Create more engaging videos with simple, actionable scriptwriting tips.

This week, I've been hyperfocused on creating my AI Scriptwriting Partner.

I'm excited to share this for testing with my community members, but it also means I've had a hectic week, without much time to write.

So instead, I thought I'd catch you up with some new content you might have missed on my YouTube channel.

And I'd love to know - what content would you like to see more of over the next few months? 👀

The Claude Scriptwriting Hack Most YouTubers Miss

Just launched! 🚀

In case you missed my newsletter last week, this video shows you how to turn Claude into a reliable scriptwriting partner with 60 seconds of extra work at the end a scriptwriting session.

Don't write another YouTube script using AI until you've seen this 👀

Click to Watch

Viral YouTube Scriptwriter: THIS Kills Viewer Curiosity

This quickly became my fastest-growing video.

Learn how you might be using curisity wrong in your videos, and how to fix it.

Click to Watch

The YouTube Script System Nobody Told You About

If your main goal right now is to write scripts faster, without sacrificing quality, check this one out.

It goes through my entire scriptwriting process, and why writing it out of order leads to more engaging scripts.

Click to Watch

That's all for this week.

Any questions? You can to reply to this email and I'll get back to you.

Speak soon,
George 👋

I’ve started co-writing my YouTube scripts with Claude.

Not as a replacement for me, but as a writing partner.

The ideas, the core decisions, and the final draft are mine.

But brainstorming every stage with Claude is making the process faster.

Today, I'm sharing a simple yet powerful system that turns Claude into a scriptwriting partner that:

• Knows your audience.
• Writes in your voice.
• Gets better every time you use it.

And all it takes is plugging these two documents into a new Claude Project:

1/ The Training Document

• A basic summary of the core scriptwriting principles I teach.
• Contains an empty Example Library at the bottom, which fills up with your best work as you write more scripts.

2/ The Process Prompts Doc

• An instruction manual for the whole process.
• Walks you through a one-time setup to prepare Claude to write like you (by adding specific project instructions, then generating an audience avatar and style guide).
• Explains the powerful post-script routine which makes the system compound - after each script, Claude learns from the changes you made to what it generated and updates its own training documents for next time.

Ready to start using it?

​Click here to get instant access to the system.​

That's all for this week.

And in case you're wondering - I have no idea whether this system works well in ChatGPT because I have not tested it there.

I strongly recommend you switch to Claude for creative writing.

Any questions? You can to reply to this email and I'll get back to you.

Speak soon,
George 👋

‍

If you've tried using AI to write YouTube scripts and found the outputs are rubbish - and that it can even take longer - listen up.

Because the truth is, AI is really good at completely ruining scripts.

And it's not because it's "not good enough yet."

It's because the way you're asking it to generate scripts is broken.

But I've spent the last four years systemising my scriptwriting process for hundreds of students and clients, and I now use a hybrid AI / human method to write scripts in under two hours.

So... here's why AI is ruining your scripts, and how to fix it.

The AI-mistake almost every YouTuber makes:

You might think that after giving ChatGPT/Claude a few examples of “gold standard” scripts + a personal writing style guide...

...you can simply ask it to generate full scripts from scratch.

And while having a style guide + past script examples are absolutely necessary for writing scripts with AI, they’re not sufficient.

Because writing a full script involves a tonne of different, complicated, interlocking steps.

The AI has to interpret your notes, build a structure, expand every sentence in your voice, check that expanding those sentences doesn't break the structure, audit your hook, check for stakes… all at the same time.

It’s too much. And even AIs with higher token counts like Claude and Gemini will struggle to do these tasks to a high standard.

The solution, then, is to create your scripts in stages with AI.

Here’s the process I’ve been following with Claude recently...

Stage 1: Brainstorm collaboratively

Asking AI simply to "create the structure" for a video leads to disaster.

I’ve found AI consistently creates the "most logical" sequence possible… which might seem ok at first, but rarely holds up to closer inspection.

So instead of asking AI to hand you a complete structure, have a conversation:

Keep it flexible and free-flowing... there is no "right" way to do this part.

• Pass the AI your titles ideas.
• Discuss your core idea, and the different angles of approach you could take.
• Be honest about any blindspots or uncertainties.

Gradually, you'll settle on your angle of approach, and find your way towards a mutually agreed-upon structure.

Let the structure emerge from that back-and-forth, rather than a single prompt.

Stage 2: Write one “phase” at a time

This is the same principle I teach for writing scripts manually.

Writing a whole script from start to finish is overwhelming, and the quality suffers without a step-by-step system.

That’s why (as you may know) I always start by writing just the payoffs, word for word.

Then the setups. Then the tension. Then the hook and CTAs.

With AI, your approach should be no different.

Ask it to generate just the payoffs at first, then provide feedback.

Are they in a logical order? Are they individually compelling? Are they too similar to each other?

Once those are locked, move to the setups. Then the tension. Then the hook and CTAs.

This gives you the continuous ability to course correct… before the AI goes off and writes something insane.

Now you have your V1 script… but it’s not going to sound right just yet.

Stage 3: Rewrite segment 1, then ask AI to learn from your edits

This is where it gets really powerful.

Rewrite segment 1 to your liking - after all, the AI won’t have written it perfectly.

Then paste your re-write back into the chat, and ask AI to rewrite segment 2 while focused on:

1. What it learned from your segment 1 re-write.
2. Your style guide.

The second point is extremely important.

I’ve found, even with my style-guide pre-loaded into my scriptwriting project on Claude, it forgets to adhere rigorously to it as the chat gets longer.

Repeat this process across the entire script - re-write segment 2, and tell the AI to learn from it when re-generating segment 3.

Etc, etc.

Each subsequent segment will get closer and closer to your style.

Stage 4: The final pass

Asking AI to do a "final check" of the whole script is, once again, too broad.

You're basically asking it to "unbake the cake" and check whether all the frameworks, structures, tonal references (etc) are up to standard.

In my experience, this leads to the AI making bad suggestions.

So accept, if you can, the need to use your human brain for this part.

Read the script back to yourself, out loud if possible, and fix anything that sounds off. After everything you've just done, this part shouldn't take long.

Not only does this give you final oversight on the script...

...but it means you'll always provide the AI with a little more data about your writing preferences.

Data you can then ask it to learn from next time you write together.

In an upcoming newsletter, I’m going to give you my exact system in Claude for capturing that data and feeding it into your next script.

That's all for this week.

Any questions? Reply to this email and I'll get back to you.

Speak soon,
George 👋

‍

When it comes to AI, I go through phases of burying my head in the sand.

Everything is moving so quickly, and it sometimes feels like my AI knowledge is out of date the moment I learn something new.

But recently, I've started to find a nice balance of integrating AI into my scriptwriting workflow - without it feeling overwhelming.

And it's helping me write scripts faster than ever.

As I write this email, I'm on a train to Amsterdam for a long weekend away with my partner.

Which meant this week, I had just 3 days at home to write and record two videos for my editor.

Videos I had not even ideated at the start of the week.

Here's how I managed it, using AI to speed me up.

1) 1of10

It’s much easier to dive into writing a script when you can already see the packaging.

I’ve spent the last two weeks generating a batch of new thumbnail ideas using 1of10’s thumbnail generator.

Here are some of my favourites (all generated in under 60s):

We all know the advice is to “create packaging first”.

But in a busy week, it’s not practical to wait until you’ve completely finished a thumbnail before starting the script.

With 1of10’s generator, you get the benefit of seeing an almost finished thumbnail in literally 60 seconds - and that’s where the value truly is.

With 1of10, you can:

• Describe any thumbnail you can imagine and it will re-create it in your channel’s style.
• Physically sketch an idea and it will do the same.
• Give it a reference thumbnail from any channel, and it’ll create your version of that thumbnail.

I had to move fast this week... and having my packaging ready to go by 9:30am on Monday morning got me off to a great start.

Want to give it a try? Get 20% off a 1of10 subscription here:

Get 1of10 (20% Off)

2) “Live” Style Guide

Every week, I give feedback to my community students.

This feedback constitutes my most up-to-date advice.

So, for the last 2 weeks, I’ve been passing all my feedback into a continuous training document.

At the end of each month, I ask Claude to create a summary of my recent advice to my students, followed by:

1. Updating my current style guide.
2. Creating 5 YouTube script ideas based on that advice.

So... think about where you’re already writing/thinking about your area of expertise each week:

• On Zoom calls.
• In a newsletter.
• In Discord Groups / Group Chats.

Transform that knowledge into a continuous stream of new ideas and pre-written chunks of your next script.

3) Use "Projects".

This is basic, but most YouTubers still don’t do it.

If you’re already using ChatGPT or Claude (I recently switched to Claude btw), stop wasting time explaining what you need it to do each time you're using it to help with scripting.

Instead, create a project and pre-train it with:

1. Your personal style guide.
2. A detailed breakdown of its purpose (to write YouTube scripts).
3. Any additional materials you think it needs to write well (e.g. I upload the full 36,000 word PDF of my course to any scriptwriting-related project).

4) Ask AI to create a report on itself.

If you've used AI in any way to help structure or draft your scripts, always provide it with the final version of the script once you've made your edits.

Then ask it to create a report on itself, identifying the differences between what it generated and what you ultimately wrote yourself.

Then use that report as training data for your next conversation with it.

I've found Claude gets 10% closer to my exact style and structure with every script.

I'll speak more about this process in the coming weeks.

That's all for this week.

And, if you're interested in trying 1of10's new thumbnail generator (which continues to blow my mind), don't miss out on our exclusive 20% discount:

Get 1of10 Now (20% Off)

Any questions? You can to reply to this email and I'll get back to you!

Speak soon,
George 👋

In December, a student of mine was about to launch a new channel.

Tim had three videos scripted, filmed, and ready to launch (following my “Whirlpool” strategy).

But, days before hitting publish… Tim’s computer died.

The scripts were safe in the cloud - but the footage was lost.

So today, I want to share how he turned this apparent disaster into an amazing opportunity…

…and the important lesson he taught me about scriptwriting.

Success from Disaster

So the videos were gone... but the ideas were still top of mind for Tim.

After all, he’d just spent weeks writing and recording them.

So rather than wallowing in misery (like I would have done), he got curious.

He decided to record some off-the-cuff podcast episodes covering similar topics.

This stripped away some of the more heavily scripted elements and allowed him to experiment with riffing.

And let me tell you something - I am secretly (although not actually) a teeny bit glad this all happened.

Because the resulting podcast is fantastic.

It’s called: “The Fiction Writer’s Toolshed: Practical Tools for Authors”

Check it out here!

Technically, it's aimed at fiction authors.

But every episode is full of wisdom for any type of writer - and that includes YouTubers.

I'll finish today's newsletter with my favourite lesson from Tim's podcast so far.

But first, let's take a moment to consider Tim's response to this tech disaster, and how we can apply it to our own YouTube videos.

Ask yourself this - how many times have you recorded an entire YouTube video only to find the mic wasn’t switched on, or the focus was playing up, or even that you never hit record?

I’ve experienced all these and more - and the funny thing is, the next take is nearly always much better.

Practice makes perfect, and - albeit unintentionally - mistakes like these force us to practice.

And this was a heck of a lot more than "forgetting to hit record".

Tim had put hours into filming, editing, and preparing for publish.

But who would bet that when he re-records these same YouTube videos...

...they'll turn out way better the second time around? ☝️

Technical disasters are often blessings in disguise.

Here’s how you could apply this thinking to your next video:

• Experiment with an alternate format - a podcast, a Short, or even a newsletter - and see whether this changes how you express your thoughts on the topic. Then rewrite the long-form piece.
• Allow yourself a “trial run” during each recording - hit record just in case, but work on the assumption that you’ll record the whole thing at least twice.
• Discuss a topic with a friend, and record the conversation - and notice the objections or questions your friend has. This could totally change how you approach the script.

Scriptwriting Lesson - Farming vs Cooking

So what have I learned from The Fiction Writer's Toolshed?

Well, a lot! But here's my favourite takeaway so far:

This is from episode 5: “Fiction Farming vs Fiction Cooking” (listen here).

Tim says:

“Writing is not the same thing as coming up with ideas. They are not the same process.”

What Tim’s describing are the two different “modes” our brains enter when writing.

In associative mode, you’re “farming”.

You’re researching ideas and throwing them into a document, without knowing exactly how they’ll fit together yet.

In analytical mode, you’re “cooking”.

You’re combining those ideas, narrowing your options, and working towards a final script.

The problem Tim identifies is this:

“As writers, we try to cook while we’re still farming […] judging seeds that could grow into incredible ideas by the standards of a finished meal. If you do that long enough, writing starts to feel bad.”

This resonated strongly with me.

How many times have you opened a new script full of excitement, but quickly found yourself stressed out and unable to make decent progress?

And the longer this goes on, the more you start to believe you’re just a bad writer.

This is part of the reason I switched my scriptwriting approach - using pre-existing material from my newsletters, and plugging in my setups and payoffs in a methodical, repeatable way.

That’s farming.

Then I switch to my analytical brain and connect each setup to each payoff using bullet points - and often write the hook later once I’m sure all ideas have been gathered and arranged.

That’s cooking.

Now, if the way I explained this feels a bit overwhelming, go check out The Fiction Writer’s Toolshed.

Not only does Tim have an incredible radio voice, but each episode explains a writing problem + solution simply yet elegantly - and you won't find it difficult to see how his ideas connect to YouTube.

Thanks for letting me share this, Tim!

That's all for this week.

Any questions? You can to reply to this email and I'll get back to you.

Speak soon,
George 👋

Last week, we flew to Morocco for a little time away.

We drove through the Atlas Mountains, hiked the Todra Gorge, and eventually made it to the edge of the Sahara.

All the while, I was carrying precious cargo - my copy of Frank Herbert's sci-fi classic, Dune.

And, at sunrise, I sat on the sand and read a few pages.

In that moment, I was so focused on the Baron Vladimir Harkonnen's nefarious scheming, I didn't really have time to process the brilliance of the situation.

But in the days since, and looking back at the photo captured by my partner, Julia, I've realised how lucky I am.

To be able to take a random week off in February, and to pursue dumb little ideas like reading a book about a big desert while sitting in a big desert... it's wonderful.

The freedom and flexibility we're afforded by the type of work we do is amazing, and I want to thank you for making that possible.

Simply by having subscribed to this newsletter, you're contributing to the continued existence of my business - and I appreciate it!

So, this week, I'll leave you with my latest video - feel free to check it out if you'd like to learn how you might be using curiosity wrong in your videos:

Watch Here

Speak soon,
George 👋

Your hook can make or break your video's performance.

But... you already know this.

Yet most YouTubers end up damaging their retention by making a (completely logical) mistake in the first 30 seconds.

To help you identify it, take a look at this hook extract:

I assume you can see the problem.

The hook reads like a resumé, rather than a promise of value.

In fact, I used Claude to compare the instances where the YouTuber spoke explicitly about something the viewer would get from watching the video vs something they had done...

...and the results were pretty stark:

15 moments about the speaker. Their achievements. Their credentials. Their journey.

Just 1 about the viewer, and what the video would do for them.

But honestly… I understand why this happens.

YouTubers often front-load credibility because it feels like the logical way to earn trust.

But think about your own behaviour on YouTube. How many pieces of relevant credibility do you need to hear before deciding a video is worth your time?

Sure, the credibility needs to be relevant to the topic. But in the above example, if I’d simply heard...

“I grew [channel] to quarter of a million subscribers and over 650,000 euros in revenue, and in this video…”

...I can't imagine I'd be sitting there saying:

"Oh yeah, but what can you really tell me about YouTube growth and entrepreneurship?!"

No. I'd say: "Fantastic. You seem legit. Now what's in this video for me?"

Your hook only needs one piece of credibility. After that, talk to the viewer.

So... check your next hook for this totally logical - but ultimately harmful - mistake.

Or, for speed, paste your hook into an LLM using the prompt below.

Analyse the following YouTube hook transcript. I want you to identify every moment where the speaker refers to something they have done, built, or achieved (speaker-focused) versus every moment where the speaker describes something the viewer will get or learn (viewer-focused).Then produce a single HTML file that visually highlights these in two colours within the transcript, includes a bar chart comparing the counts, and ends with a short verdict summarising the imbalance.

Here is my hook transcript to analyse:

[PASTE YOUR HOOK TRANSCRIPT HERE]

(I started using Claude a LOT recently - it turns analyses like these into beautiful presentations.)

That's all for this week!

Any questions? You can to reply to this email and I'll get back to you.

Speak soon,
George 👋

“Be super specific - with everything."

I wrote that feedback to a student yesterday.

In fact, I rewrote six hooks in my scriptwriting community this week…

…and five of them needed the same fix.

Because non-specific language in your hooks is a big problem for both retention and gathering a loyal audience long-term.

Let me show you why:

Examples of non-specific language, and why it matters:

Example 1:

One student sent me a hook about nutrition for fitness. It started like this:

"Everyone is talking about the nutrition pyramid these days. As always, where attention goes, energy flows. If you're a career-driven human over 40..."

But here was my re-write:

"If you're over 40 and trying to [get down to X% body fat], you already know that nutrition is important. But after [X] years [doing relevant thing], I discovered that…"

Notice what changed?

• I cut the generalised opener ("Everyone is talking about...") entirely.
• "Over 40" became “over 40 and trying to [get down to X% body fat]”
• I added a placeholder for their specific credibility, where there had been none.

In this case, the added specificity makes it clear who the exact target audience is, what their goals are, and why this creator is the person to help them.

Without it, I have no reason to watch this fitness channel over any other.

Example 2:

Another student was writing about the dangers of having a fatty liver. One line said:

"If fat builds up on our liver, it can destroy it."

Which is true. But the impact of this is not made clear.

So I suggested adding this line right after:

"And long-term, this can lead to terrible side effects like [X] and [Y]."

(Again, I left placeholders for the YouTuber to add the specifics.)

But the point here?

Being specific helps the viewer truly picture what's at stake.

Yes, I know that a “destroyed liver” is bad. But I can’t really picture it.

But naming specific, day-to-day side effects it can lead to?

Now it feels urgent. Now I have to keep watching.

Example 3:

A third student was writing a video about menopause after breast cancer.

Can you spot the non-specific terminology in here? (It’s not super obvious.)

"So when women are frightened into thinking this is the rest of their life..."

It was only small, but there’s an important change to be made here too. See my re-write:

"So if you've been frightened into thinking this is the rest of your life..."

In this case, being more specific means talking directly to the viewer, as opposed to the general audience.

Your videos should be designed to address just the person watching, not a large crowd.

The Fix

To make sure your hook doesn’t fall into the non-specificity trap, ask yourself these three questions.

1/ Who is this for, specifically? (Target)

• Not "people who want to get fit" → "over 40s trying to build 10lbs of muscle"

(And, where possible, referring to them as “you”, instead of "they".)

2. What's the specific outcome you're promising? (Transformation)

• Not "grow your channel" → "hit 100k subscribers in 6 months"
• Not "write better scripts" → "cut your writing time from 6 hours to 90 minutes"
• Not "improve your fitness" → "get down to 15% body fat"

3. What's the specific consequence if they don't fix this? (Stakes)

• "It can destroy your liver…" → "…which leads to [X] terrible side effects"

This all ties back to my “target, transformation, stakes” hook framework (more info).

That's all for this week!

​Any questions? You can to reply to this email and I'll get back to you.

Speak soon,
George 👋

Sponsored by:
​1of10.com

Since launching my channel in October, the priority has been consistency.

I took a break over Christmas, but otherwise I haven't missed an upload.

But now it's time to get strategic.

Because, even at a glance, I've started to notice some interesting takeaways from my first 10 videos:

1. Listicles have consistently underperformed.
2. Riffing personal stories led to stronger retention and my most-viewed video. Riffing scripting advice led to extreme retention dropoff.
3. Text-only thumbnails (i.e. no fancy design) won the majority of A/B tests.
4. My "whirlpool strategy" for end-screen CTAs was highly effective at launch, but is becoming less effective over time. I have theories, but I'll need a full newsletter to discuss!
5. My most effective lead magnet came from this video where I pushed viewers to download a template I'd been subtly showcasing throughout the video.

I'm yet to do a full analytical breakdown of every single video, but this gives me a clearer direction for how to approach upcoming scripts.

I encourage you to take stock once every few months, too. Spend just an hour looking at your views + retention, and it'll be hard to miss the more obvious patterns.

But there's an even bigger change I'm about to make...

The Plan

Until now, every script has been directly converted from an old newsletter.

This was a useful approach, and I encourage you to repurpose other written material to increase your writing and uploading consistency, if that's something you struggle with.

The downside was - and don't tell anyone shhh - I was committing the cardinal sin of creating my packaging *after* writing the script.

But now it's time to strategically build every video from the packaging first.

To show you how I'm going to do it, I want you to check out this thumbnail:

What if I told you that this thumbnail was made in under 60 seconds entirely using AI.

Specifically, 1of10.com's mindblowing new idea and thumbnail generation tool.

For context, I've been using 1of10 for 2+ years, and their old thumbnail generation tool was... ok.

Good for some light inspiration, but ultimately not really usable:

Now? It's a whole different boardgame.

Not only does their idea generator create some great title inspiration...

...but the thumbnails themselves are, in many cases, 90% ready to use:

Now you probably had the same reaction as me:

An initial "wow, COOL!", followed by "wait, that diagram doesn't quite make sense".

Well, the coolest part is, you can prompt it to make any changes you want.

And let me tell you, if you've ever spent hours wrestling with ChatGPT's image generator and watched an *almost* perfect image slowly descend into dark mush the more you prompt it...

...this is not that.

When you request changes, it *does what you ask* with a high degree of accuracy... and fast.

Notice the small tweaks I asked for from my earlier example - like changing the main heading, removing duplicate words from the diagram, and swapping two boxes for "?" boxes.

Wait, sorry... did I say we'd already covered the coolest part?

Nuh uh. Check this.

Here's a quick thumbnail mockup I drew:

After uploading it to 1of10's thumbnail generator, I got THIS after just 60s 👇

Does this mean I'll stop using my thumbnail designer?

No.

I really care about the little details, and my thumbnail designer is not just an "artist", but also a strategist who I value highly.

But for many, thumbnails are a massive barrier to entry.

It's bloody hard to find someone both affordable and skilled.

That's why 1of10's idea and thumbnail generator will be lifechanging for thousands of YouTubers.

And as my channel strategy pivots from consistency to, well, actual strategy...

...I'll be using 1of10's idea and thumbnail generator to drive things forward.

Thanks to Richard and the team at 1of10 for partnering up with me again!

If you're interested in trying out 1of10 with 20% off, click here:

Try 1of10 [20% OFF]

I'll keep you updated on how these new strategic ideas perform...

...and how starting with the packaging (like a good boy) impacts my scriptwriting.

That's all for this week.

Any questions? You can to reply to this email and I'll get back to you.

Speak soon,
George 👋