Forem: Sam May

I made a finished lead magnet in minutes from a one line idea

Sam May — Fri, 20 Mar 2026 00:59:35 +0000

Everyone tells you to "make a lead magnet" like it's a quick afternoon task.

In reality you end up:

staring at a blank doc trying to pick a topic
outlining chapters that you'll rewrite 3 times
writing 5,000 words over multiple sessions
fighting with formatting in Google Docs
switching to Canva for a cover
exporting, realising the formatting broke, fixing it, exporting again

Most people abandon it somewhere around step 3. I've done this myself more times than I'd admit.

The experiment

I wanted to see what happens if I skip all of that and just describe what I want.

So I opened Inkfluence, typed in:

"Email marketing for beginners"

And hit go.

Just that one sentence.

What came back

Within a few minutes I had:

A structured 6 chapter ebook with an intro and conclusion
Each chapter actually built on the previous one (not the same generic advice repeated 6 times)
A designed cover
The whole thing ready to export as PDF or EPUB

I didn't touch Google Docs. Didn't open Canva. Didn't copy/paste between 4 different tools.

The thing that caught me off guard was that I actually finished. The whole thing. In one sitting. That basically never happens with lead magnets.

Why this is different from ChatGPT

I've tried the "paste a prompt into ChatGPT" approach. Everyone has. You get a wall of text that kinda sounds right but has no structure, repeats itself, and still needs hours of formatting work before it's something you'd actually put your name on.

The difference with Inkfluence is it handles the full pipeline, not just the writing part, but the structure, the formatting, the cover, and the export. You get a real file out the other end, not a chat transcript you need to wrestle into shape.

It also does something I didn't expect; the chapters are context aware. Chapter 4 actually references concepts from chapter 2 instead of pretending the earlier chapters don't exist. That's the thing that makes it feel like a real ebook rather than 6 blog posts stitched together.

Who this is actually useful for

If you're a:

Freelancer or consultant who keeps meaning to make a downloadable guide for leads but never has time
Course creator who wants companion workbooks or email courses
Small business owner who knows they should have a lead magnet but can't justify spending a week on it
Content creator who wants to turn their expertise into a low ticket digital product

This is the thing that actually gets it done. Not "generates some text you'll need to clean up later". Actually done. Cover, formatting, export, the whole lot.

What I'd actually use it for

Since testing it I've been using it for:

Lead magnets - the obvious one. PDF guide behind an email gate, done in minutes
Client deliverables - instead of spending 2 days writing a strategy doc, I generate a first draft and refine
Quick digital products - $9 - 19 ebooks on niche topics, basically passive income once they're listed
Content repurposing — take a topic I've already written about and turn it into a proper downloadable format

The mental shift is real. When making something takes 10 minutes instead of 10 hours, you just... make more things. The question changes from "can I be bothered?" to "what should I make next?"

Try it

If you've had a lead magnet idea sitting in your notes for months (we all do), just go try it:

👉 inkfluenceai.com

Free to start, no card needed. Type in your idea and see what comes out. Worst case you wasted 5 minutes. Best case you finally ship that thing you've been putting off.

AI Didn't Kill Publishing. It Changed What Matters.

Sam May — Tue, 24 Feb 2026 23:43:08 +0000

In 2026, you can generate a full book draft in minutes.

Outline, chapters, formatting, even a cover design. The mechanical part of writing is no longer the bottleneck.

That shift has split people into two camps.

Some assume publishing is now meaningless because anyone can generate text. Others assume writing is "solved" because first drafts are fast.

Both miss the point.

The draft was never the hard part of producing a useful book.

What Actually Stops Most Books

When people abandon a book project, it's rarely a speed problem.

It's a clarity problem:

Who is this book for?
What specific outcome does it deliver?
What belongs in it (and what doesn't)?
How do the chapters build on each other?

AI can generate coherent paragraphs. It cannot define scope.

If the premise is unclear, the output feels generic. Not because the language model is bad, but because the input was underspecified.

This is something we think about constantly while building Inkfluence AI. The tool starts with a structured outline step before any chapter is generated, because skipping that step is where most AI-assisted books fall apart.

Why Most AI Books Feel Empty

Low-quality AI books follow a predictable pattern:

Vague idea
Single large prompt
No outline review
Immediate export

The output reads fine sentence by sentence but lacks direction. It's the "tutorial hell" equivalent of book writing.

The issue isn't that AI writes poorly. It's that structure was skipped.

When the workflow includes:

Clear audience definition
Deliberate outline shaping
Sequential chapter drafting with context from previous chapters
An actual editing pass

The results are materially different. Same model. Better process.

We built Inkfluence around this exact flow: idea → outline → sequential chapters → cover → export. Each chapter is generated with awareness of what came before, so the book reads as a coherent whole rather than disconnected prompt outputs stitched together.

Drafting Is No Longer the Bottleneck

Before AI, finishing a first draft required sustained effort over months. Now it requires clarity upfront.

The leverage has shifted from endurance to decision-making.

If you know exactly what you're building, AI accelerates it dramatically. If you don't, AI makes that gap obvious fast.

Where AI-Assisted Writing Works Best

AI performs best in formats that already rely on structure:

How-to guides and practical books - step-by-step formats where organisation is the value
Business and strategy books — frameworks, processes, structured thinking
Study materials and workbooks — structured learning with clear objectives
Cookbooks — recipe collections with consistent formatting (AI cookbook generation works surprisingly well here)
Lead magnets — short, focused ebooks built to attract an audience

These formats are built around sequencing and organisation. That maps well to how language models operate.

AI performs less well when the value depends on lived experience, original research, or a distinctive voice. In those cases, it's a drafting assistant, not a replacement.

The Real Opportunity for Builders

What's changed isn't just that writing is faster. It's that shipping a professional ebook is now accessible to people who previously couldn't justify the time investment.

A fitness coach can turn their methodology into a lead magnet in an afternoon. A developer can publish a technical guide and put it on Amazon KDP within a week. A course creator can generate companion workbooks for every module.

The barrier was never ideas. It was production. AI removed that barrier.

What Has Actually Changed

Publishing is not easier in the way people assume.

Typing is easier. Formatting is easier. Starting is easier.

Defining something worth publishing still requires thought.

AI removed friction from production. It didn't remove the need for structure, audience clarity, or editorial judgement.

The people producing strong books in 2026 aren't generating the most text. They're the ones who understand what they're building before they generate anything at all.

I'm building Inkfluence AI — an ebook creation tool that takes you from idea to finished, exportable book in minutes. If you want to see the structured workflow in action, you can try it free.

How I Used Astro 5 + React + Inngest to Build an AI Ebook Creator (700+ Users, $0 Ad Spend)

Sam May — Fri, 13 Feb 2026 01:01:01 +0000

I've been building Inkfluence AI since October 2025 - an AI-powered ebook creator that takes you from idea to finished PDF/EPUB in minutes. 700+ users so far, entirely organic. No funding, no ads, just code and content.

This post is the technical deep dive. I'll focus on the architecture decisions, the SEO system that drives growth, and a relatively new channel; AI citation optimisation - that's been surprisingly effective!

The Architecture

The product has two distinct halves that serve very different purposes:

The App (React + Vite)

The ebook editor is a full React SPA. Users pick a content blueprint (23 types: novels, cookbooks, study guides, workbooks, lead magnets), generate outlines and chapters with AI, design covers on a canvas editor, and export to PDF/EPUB/DOCX.

Stack:

React + Vite + Tailwind CSS v4 on Vercel
Firebase Auth + Firestore for data
Stripe Checkout + Customer Portal for payments
OpenAI GPT-4.1 (mini on free/Creator tier, full on Premium)

The Marketing Site (Astro 5)

This was the pivotal architecture decision. I started with everything as a React SPA. Terrible for SEO because Google saw a blank page with a loading spinner. Moving to Astro 5 for the marketing site, blog, and landing pages was the single biggest growth unlock.

Blog posts are TypeScript files in src/lib/blog-posts/ that export metadata + HTML content. Astro auto-discovers them with import.meta.glob and generates static HTML at build time. No CMS, no database for content. Just TypeScript files and git.

// src/lib/blog-posts/my-post-slug.ts
export const metadata = {
  title: 'My Post Title',
  slug: 'my-post-slug',
  publishDate: '2026-02-12',
  // ... more metadata
};
export const content = `<article>...</article>`;

This approach gives me:

Zero runtime cost for content pages
Type-safe metadata - TypeScript catches broken links and missing fields at build time
Git history on every content change
No CMS lock-in - it's just files

I now have 84 blog posts, 15+ comparison pages, and 200+ total indexed pages. All static HTML. Lighthouse scores are consistently 95+.

Background Jobs (Inngest)

Book generation is the tricky part. A single chapter takes 60-90 seconds with GPT-4.1. A full 10-chapter book can take 5-10 minutes. Vercel serverless functions timeout at 30 seconds.

I evaluated several options:

Direct API calls with chunking - fragile, user has to keep the tab open
AWS SQS/Lambda - works but adds infrastructure complexity
Inngest - serverless durable functions with built-in retries, timeouts up to 300s, and step functions

Went with Inngest and it's been rock solid. The flow:

User clicks "Generate Book"
API endpoint fires inngest.send({ name: 'book/generate.requested', data: { projectId } })
Inngest function picks it up, generates chapters sequentially (each as a step with its own retry logic)
Firestore updates in real-time, frontend shows progress via snapshot listeners

// Simplified - actual function is ~200 lines with error handling
export const generateBook = inngest.createFunction(
  { id: 'generate-book', retries: 2 },
  { event: 'book/generate.requested' },
  async ({ event, step }) => {
    const { projectId, chapters } = event.data;

    for (const chapter of chapters) {
      await step.run(`generate-${chapter.id}`, async () => {
        const content = await generateChapterWithAI(chapter);
        await updateFirestore(projectId, chapter.id, content);
      });
    }
  }
);

The step-based approach means if chapter 7 fails, Inngest retries just that step instead of regenerating the whole book. Saves tokens and time.

The SEO System That Actually Works

I don't guess at content. Every piece starts with Google Search Console data.

The Weekly Loop

Export GSC queries, sort by impressions (descending) with CTR near zero
For high-impression / zero-click queries: rewrite the page title and meta description to be more compelling
For queries with no matching page: create one
Interlink everything - every blog post links to 3-5 related posts and 2-3 product pages
Run generate-sitemaps.mjs and ping IndexNow on every deploy

Real example: I saw "free ai book writer" pulling 136 impressions at position 38 with zero clicks. I didn't have a page for it. Wrote a 7-tool comparison. Within days it was indexed and climbing.

Internal Linking Matters More Than You Think

I spent a full session today adding contextual links between 9 related blog posts. Not a fun afternoon, but the data is clear: my well-interlinked pages (sitting inside topical clusters with 5+ bidirectional links) rank noticeably better than orphan pages with identical domain authority.

If you have a content site and you're not actively managing internal links, you're leaving rankings on the table.

IndexNow for Fast Indexation

I built an IndexNow integration (api/indexnow.js) that pings Bing/Yandex whenever I deploy. New pages get indexed in hours instead of days. The implementation is trivial:

// POST to IndexNow with your key and URLs
const response = await fetch('https://api.indexnow.org/indexnow', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    host: 'www.inkfluenceai.com',
    key: process.env.INDEXNOW_KEY,
    urlList: changedUrls
  })
});

Google doesn't officially support IndexNow, but I submit sitemaps to both GSC and IndexNow endpoints. Belt and suspenders.

AI Citation Optimisation (the Channel Nobody's Talking About)

This one surprised me. Microsoft Copilot has cited my pages 591 times, with the trend accelerating at 53 citations in a single day recently.

I started adding "direct-answer blocks" at the top of key informational pages. These are styled callout boxes with a single, comprehensive paragraph that definitively answers the page's core question. Example for my KDP SEO page:

What is KDP SEO? KDP SEO is the practice of optimising your Amazon Kindle Direct Publishing listing; title, subtitle, description, backend keywords, categories, and A+ content to rank higher in Amazon's search results. Unlike Google SEO which focuses on backlinks and domain authority, KDP SEO is primarily driven by keyword relevance, sales velocity, and review quantity...

AI chatbots love to quote these because they're self-contained, authoritative, and directly answer the user's question without requiring the AI to synthesise from multiple paragraphs.

If you're doing SEO in 2026, this is not optional. AI-driven search is becoming a significant traffic source, and the pages that get cited are structured differently from traditional SEO content.

Mistakes Worth Sharing

Starting with a React SPA for everything. I had zero organic traffic for months. Astro was a revelation - static marketing pages with React islands for interactive components. If your product needs organic traffic, choose your rendering strategy on day one.

Ignoring mobile for internal tools. I've been working 10+ hour days since October and only just made my admin dashboard responsive. Four months of being chained to my laptop to check metrics. Build responsive from the start, even for admin panels only you use.

Underestimating niche use cases. My cookbook/recipe-book blueprint turned out to be surprisingly popular. Users kept finding it organically while I focused all marketing on "ebook creation." Watch your analytics for unexpected use cases, they might be your best growth vector.

The Numbers

Metric	Value
Users	700+
Blog posts	84
Indexed pages	200+
AI citations (Copilot)	591, trending up
Ad spend	$0
Infra cost	~$20/mo
Time	4 months solo

Wrapping Up

The three biggest levers for growth, in order:

Astro for static pages - turned a React SPA black hole into 200+ indexable pages
GSC-driven content - no guessing, only writing what the data says people are searching for
AI citation blocks - structuring content so AI chatbots cite you (this is the next SEO)

If you're building a content-adjacent SaaS and not doing these three things, you're leaving a lot of organic growth on the table.

Happy to answer questions about any of this; the Astro + React split, Inngest for background jobs, the AI citation strategy, whatever.

Check out Inkfluence AI if you're curious about the product itself.

What actually works for writing full books with AI (after testing the tools)

Sam May — Tue, 10 Feb 2026 01:29:00 +0000

I started testing AI writing tools because I kept ending up with half-written books and no realistic path to finishing them.

At first, I did what most people do. I used general assistants like Claude to draft content. And to be clear, Claude is excellent at writing. The prose is thoughtful, it handles long context well, and it’s great for brainstorming and research.

But after a few attempts, the same pattern kept repeating.

I could generate good text, but I couldn’t turn that text into a finished book without a ridiculous amount of manual work. Every chapter lived in a chat window. Outlines were separate. Formatting happened later in Word or Google Docs. Covers meant opening Canva. EPUB meant another tool. Audiobooks meant yet another one.

None of that sounds hard in isolation. The problem is that when you stack all of it together, momentum dies.

What I realised pretty quickly is that most AI tools are optimised for writing, not for publishing. They stop at text. Everything after that is assumed to be someone else’s problem.

That’s fine if you’re writing an article or a one-off document. It completely breaks down when you’re trying to produce a real book.

The biggest issue isn’t quality. It’s continuity.

Once you’re a few chapters in, you start dealing with small but compounding problems. Chapters drift slightly in tone. Ideas repeat. You’re never quite sure which version of a paragraph is the latest one. You start hesitating before generating the next chapter because you know you’ll have to clean things up later.

That hesitation is what kills most projects.

What finally worked for me wasn’t better prompts or switching models. It was changing the workflow so finishing became the default outcome instead of something you had to push yourself toward.

That meant starting with structure, not text. A proper chapter outline that stays fixed while the content fills in around it. It meant writing chapters in a place where they’re already formatted, already organised, and already part of the final book.

It also meant treating exports as part of the process, not a chore at the end. When you can click a button and get a clean PDF or EPUB at any point, the book starts to feel real much earlier. That changes how you work on it.

This is basically why I built Inkfluence.

Not because Claude writes badly. It doesn’t. And not because tools like Canva or Designrr are bad either. They’re good at what they’re designed for. Canva expects you to bring finished content. Designrr expects you to already have blogs or podcasts to repurpose.

Inkfluence exists for the gap between those tools. When you have an idea, but not a manuscript. When writing is the bottleneck, not design. When you want to go from topic to a professional, downloadable book without stitching together five different apps.

Under the hood, Inkfluence is just using strong language models, the same class of models people already trust for writing. The difference is everything wrapped around them. Chapter management instead of chat messages. A real editor instead of copy-paste. Covers, exports, and audiobooks as part of the same workflow instead of afterthoughts.

The most important thing I’ve learned from all of this is that finishing books isn’t about brilliance. It’s about removing the points where people naturally stop.

If a tool reduces the number of decisions you have to reopen, reduces the amount of manual cleanup, and makes progress feel visible, you’re far more likely to get to the end.

Once you finish one book, the next one is easier. And the next one after that even more so.

That’s the real leverage. Not better sentences, but a system that doesn’t collapse halfway through.

If you’re curious, Inkfluence is the tool I ended up building to solve exactly this problem:

Inkfluence AI

A workflow designed to get books finished.

My SaaS has a Domain Rating of 2, and Google is ranking it anyway.

Sam May — Thu, 29 Jan 2026 19:51:06 +0000

I’m building Inkfluence AI, a SaaS that helps people create ebooks and PDFs with AI.

According to most SEO tools, my site’s Domain Rating is 2. Which, if you believe SEO Twitter/X, means I shouldn’t expect Google to rank anything I publish.

But when I open Google Search Console, I see something very different. Impressions are growing daily. Dozens of keywords are indexed. Pages are already climbing into the top 50–100 results.

That gap is what surprised me!

If you only look at Domain Rating, you’d assume nothing is happening. But Google clearly doesn’t wait for “authority” before testing new sites.

I didn’t do anything clever. No expired domains. No parasite pages. No link schemes. Most of my backlinks so far are just basic SaaS directories.

What did matter was intent.

Inkfluence pages are narrowly focused around what users actually search for: creating ebooks, lead magnets, and publish ready PDFs. Each page answers one thing clearly, and users actually stay and use the product.

My working theory is that Google treats early sites like a probation period. If your pages match intent and users don’t immediately bounce, you get tested - even with very low authority. Backlinks still matter, but they seem to matter more once Google already trusts that your site isn’t garbage.

What’s interesting is how far behind third-party tools are. My DR hasn’t moved, but impressions and clicks keep going up. Authority scores feel more like a trailing indicator than a gate you have to pass first.

I’m still going to write content. I’m still going to build links. That stuff compounds, for sure.

But this experience changed how I think about early SEO.

You need a real product, pages that match real searches, and users who don’t instantly leave.

If you’re building a SaaS and putting off SEO because your DR is “too low”, don’t. I almost did the same, and I’m glad I didn’t.

I’m building Inkfluence AI, a tool for creating ebooks and publish ready PDFs with AI: Inkfluence AI

AI vs Human Ebook Creation: An Honest 2025 Comparison

Sam May — Wed, 03 Dec 2025 19:21:45 +0000

AI vs Human Ebook Creation: An Honest 2025 Comparison

If you’re thinking about writing an ebook in 2025, you’ve probably noticed something strange happening in the publishing world. On one side, there are traditional ghostwriters and book coaches who position writing as a long, thoughtful, deeply human process. On the other, there are AI tools promising to turn ideas into a polished manuscript in minutes. Both claim to solve the same problem. Both tell you they’re the future. And for most creators, founders, and experts, it’s confusing to know which one actually fits your goals.

I’ve spent the last year building Inkfluence AI and talking to the types of people who actually write ebooks today - course creators, coaches, content creators, niche experts, solopreneurs, founders, teachers, therapists, and people building personal brands. Almost none of them are trying to write the next Pulitzer-winning epic. They want something far more practical: a clear, structured, professional ebook or workbook that communicates their knowledge cleanly and becomes an asset they can use to grow their business.

When you look at the landscape from that angle, the “AI vs human” debate stops being philosophical and becomes very real, very practical, and in some cases surprisingly simple.

What Traditional Ghostwriters Still Do Better

Human writers shine when the goal is depth, originality, emotional nuance, or a full-blown thought-leadership book. Teams like Intelligent Ink take a raw idea and expand it into a full manuscript, iterating, researching, shaping voice, and challenging your thinking along the way. That’s real, hard, specialised work. If you’re looking to write the next “big idea” book or publish with a traditional press, humans still win by a wide margin.

But that level of service comes with realities: long timelines, multiple drafts, complex reviews, and price tags that often land somewhere between £8,000 and £30,000 depending on what you need. And those timelines can easily stretch into six to twelve months. That’s not a criticism - that’s the nature of premium creative work. But it’s out of reach for most creators who simply need a polished, actionable ebook for their audience.

Where AI Has Completely Changed the Game

This is the gap where AI has quietly become the better choice for a huge segment of writers. Not because it “replaces creativity,” but because it removes all the friction that stops people from finishing.

Most creators already have more than enough material. They’ve written threads, newsletters, voice notes, blog posts, course scripts, private notes, emails, coaching frameworks, messy outlines - all of which already form 60–80% of a book. What they lack is structure, consistency, flow, formatting, and a system that turns what they already know into something usable.

That’s exactly what Inkfluence AI is built around. It doesn’t replace someone’s ideas. It organises them. It cleans up tone so the whole book reads like one voice instead of ten different moods. It fills in gaps without derailing your original concept. And because everything lives inside one workspace, you’re not juggling six different apps just to get one chapter finished.

The biggest surprise for most users isn’t that the AI can write paragraphs. It’s that it can take chaos and turn it into a book-shaped project in minutes - something that traditionally required a strategist or book coach.

What Readers Actually Care About (Hint: It’s Not the Method)

Readers don’t ask whether a book was written by an AI or a human.

They ask:

Is this useful?
Is this clear?
Is this something I can apply?

A well-structured, well-designed ebook answers those questions instantly. Most readers don’t care if you spent six months outlining it with a consultant or generated it in two hours using a properly-built workflow. They care about value and clarity.

What AI speeds up is not “writing creativity.” It speeds up the boring middle part - the part where most people quit. Cleaning, organising, formatting, rewriting, restructuring, editing, and converting raw material into something smooth and professional. In 2025, the most common ebook problem isn’t a lack of ideas. It’s unfinished drafts abandoned in Google Docs.

The Honest Trade-Offs

There are trade-offs. A human ghostwriter can interview you, challenge your thinking, and pull out stories or philosophies you didn’t know you had. AI can’t do that. Human editors can detect subtle emotional cues and narrative arcs that models still struggle with. AI can’t replicate years of lived experience.

But for 80% of ebooks - practical guides, niche-specific how-to books, mini-courses, lead magnets, playbooks, frameworks, handbooks, content repurposing - that level of depth isn’t required. What matters is speed, clarity, consistency, and getting the book finished.

That’s why creators have shifted their expectations. They no longer need a handcrafted, literary masterpiece. They need a useful, polished asset their audience will actually read.

Why Many AI Tools Still Fail (And Why I Built Inkfluence Differently)

Most “AI book generators” fail because they treat book writing as a text-generation problem. But a book isn’t just text. It’s structure, hierarchy, pacing, voice, layout, design, flow, typography, and the ability to navigate the entire manuscript as a single project.

That’s the part I rebuilt from scratch when rebuilding Inkfluence.

Instead of generating chapters blindly, the system works across the whole project. It understands the outline, the relationship between sections, and the tone you set at the start. You can drop in messy notes or long drafts, and it reshapes everything into a coherent, human-sounding manuscript. Then it handles the layout, spacing, page breaks, and export formatting - the part that normally forces people into Canva for a weekend they didn’t plan for.

The goal wasn’t to “copy ghostwriters.” It was to remove the unnecessary parts of the writing process so more people can actually finish the books they start.

So Which Option Wins in 2025?

Neither wins universally. It depends on your goal.

If you want a deeply researched, high-profile, traditionally published book that represents years of thinking, hire humans. Teams like Intelligent Ink exist for a reason and do brilliant work.

But if your goal is to produce a clean, valuable, professional ebook, workbook, guide, or lead magnet without disappearing into a six-month writing hole - AI wins every time. It’s faster, cheaper, accessible to everyone, and designed for the workflows creators actually have.

And if you already have a library of ideas scattered across apps, AI doesn’t just win - it’s objectively the only option that can turn that chaos into a finished draft in a single afternoon.

The Future Is Hybrid

The real answer is not “AI or humans.” It’s both. Humans bring depth, intention, originality, and creative judgment. AI brings speed, structure, clarity, and the ability to turn messy ideas into a refined, publishable format without friction. In 2025, the writers who ship consistently are the ones using both.

I built Inkfluence for that world.

A world where creators don’t need permission to write a book.
A world where ideas become assets instead of abandoned drafts.
And a world where publishing stops being a mysterious, complicated process and becomes something you can complete in a single focused session.

If that’s the world you want to build in, Inkfluence is waiting for you.

AI Ebook Generator