis
• web optimization research
• Business experiences
• Product insights
• Knowledge journalism
• Instance

In 2026, an OpenAI mannequin solved a geometry downside that had stumped mathematicians for 80 years. The breakthrough was that it explored an method people had dismissed. Researchers spent many years attempting to show the accepted reply as a substitute of following an unpromising path. The AI had no such bias or impatience, so it discovered what everybody else ignored.

Brainstorming works the identical means. Most individuals cease after their first few first rate concepts—the identical apparent ones everybody else has. AI retains going.

You possibly can actually ask AI for “100 methods to consider this,” then cluster the concepts or broaden the perfect ones. It’ll floor angles you most likely wouldn’t have thought-about. Your job is deciding which of them are value pursuing.

Instance

My colleague Si Quan instructed me about this technique, and I’ve at all times been impressed by the titles and angles he comes up with. So I made a decision to strive it with an concept that retains coming again to me every time I analysis AI web optimization: model is content material.

It surfaced just a few angles I’d already explored, which gave me confidence it was heading in the right direction. However it additionally uncovered a number of concepts I’d by no means thought-about.

Listed here are a number of the new views I found due to this method:

By the best way, this technique is an efficient instance of how AI can increase your work, not solely automate it.

Beginning immediate

Give me 100 methods to consider [topic with a brief explanation of how you interpret it]. Cluster related concepts.

Strive with:

• Brainstorming angles and matters ought to work with any sort of content material.
• May very well be an excellent approach for repurposing longer content material items for social media short-form content material.

One in every of AI’s largest strengths is how adaptable it’s; possibly much more than people. You possibly can ask it to suppose in a specific means, and it’ll change approaches immediately.

You should use that to your benefit in content material advertising. As a substitute of asking AI to generate concepts from scratch, give it a confirmed considering framework to work inside.

A great framework provides the mannequin a transparent path to observe, challenges weak assumptions, and helps produce articles that designate, diagnose, or argue—not simply summarize.

So quite than prompting it to “write an article about [topic],” begin by giving it a strategy to suppose: Jobs to Be Achieved, the Idea of Constraints, Porter’s 5 Forces, a choice tree, first ideas, and even your individual psychological mannequin.

Instance

That is one other approach my colleague Si Quan launched me to. I already knew you possibly can ask AI to tackle a job—like a knowledge analyst, a lawyer, or a tricky editor—however this method felt extra structured and managed. So, let’s strive it in Letaido utilizing Opus 4.8.

The outcome was an in depth report with the complete reasoning course of specified by entrance of me. Two sections stood out particularly.

The primary was the place the AI challenged its personal conclusions, questioned its assumptions, and labored its means towards what it thought-about the strongest rationalization.

The second was seeing these insights make their means into the article itself. It wasn’t simply reasoning for reasoning’s sake—the AI truly carried its conclusions by into the ultimate draft.

I don’t know whether or not the AI genuinely reasoned its means by the issue or just simulated the method. And it positively didn’t produce one thing I might publish as is.

However that wasn’t the level.

It acquired me a lot additional than a clean web page would have, and it helped me set up my very own considering.

That’s extremely useful as a result of good writing begins with good considering—and considering remains to be the exhausting half. It’s not one thing we will totally outsource to AI.

Beginning immediate

Use the Idea of Constraints Logical Considering Course of to research
[topic]. First, construct the suitable logic tree for this kind of
article. Determine the seen signs, root causes, assumptions, constraints, and certain results of the proposed answer. Problem weak causal hyperlinks earlier than writing. As soon as the tree is sound, flip it into a transparent article with a powerful argument.

Strive with:

• Opinion items
• Product decision-making guides

Some articles don’t want a contemporary burst of creativity. They should come out the identical means each time. Launch notes, recurring roundups, touchdown pages: you already know the method. A single mega-prompt attempting to do it suddenly provides you inconsistent high quality you possibly can’t belief throughout a group.

Break it right into a pipeline as a substitute; a set of AI abilities chained collectively. Analysis, sources, temporary, define, draft, confirm, format, with a pause on your sign-off at every gate. AI does the levels between. You approve on the checkpoints, so errors get caught early as a substitute of compounding.

How is that totally different from typical AI content material automation?

• The workflow follows your confirmed course of. It isn’t inventing a brand new means of working every time, which makes the output extra according to the way you already write.
• You management the inputs and keep concerned all through. Since you’re invested in every stage, it’s a lot simpler to evaluate the standard, spot issues, and enhance the system over time.
• It’s comparatively fast to create and straightforward to alter. That’s as a result of the workflow is constructed from particular person AI abilities quite than locked inside a closed-source device. You don’t want deep technical data or pages of documentation to regulate it, both.
• It can be extra resilient than a inflexible automation. If one step fails, the AI can typically diagnose the issue, revise the instruction, or strive a special method as a substitute of merely stopping the workflow (in contrast to an n8n automation).

Instance

Ryan Legislation constructed an app like this utilizing Letaido. You give it a subject and some supply hyperlinks, and it takes care of the remaining. It researches the subject, creates an editorial temporary, builds an overview, writes the article, fact-checks each declare, and pauses at three key levels so you possibly can overview and approve the route earlier than it strikes on.

Right here’s Ryan explaining the app:

Beginning immediate

Construct me an assisted long-form article pipeline. Atomic enter is a goal key phrase. Phases run sequentially as background jobs the UI polls: (1) key phrase analysis through Ahrefs, (2) competitor SERP fetch, (3) AI Content material Helper matter snapshot, (4) bulleted define with mandated matter protection, (5) data-mention placement, (6) full draft, (7) polish, (8) WordPress shortcode formatting + .docx export. Every stage exhibits its output, has an "edit" textarea, and a "refine with suggestions" chat that re-runs the stage with my notes. Fashion information comes from a per-author voice profile.

Strive with:

• Recurring weblog posts
• Product bulletins
• Documentation
• Touchdown pages
• Editorial workflows

Buyer conversations have at all times been among the best sources of article concepts. They include actual questions, requested in your prospects’ personal phrases, and you’ll even see which of them come up most typically.

The issue was that uncovering these insights meant manually studying by 1000’s of help tickets, chat logs, and gross sales name transcripts. The knowledge was at all times there—it simply wasn’t sensible to entry at that scale.

That’s what AI modifications.

Level it at these conversations, and it may well analyze all of them, group related questions collectively, examine them in opposition to your present content material to keep away from duplicates, and determine the gaps in your content material library. The questions your prospects ask most frequently turn into the guides they’re truly on the lookout for.

Instance

This technique works with any sort of buyer help/CRM product so long as it gives an API or MPC with entry to buyer conversations. On this instance, I’ll be utilizing Fin (Intercom) with Letaido dealing with the MCP.

I discovered some untapped matters with just some minutes of working with the info. Apparently, some customers had bother discovering inside hyperlink knowledge and skilled points fetching knowledge with Google Knowledge Studio.

AI was even capable of generate some first rate solutions to those questions:

Kudos to Kamila Olexa for the concept!

Strive with:

• Assist middle articles
• Product documentation
• FAQs
• Buyer training
• Backside-of-funnel content material

Beginning immediate

Earlier than we begin, right here’s one tip for utilizing AI to research knowledge: don’t ask it to interpret knowledge you haven’t checked out your self. As a substitute of asking for the ultimate reply straight away, ask AI to indicate you the obtainable knowledge first and clarify what it’s seeing.

AI can nonetheless hallucinate or take shortcuts, particularly when analyzing giant datasets. For instance, we had round 7,500 Intercom conversations in a single month—far an excessive amount of to research reliably in a single cross.

Right here’s a immediate to begin that sort of evaluation:

I wish to determine gaps in our documentation, however do not generate suggestions but.
First, analyze our buyer conversations and present me the info.
Please:
- Group related buyer questions into themes.
- Rely how typically every theme seems.
- Embrace consultant examples from actual conversations.
- Present the precise wording prospects use every time attainable.
- Flag any uncertainty or themes that will overlap. Don't recommend new articles but. I wish to overview the grouped questions earlier than we resolve what to doc.

After reviewing the output, you possibly can observe up with:

Now examine these themes with our present assist middle and documentation.
For every theme:
- Inform me whether or not it is already lined.
- Level to the present article if one exists.
- Determine lacking or outdated content material.
- Rank the gaps by how typically prospects ask about them. Then recommend the highest 10 documentation alternatives, explaining why each deserves to exist.

A extra dependable method is to have AI monitor new conversations as they arrive in as a substitute of asking it to dig by months of historic knowledge suddenly. Breaking the duty into smaller, ongoing analyses is each simpler for the AI and far much less prone to produce deceptive outcomes.

Any more, monitor new buyer conversations as a substitute of analyzing the complete historical past each time.
At any time when new conversations can be found:
- Group recurring questions into themes.
- Spotlight any new matters that have not appeared earlier than.
- Observe which questions have gotten extra frequent.
- Evaluate new questions in opposition to our present documentation.
- Alert me when a recurring query is not answered by our assist middle. For each suggestion, embody:
- What number of conversations point out it.
- Instance buyer messages.
- Associated documentation (if any).
- A recommended article title and a brief define. By no means assume conclusions with out exhibiting the supporting dialog knowledge first.

Documentation begins going outdated the second you ship the following launch. A setting will get renamed, a restrict modifications, a brand new function launches, and abruptly, a assist article is not correct.

The identical is true for product advertising content material like purchaser’s guides and comparability pages. In lots of instances, it’s even tougher to maintain these updated as a result of it’s important to observe modifications in each your individual product and your rivals’.

That’s an issue for each web optimization and consumer expertise.

Thankfully, AI can maintain a lot of that work. All it wants is an inventory of the pages you wish to preserve, the sources the place it ought to search for updates, and—in case you select to offer it entry—your CMS, so it may well replace every little thing robotically.

Instance

My colleague Kamila Olexa constructed a system like that utilizing Claude Code and Firehose. Firehose (by Ahrefs) is a real-time net knowledge streaming API that constantly displays modifications throughout the general public net and pushes matching updates to your utility as they occur.

The workflow is constructed round automation with a human approval step. In a nutshell:

1. Firehose constantly displays your rivals’ pricing pages and triggers the workflow every time one among them modifications.
2. Claude then extracts the up to date pricing into structured knowledge, identifies which of your articles point out that competitor, and rewrites solely the affected sections as a substitute of the complete publish.
3. Moderately than publishing robotically, the workflow sends a abstract of the proposed modifications to Slack, the place you possibly can shortly overview what will likely be up to date.
4. A easy ✅ response approves the edits, after which the workflow updates the related pages in your CMS and publishes them robotically.

Beginning immediate

As a substitute of a beginning immediate, I’ll go away you with Kamila’s article. It explains her workflow from begin to end, so you possibly can copy the identical method your self.

Strive with:

• Product documentation
• API documentation
• Assist facilities
• Inside data bases
• Launch notes
• Function comparability pages
• Authorized or coverage modifications

AI bros found a planet manufactured from gold and determined the perfect use for it’s mass-producing low cost jewellery. You’ve gotten a greater choice.

You should use AI to make higher content material whereas having fun with the method. The catch is that it’s important to keep concerned. The extra you contribute, the higher the result. I believe that’s the course correction we have to make with AI.

Thanks for studying! Come and say hello on LinkedIn or Substack.