Category: Uncategorized

  • Day 100

    I’m using this word press blog to get my original thoughts out.

    In a sea of AI generated content, originality is rare.

    So I’m going to carry on writing as I want to.

    That’s not to say that I won’t use AI generation, but I’ll do it in other areas. For a personal founder blog, generating anything with AI seems completely counter intuitive.

    Hitting day 100 was somewhat of a decent milestone.

    I will review over the next few days and weeks but I wanted to give some space to an excellent hour long video with a guy interviewing Gary Vee.

    The only thing I would say about Vee, is he has done excellent *but* he did build upon his father’s liquor store business. It’s always easier to take something and optimise it than build from scratch. So always bear that in mind if you are looking to compare your version of success to his.

    That aside, he’s so excellent to listen to.

  • Day 99 – Flowgramming with N8N is better than vibe coding with Cursor and most software developers don’t see the threat

    Everyone is going on about vibe-coding at the moment but the dark horse that is gaining traction, which I think is more likely to have a much bigger impact … are flowgramming tools like N8N, Make and Zapier.

    Whilst the automation tools are technically not AI, and Zapier has been around for ages anyway, there is a surge in creative usage of the tools – especially since you can easily automate with AI APIs.

    Key value proposition:

    • The cost reduction of creating useful outcomes is massive with automation tools.
    • They are easy to use and only require programming knowledge in somewhat advanced situations.
    • They are very visual, meaning you can retain a birds eye view of what you are trying to do, without getting lost in code
    • Most software is just a collection of functions in a workflow and automation tools provide the framework that lets you easily work on these functions

    Of course not all software will be replaced, but I have a friend who managed to create a automated voice assistant who takes phone calls, all with N8N. It took him several weeks of long hard days, but he managed it all himself without any programming experience.

    Developers who have software experience will always be at advantage in some situations, and of course as the number of juniors going into the industry die, old school programmers will be in demand to fix older software … so hang in there developers, there will be an upsurge in demand eventually.

    For myself, as I explore the automation tools, I now have to face reality and ask whether every business case I get asked to make for people, could actually be done within the flowgramming paradigm … and a large proportion can be!

    I honestly think businesses who don’t create automation networks within the next few years will start falling behind. It’ll take effort to work out what can be automated within a company but there are always manual tasks that take up time.

    Once you’ve skilled-up someone within the company on a tool like Make, N8N or Zapier … and they know how the company works … you can start picking off small tasks that consume time. If you can completely eliminate pesky tasks that take a few minutes every day for everyone in the workforce, or even attack larger problems … you start saving hours every week.

    For instance, emails are getting unwieldy for most people around me. I’ve never liked emails much anyway, although we are very fortunate to have an open protocol that allows us to communicate with one another.

    How many minutes a day do I waste opening up my email, scanning through them to identify urgency, or longer term relevance, deleting the spam … and maybe even making a quick response to a simple question… this is stuff that can now be automated by an pervasive AI that has context on your situation and goals.

    An example with N8N that takes an RSS feed and outputs an image for each item

    Results

    For the moment I just selected the first RSS item as an example, and then pumped it through to the OpenAI image generator.

    If you aren’t impressed, then you aren’t paying attention.

  • The end of software engineering

    AI has fundamentally changed developers jobs. This is a really good conversation about how good AI is at building software. The reality is software engineering teams can be way smaller.

    This excerpt is AI generated

    Think of today’s AI coding agents as the “combine harvester” of software: what once took whole armies of engineers hand-tilling every line of code can now be done in minutes by supercharged bots, letting founders and small teams build, ship and iterate faster than ever.

    Suddenly, building an app no longer means wrangling legacy stacks for months—tools like Claude Code, Cursor and Windsurf let you dream up features, prompt them into existence, then sip your coffee while the AI auto-writes the boilerplate and infrastructure. It’s not about replacing creativity, it’s about amplifying it: with lower costs and higher velocity, you can focus on obsessing over real human problems (the skill that will always outlive any algorithm).

    The upshot? In five years, “software engineer” will mean someone who knows how to choreograph AI agents, not who types every function by hand. So don’t wait for the bots to leave you behind—embrace these tools now, level up your agency, and join the next wave of founders riding this revolution. (Fun fact: when Rome outsourced too much to mercenaries, it crumbled—so always keep core skills sharp!)

  • Days 79 – 84 Sugar!

    Am approaching launch on a web project that’s been a bit of a distraction to the AI efforts; but things are moving forward slowly.

    The truth is, I’ve been tired for the last month or so. I’ve really upped my output. But I’ve come up against my own energy levels. I’ve known for a while that I’ve needed to look at my diet and have made some good inroads in it.

    Last winter I removed caffeine from my life. No coffee, no tea. Five years ago I stopped drinking alcohol.

    Almost all major changes in life come about through fundamental paradigm changes.

    The past week my paradigm change has been around sugar. What’s this got to do with building an AI startup? To simplify the answer I would say it’s about energy. I’ve noticed how tired I’ve been getting – mostly mentally – over last month.

    This led me to point of realisation where I actually genuinely want to change what I eat. When you hit your 40s, your body starts slowing down if you haven’t looked after it.

    What is sugar?

    Coming from the sugar cane plant … the plant is then refined – stripped of all original fibre, minerals and vitamins – leaving a white crystalline structure that is very sweet and most importantly, soluble – which means it can be added to almost anything.

    Our bodies love the taste of sugar

    In some grand form of intelligent design, nature made fruits that are good for us, taste good. Natural sugar. So we like the taste.

    Big food industries realised they can hijack our natural taste for good natural sugar… with refined sugar … which became the trojan horse that allows it into our life.

    When you eat it, what happens?

    So, you get a high, followed by a low. You ingest something which has zero nutritional value and it completely disrupts your sugar levels. It’s high carb level means you probably won’t burn it off and it just gets stored as fat.

    … and that just leads to diabetes, heart disease and in general a life of lower vitality.

    The crazy thing that I’ve realised in the last week is how much bad sugar is in everything I’ve been eating my entire life. It’s not just the junk food; it’s any processed food, bread, rice, wheat, pastries … literally everything.

    Triggers

    It’s really useful to know what triggers cause you to reach for any sugary stuff:

    • boredom
    • sadness
    • stress
    • routine
    • reward

    The brainwashing

    What I’ve learnt this week, which seems obvious now, is that

    • anything with bad sugar in, is pretty much tainted with poison.
    • most of the food i’ve been eating, isn’t even food

    So, it’s no wonder that my body has started to ache and slow down; I am just eating actual food. It’s a wonder my body has managed to last this long. But it’s time to sort it out.

    So … a sandwich.

    Popular snack right? Often pushed as a lunch for busy people. Throw a bit of meat in there and a salad and you get a nice sandwich. But the bread isn’t really food. What sort of nutrition do you actually think the bread has? It has sugar in it, so it’s somewhat poisonous.

    Most will totally disagree. I would try to justify the bread. But anything with sugar in, by it’s very nature is going to damaging to your system. IT’S NOT FOOD!

    Absence of willpower

    There is a well known method of removing addictions that relies on changing perception rather than using willpower to stay away from the thing that is damaging you.

    I am talking about the unnatural sugar – the refined sugar that is present in everything. It messes seriously with your body to the point that it is responsible for killing millions of people every year. It is one of the things that we don’t talk about as a society, probably because most of us are unaware.

    We think we get pleasure from some foods mainly because of the high that we get immediately from foods with sugar in. So it fools us.

    It’s exactly the same as other addictions:

    Caffeine

    The main lie about caffeine is that it gives you energy and that it’s non-addictive. Caffeine has zero nutrients in it, and stresses your body out to produce an anxiety that feels like energy but actually frazzles you.

    Alcohol

    Alcohol is lied about too. The wonderful social aspect of alcohol is is a lie – it takes the credit for the endorphins that get released when humans socialise. But alcohol is an empty, meaningless liquid that has zero benefits.

    So what’s the lie about sugar:

    • We generally don’t consider it addictive
    • We know it’s ‘bad’, but we don’t realise HOW bad
    • We accept it’s added to foods, but don’t really pay attention
    • We accept it’s added for taste
    • The pleasure that we supposedly get from anything sugary is false – it’s just the food industry hijacks your natural taste buds for foods that are actually good for you
      • Also it raises sugar levels and gives you a brief high and then a crash …
    • We dont realise we develop a tolerance for it

    The big thing with sugar is that it creates its own demand. It leaves that anxiety that only it can fill. But the only solution is to remove that ongoing source.

    Enough for now.

  • Day 77 & 78

    As I continue to use AI in my work I increasingly know my world has changed fundamentally.

    Today I had to come up with a quick way of holding booking information, and be able to export it to CSV.

    Fairly standard stuff but in an unstructured codebase i.e. vanilla no framework, it’s a bit of a pain with what I have to work around.

    So I manage to get the data into the database fairly simply.

    Well, what about just a UI so that the customer can quickly look at whats going on in that DB rather than download it manually and open the flatfile.

    So I ask Cursor to help me out.

    Within a few minutes it’s made a UI that did the job, with a CSV export to boot.

    I will say that at one point it did some very stupid things in the code which I had to go and tell it ‘bad, please fix’ … but it quickly remedies.

    The more I use Cursor the more I realise that it is GREAT … BUT you need to know what you are doing so you can spot things. Potentially when I experiment with MCP it would have tested this itself, worked it out and remedied. But i’m not at that stage yet.

    It’s obvious that AI mimics intelligence really well, but the current LM stuff really doesn’t *think* at all; but sort of spoofs thinking. At any rate, if you are mid to senior developer it’s a phenomenal tool that you can make some really impressive stuff with.

    I have no idea really how this technology actually manages to do what it does. From the most vague prompt it can pretty much ‘understand’ my meaning, and give me what i’m looking for.

    We are the last generation to know what life was like before language models! Something to ponder on!

  • Day 76 – Recent Progress

    Last six weeks I’ve been working on some client work. It’s so difficult to do this and still have enough time to focus on your own stuff at the same time.

  • Day 75 -Emails With AI

    The system I’ve designed is capable of indexing and tagging emails. Just need to build the module that grabs them via IMAP. But emails really annoy me. They are incredibly unstructured and they allow anyone from ‘the internet’ to take up my time often with completely unstructured, poor quality information delivery.

    I’ve said quite a few times that language models are really primed for abstracting information away from people; and providing it to them in a much more synthesised fashion. As the amount of information increases exponentially, and the more busy you get the more shit you need to deal with.

    Hence, language models having excellent potential for emails. Not necessarily writing emails. I’ve sent a few emails that have been completely AI driven, and I always felt a bit sick afterwards. It just feels completely non genuine especially when they to people I know. But the idea of having an assistant that tracks incoming information, assessing and categorising them according to your training, this is a nice idea.

    Obviously already done and out there as a service; but the market will be extensive since everyone will have their own VA eventually.

  • Day 72 -74 Of Building An AI Startup

    A lot of my time and mental energy recently has been taken up with some paid work. But during that time I’ve made a lot of use of Cursor, now my goto IDE. It definitely makes me more capable and when I get stuck it can spot obvious mistakes which happen to the best of us.

    Overall, things are going well.

    My energy, attitude and work rate compared to day 0 are way better. I’ve had a few blips for sure.

    Building a team

    I was reading this week that the most effective companies are going to be small teams of senior experienced / C-Suite level thinkers and doers; working together toward building something.

    Employing people in the UK is incredibly expensive. I have no idea what junior level people are going to do anymore. The ones that work hard and compete, will do fine as always; but there will be a huge drop off of demand.

    Building an automated company

    The tools are now here to automate actions that are regularly taken in a company. It might be just the signing up of a customer to various systems, that are manually done. It might only save a few minutes but it means someone doesn’t need to context switch. So it’s not just the time saved, it’s also the mental energy saved.

  • Day 70 – AI makes you a 10x more useful programmer.

    Day 70 – AI makes you a 10x more useful programmer.

    Today was a breakthrough day.

    I needed to collect some data from two sources and cross-link them.

    I was able to use Claude 3.7 to generate several python scripts that used Playwright to crawl a site, intercept a script call and grab a particular value from it, and insert it somewhere else.

    Claude was able to generate the python scripts for me.

    I wouldn’t be able to do this without spending a long, long time learning python and how to use some of the libraries.

    So, another win for “AI”.

  • Work Diary #10

    Filament Forms

    In the last work diary, I covered how easy it was to link select fields … where values of select B are dependant on the value of select A.

    When you get an excessive amount of options though its nice to add a searchable field:

    Forms\Components\Select::make('venue_id')
    ->searchable()
    ->preload()

    So easy!

    But Filament gets even better.

    You can add an inline form to the select!

    ->createOptionForm(Venue::getForm())
    ->editOptionForm(Venue::getForm())

    The getForm function simply returns an array of form elements like you would get in the normal filament resource files.

    The amount of work this saves the developer is crazy good.

    Filament is really very good at first glance although I’ve noticed some very minor bugs.