← Back to the book

Free preview

Look inside AI-Powered Blog and Article Writing

This is the introduction and the opening chapter in full — the same text you get in the bundle, not a rewritten sample. The complete book runs to 45 sections.

See what's included

Introduction — The Statistic That Was Never True

Eleven hours, a rounded figure with its qualifier gone, and a verdict three months late.

Marek wrote articles for three agencies and two direct clients, at a per-word rate that had seemed reasonable when it was agreed.

The 2,400-word piece took eleven hours. Not because it was difficult, but because there was no outline. Marek researched for four hours, wrote for five, delivered it, and then received a note saying the client had expected a different angle — not a different topic, a different angle — which meant most of the research had been for the wrong article. The rewrite took two more hours and was not billable, because nothing in the arrangement said what a rewrite was. At the agreed rate the piece paid a little under what a competent evening's work should, and Marek had spent two evenings and part of a weekend on it.

That was the visible problem. Three others were quieter.

The first was a number. A piece published under a doctor's byline contained a statistic about how long a particular condition takes to resolve. Marek had taken it from a well-written article on a reputable-looking health site. That article had taken it from a press release. The press release had summarised a study — and had rounded, and had dropped the qualifying clause about which patient group it applied to. By the time it reached Marek it was a clean, quotable sentence with no hedging in it at all, and it was not true of the people who would read it. Nobody checked. It ran for a year under a real doctor's name, and the doctor had signed it off because doctors are busy and the writer is supposed to have checked.

The second was a handover. A piece delivered in March was published in July, retitled to something Marek would not have chosen, with two paragraphs added by somebody at the client who wanted a product mentioned. One of those paragraphs made a claim that the sourcing in the rest of the article did not support, and it sat directly above a properly cited section, which made the whole piece look carelessly researched. Marek found out by seeing it in a search result.

The third was a verdict. At the end of the quarter one agency reported that the articles "weren't performing". The measurement was ranking position at ninety days, on a site with four hundred other pages, half of which had been rewritten by somebody else during the same period, tracked by a tool whose traffic figures disagreed with the client's own analytics by roughly a third. There was no baseline. There was no record of what had been published when. And the piece that had actually earned the client an enquiry — Marek later learned, in passing — was one that ranked nowhere at all and had been forwarded by hand between two people who worked in the industry.

By month five Marek was working most evenings, being paid by the word for a job whose cost is research, and being judged on a number arriving three months late about a page that had been changed after delivery.

Nobody behaved badly. The health site was reputable. The press release was written by a person doing their job. The client who added a paragraph was proud of the product. The agency was reporting what its tool reported.

Every part of it was ordinary, and all of it was expensive.


What this book is about

This book is about the four things underneath that story, because every one of them is a property of the trade rather than a mistake anybody made.

Every sentence is a claim in somebody else's name. You are asserting facts about the world, under a byline that belongs to a person or a business who probably has not checked them. The chain from a study to a press release to an article to your draft loses a qualifier at every step, and the version that reaches you is the cleanest and the least true. This is why fact-checking is a separate pass in this book rather than a step in editing, and why Chapter 24 exists at all.

Research is unbounded and the fee is not. There is always another source, another paper, another person who would know. Nothing in the work itself tells you when to stop — the topic does not end, the reading does not end, and at eleven at night the next source always looks worth opening. The only thing that ends research is a decision made in advance, which is why the outline is the most important document in this trade.

You lose control at handover. The piece will be retitled. It will be edited by somebody who does not know which sentence the citation was attached to. A paragraph will be added. It will be published four months late, or split into two, or not published at all. What appears under that byline is not what you delivered, and you will be judged on the difference.

The verdict arrives late and belongs to somebody else. Rankings settle over months. Traffic tools disagree with each other and with the client's own analytics. Everything else on the site moved during the same period. And the piece that actually did something for the business may be the one that ranked nowhere and was forwarded by hand.


What this book will give you

An outline that lists the claims before they are written and identifies the source for each, signed off before drafting begins — which bounds the research, prevents the structural rewrite, and turns "a different angle" from a free rewrite into a scope conversation. A research budget stated in hours, agreed in the brief. An eleven-point fact-check run as a separate pass, on every number, date, name, quotation and link. A source library that makes the fourth piece in a subject cheaper than the first. A style guide that makes a voice checkable rather than a matter of taste. A delivery note that survives the handover and says what was checked, what was sourced, and what must not be changed without re-checking. And a report that states what you can honestly be measured on, agreed before the first piece rather than after a bad quarter.

The economic unit is revenue per finished piece — what a commission returns against every hour it consumed, research included.

The leading indicator is research hours per thousand words, which falls sharply once a source library exists and does not fall at all without one.

The master variable is the outline sign-off rate — the share of pieces drafted only after a written outline was approved. It is the single number that predicts whether a month is profitable.

And the risk indicator is the count of published claims you could not source, tracked cumulatively, because that is the one that ends up under somebody else's name.


Who this is for

Somebody paid by the word for a job whose cost is research. Somebody who has rewritten a piece because the angle was wrong and not charged for it. Somebody who has cited a statistic they found in an article rather than in the study. And anybody who has been told their work "isn't performing" by a number measured three months late on a page that was edited after delivery.

There is one more person in this, and they never asked to be here: the reader. They will act on what you wrote — take the advice, believe the number, follow the link — and they will do it on the strength of a name that is not yours. Chapter 5, Chapter 9 and Chapter 24 exist for them.


©2026 James Henderson / https://localhandyman.work

Chapter 1 — What Blog and Article Writing Actually Is

Writing is a third of it; the rest is research, structure and checking.

1.1 The job is not typing

Writing is perhaps a third of it, and it is the part everybody pictures.

Deciding what the piece is actually about, which is an angle rather than a topic. Chapter 20.4.

Finding out whether the thing you assumed is true. Chapter 22.3.

Deciding what may be claimed and what must be softened. Chapter 5.6.

Structuring it before writing it, which is where the hours are saved. Chapter 21.1.

Writing it in somebody else's voice. Chapter 23.2.

Checking every number, date, name, quotation and link. Chapter 24.2.

And handing it over in a way that survives being edited by somebody else. Chapter 7.8.

What people who have not done it imagine the job is: the fifth item, and only the fifth. Chapter 4.3.

Resource 1.


1.2 What you are actually selling

Not words, and not rankings.

That every claim in it can be traced to a source you actually opened. Chapter 24.4.

That the piece says something a reader could not have got elsewhere in five minutes. Chapter 20.3.

That it is structured so somebody skimming still gets it. Chapter 23.4.

That it sounds like the person whose name is on it. Chapter 23.2.

And that it arrives on the day, finished, without needing a rewrite. Chapter 21.7.

What a client believes they are buying: a word count, and a position in a search result. Chapter 4.1.

Why the gap matters commercially: everything on your list can be delivered on every piece, and neither thing on theirs can be promised — so the first conversation decides whether the arrangement is honest. Chapter 4.7.


1.3 What a piece actually contains

Behind a finished article, roughly, before anything goes wrong.

A topic and an angle, decided rather than received. Chapter 20.4.

A research block with a stated bound. Chapter 6.5.

An outline listing the claims and their sources. Chapter 21.2.

A sign-off before any drafting. Chapter 21.5.

A draft, written from the outline. Chapter 23.1.

A fact-check pass, run separately. Chapter 24.1.

A self-edit done cold, ideally the next day. Chapter 23.5.

And a delivery note saying what was checked and what must not change. Chapter 23.9.

What is missing from most people's mental version: the fourth and sixth items, which are the two that decide whether the fee works and whether anything goes wrong. Chapter 21.9.


1.4 The four rules

Everything in this book resolves to one of them.

One — every sentence is a claim in somebody else's name. Chapter 5.1.

Two — research is unbounded and the fee is not. Chapter 6.1.

Three — you lose control at handover. Chapter 7.1.

Four — the verdict arrives late and belongs to somebody else. Chapter 8.1.

They are not warnings. They are properties of the trade, true on the good commissions as well as the bad ones. Chapter 9.1.

What they replace: the belief that this is a writing job with some research attached. It is a research and judgement job with a writing requirement attached, and the difference decides whether you are still doing it in year two. Chapter 33.8.

Resource 3.


1.5 The five things a client cannot do themselves

Not because they lack the ability.

Stop researching, because they do not know what enough looks like. Chapter 6.9.

Find the study behind the statistic everybody repeats. Chapter 22.4.

Write about their own subject for somebody who does not already know it. Chapter 20.1.

Cut two hundred words they are attached to. Chapter 23.6.

And say plainly that a claim they want to make cannot be sourced. Chapter 5.7.

Which of the five sells the arrangement: the third, almost always — the expert who cannot write for a beginner is the most common client in this trade. Chapter 2.4.

And which one they thank you for two years later: the fifth, usually after somebody else's article got them into trouble. Chapter 5.5.


1.6 Where the hours actually go

Honestly, and it is not where a per-word rate assumes.

Research — the largest block, and unbounded unless you bound it. Chapter 6.2.

Outlining — small, and it is what saves the rest. Chapter 21.9.

Drafting — significant, and the part everybody counts. Chapter 23.1.

Fact-checking — separate, and never optional. Chapter 24.1.

Self-editing and cutting. Chapter 23.6.

Revision rounds, and rewrites caused by a missing outline. Chapter 21.7.

Interviews, transcription and quote-checking, where they apply. Chapter 22.6.

The single largest recoverable block: the rewrite caused by no outline — which is not efficiency, it is a process failure that a signed-off page prevents entirely. Chapter 21.5.


1.7 Who is already doing this

And what each of them leaves on the table.

Agencies, who price properly and have a minimum. Chapter 12.3.

Content mills, delivering volume with no sourcing and no angle. Chapter 12.4.

The client's marketing person, for whom this is the fifth thing on a list. Chapter 2.6.

A subject expert who cannot write for a non-expert. Chapter 2.4.

And a generative tool producing plausible text with invented citations. Chapter 37.3.

Where the recurring work actually sits: with clients who need long-form that is genuinely correct in a field where being wrong matters — because that is the one thing none of the five above reliably delivers. Chapter 12.5.


1.8 What makes somebody good at it

A specific and slightly unglamorous list.

Opening the source rather than citing the article that cited it. Chapter 22.3.

Stopping researching when the outline is satisfied. Chapter 6.9.

Structuring before writing, every time. Chapter 21.1.

Cutting the paragraph you are proud of. Chapter 23.6.

Writing convincingly in a voice that is not yours. Chapter 23.2.

Saying a claim cannot be sourced, in writing, to somebody who wants it. Chapter 5.7.

And checking a number for the second time when you already know what it says. Chapter 24.3.

What is not on the list: prose style. It helps, it is the most visible thing, and it is the smallest factor in whether a client renews. Chapter 28.5.


1.9 What the first year actually looks like

Roughly, and it is not linear.

Months one to three: research takes far longer than expected, and at least one piece is rewritten for free. Chapter 21.7.

Somewhere early: a client asks for a claim you cannot source, and how you handle it sets the relationship. Chapter 5.7.

Months three to five: the outline becomes non-negotiable, and hours per piece fall sharply. Chapter 31.6.

Months four to six: the source library starts making repeat pieces cheaper. Chapter 22.8.

Somewhere in there: a piece is published retitled, edited and months late. Chapter 7.5.

Months eight to twelve: the fee gets revisited against measured research hours rather than nerve. Chapter 31.9.

What decides whether year two is better: whether you were recording hours during year one. Chapter 35.1.


1.10 Chapter summary

Writing is about a third of the job; the rest is deciding the angle, finding out whether the assumption is true, bounding the research, structuring before drafting, checking every number and handing over so the piece survives editing. You sell traceable claims, a genuine angle, a skimmable structure, a borrowed voice and delivery without a rewrite — while the client believes they are buying a word count and a ranking. The largest recoverable block of hours is the rewrite caused by having no outline, which is a process failure rather than an efficiency problem. This is a research and judgement job with a writing requirement attached.


AI prompts for this chapter

Prompt 1 — Map Where My Hours Actually Go

"Map where my hours actually go on an article. ⚠ Split them into research; outlining; drafting; fact-checking; self-editing and cutting; revision rounds and rewrites caused by a missing outline; and interviews, transcription and quote-checking. ⚠ Tell me which block is largest and which is recoverable. Do not supply any figures, benchmarks or industry averages — use only what I paste.I will describe a recent commission."

Prompt 2 — Separate What I Sell From What They Think They Are Buying

"Help me separate what I actually sell from what a client believes they are buying. ⚠ What I sell: every claim traceable to a source I actually opened; a piece that says something a reader could not get elsewhere in five minutes; a structure that works for somebody skimming; a voice that matches the byline; and delivery on the day without a rewrite. What they believe: a word count and a position in a search result. ⚠ Everything on my list can be delivered on every piece and neither thing on theirs can be promised.I will describe the client."

Prompt 3 — Name the Five Things They Cannot Do Themselves

"For this client, name which of the five they genuinely cannot do themselves. ⚠ Stop researching, because they do not know what enough looks like; find the study behind the statistic everybody repeats; write about their own subject for somebody who does not already know it; cut two hundred words they are attached to; and say plainly that a claim they want cannot be sourced. ⚠ The third is the most common reason somebody commissions a writer, and the fifth is what they thank you for two years later.I will describe the business."

Prompt 4 — Pressure-Test My Understanding of the Trade

"Challenge my description of this business against four properties. ⚠ Every sentence is a claim in somebody else's name; research is unbounded and the fee is not; I lose control at handover; and the verdict arrives late and belongs to somebody else. ⚠ Treat these as properties of the trade rather than risks to be mitigated, and tell me where my description assumes verified facts arrive free, research ends by itself, the published piece is what I delivered, or performance can be attributed to my work.I will paste how I currently describe what I do."


⚠ AI checkpoint for this chapter

One — did it call this a writing job? It is research and judgement.

Two — did it leave fact-checking inside editing? It is a separate pass.

Three — did it promise a ranking? That is decided months later by somebody else.

Four — did it treat the rewrite as inefficiency? It is a missing outline.


Do This Now

1. Count the research hours on your last three pieces, separately.

2. Write down what you sell, in five lines, without the words "words" or "ranking".

3. Ask which of the five things this client genuinely cannot do.

4. Read the four rules once more, in order.

5. Find one statistic you have cited and open the actual study. Resource 1 and Resource 3.


©2026 James Henderson / https://localhandyman.work

That's where the preview ends

The rest of the book — 43 further sections — comes with your purchase, along with the worksheets, the resource library and the full set of AI prompts.

Everything in the book

  1. 01 Introduction The Statistic That Was Never True — included above
  2. 02 What Blog And Article Writing Actually Is — included above
  3. 03 Who Pays For This And Why They Decide
  4. 04 The Services You Can Actually Sell
  5. 05 What A Client Thinks They Are Buying
  6. 06 Every Sentence Is A Claim In Somebody Elses Name
  7. 07 Research Is Unbounded And The Fee Is Not
  8. 08 You Lose Control At Handover
  9. 09 The Verdict Arrives Late And Belongs To Somebody Else
  10. 10 What You Are Not And What You Refuse
  11. 11 Choosing What You Sell
  12. 12 The Brief You Write Rather Than Receive
  13. 13 Market Research And Competitors With Ai
  14. 14 Creating A One Page Business Plan
  15. 15 Startup Costs And A Realistic Budget
  16. 16 Sources Rights Disclosure And What To Establish
  17. 17 The Toolkit The Sources And What You Do Not Own
  18. 18 Pricing Per Piece Per Word And What A Contract Must Return
  19. 19 The Portfolio And Proving Work Published Under Another Name
  20. 20 The Writing Process You Can Repeat
  21. 21 Topic Strategy And The Content Calendar
  22. 22 Outlines And The Sign Off That Bounds Everything
  23. 23 Research Sources And The Interview
  24. 24 Drafting Editing And The Style Guide
  25. 25 Fact Checking And Citation
  26. 26 Quality Assurance And Auditing Your Own Work
  27. 27 Client Relationships Scope And The Contract You Should Not Have Taken
  28. 28 Analytics Rankings Traffic And What The Report Does Not Say
  29. 29 The Returning Client And The Article Retainer
  30. 30 Growth Volume Templates And A Second Writer
  31. 31 Records Money And Tax
  32. 32 Contract Arithmetic And What A Piece Is Worth
  33. 33 Seasonality Concentration And The Client Who Brought It In House
  34. 34 The Shape Of A Working Year
  35. 35 Standard Operating Procedures And Quality Control
  36. 36 Tracking Money And Attention
  37. 37 The Thirty Day Ninety Day And One Year Plans
  38. 38 Using Ai Responsibly In Your Business
  39. 39 Resources Part One
  40. 40 Resources Part Two
  41. 41 Resources Part Three
  42. 42 Resources Part Four
  43. 43 Resources Part Five
  44. 44 Resources Part Six
  45. 45 Back Matter