Ready to build with AI?
Free, practical guidance for working critically, confidently and responsibly.
Why now?
-
An extension of the oath
I have always seen digital communication as an extension of my Hippocratic Oath.
So I am happy to teach, train and up-skill when it comes to digital communication in the intelligence age.
-
Long before AI
Long before the current AI era, I believed that helping reliable medical information reach more people was part of my responsibility as a doctor.
-
The benefits of broadcasting
That belief led me from search and social media into mainstream media, where working with journalists and broadcasters taught me more about the rigour and discipline involved in communicating responsibly.
-
A tectonic shift
The way people find and process information is undergoing a tectonic shift. For years, organisations could expect people to discover their work through websites, search engines or social platforms.
-
The collapse of traditional web search
Increasingly, information is being summarised, interpreted and delivered by AI systems before someone ever reaches the original source.
-
The space will not remain empty
If credible experts do not learn to participate in this new information landscape, the space will not remain empty. It will be filled by increasingly automated content, often produced at scale and designed to capture attention rather than improve understanding.
-
Risks of remaining silent
Some of it exploits the parasocial relationship between an influencer and an audience, building trust in order to sell something further down the line.
-
We have the skills
People working in medicine and the life sciences already possess many of the skills this moment demands.
-
they are transferable!
We learn complicated and rapidly advancing science. We assess evidence, work with uncertainty, revise our conclusions and remain accountable for the decisions we make. Learning to use AI is another expression of that commitment to lifelong learning.
-
The purpose
The purpose of these lessons is not to persuade everyone to build a website in twenty-one days.
It is to provide the scaffolding through which people across the life sciences can begin preparing now. When the need or opportunity arises, they should be ready to use these tools critically, confidently and responsibly.
-
Why now
We have an opportunity to help shape a new information ecosystem in which credible expertise remains discoverable and useful. If enough of us participate, the potential societal benefit for improving global health and well-being is immense.
1 / 11
-
An extension of the oath
I have always seen digital communication as an extension of my Hippocratic Oath.
So I am happy to teach, train and up-skill when it comes to digital communication in the intelligence age.
-
Long before AI
Long before the current AI era, I believed that helping reliable medical information reach more people was part of my responsibility as a doctor.
-
The benefits of broadcasting
That belief led me from search and social media into mainstream media, where working with journalists and broadcasters taught me more about the rigour and discipline involved in communicating responsibly.
-
A tectonic shift
The way people find and process information is undergoing a tectonic shift. For years, organisations could expect people to discover their work through websites, search engines or social platforms.
-
The collapse of traditional web search
Increasingly, information is being summarised, interpreted and delivered by AI systems before someone ever reaches the original source.
-
The space will not remain empty
If credible experts do not learn to participate in this new information landscape, the space will not remain empty. It will be filled by increasingly automated content, often produced at scale and designed to capture attention rather than improve understanding.
-
Risks of remaining silent
Some of it exploits the parasocial relationship between an influencer and an audience, building trust in order to sell something further down the line.
-
We have the skills
People working in medicine and the life sciences already possess many of the skills this moment demands.
-
they are transferable!
We learn complicated and rapidly advancing science. We assess evidence, work with uncertainty, revise our conclusions and remain accountable for the decisions we make. Learning to use AI is another expression of that commitment to lifelong learning.
-
The purpose
The purpose of these lessons is not to persuade everyone to build a website in twenty-one days.
It is to provide the scaffolding through which people across the life sciences can begin preparing now. When the need or opportunity arises, they should be ready to use these tools critically, confidently and responsibly.
-
Why now
We have an opportunity to help shape a new information ecosystem in which credible expertise remains discoverable and useful. If enough of us participate, the potential societal benefit for improving global health and well-being is immense.
- Get started with the modules →
I have always seen digital communication as an extension of my Hippocratic Oath.
So I am happy to teach, train and up-skill when it comes to digital communication in the intelligence age.
Long before the current AI era, I believed that helping reliable medical information reach more people was part of my responsibility as a doctor.
That belief led me from search and social media into mainstream media, where working with journalists and broadcasters taught me more about the rigour and discipline involved in communicating responsibly.
The way people find and process information is undergoing a tectonic shift. For years, organisations could expect people to discover their work through websites, search engines or social platforms.
Increasingly, information is being summarised, interpreted and delivered by AI systems before someone ever reaches the original source.
If credible experts do not learn to participate in this new information landscape, the space will not remain empty. It will be filled by increasingly automated content, often produced at scale and designed to capture attention rather than improve understanding.
Some of it exploits the parasocial relationship between an influencer and an audience, building trust in order to sell something further down the line.
People working in medicine and the life sciences already possess many of the skills this moment demands.
We learn complicated and rapidly advancing science. We assess evidence, work with uncertainty, revise our conclusions and remain accountable for the decisions we make. Learning to use AI is another expression of that commitment to lifelong learning.
The purpose of these lessons is not to persuade everyone to build a website in twenty-one days.
It is to provide the scaffolding through which people across the life sciences can begin preparing now. When the need or opportunity arises, they should be ready to use these tools critically, confidently and responsibly.
We have an opportunity to help shape a new information ecosystem in which credible expertise remains discoverable and useful. If enough of us participate, the potential societal benefit for improving global health and well-being is immense.
Where these questions came from, and where they are going: they began as one AI model's map of what a beginner asks. I am now testing that map against real readers, the people I teach and talk to, correcting it where it is wrong. The record shows the working.
What is this?
- What do I need to set up? The room, the folder and the habits a non-technical reader needs, using the Claude ecosystem as an example.
- Do I need to know how to code? No, not to start: this whole site was built by a doctor who never trained as a developer. What you cannot skip is verifying what the model builds, and that is the difference this session is about.
- What exactly is vibe coding with veracity? Vibe coding is building software by describing what you want to a model in plain language and reviewing what comes back; the veracity this site adds is the discipline that keeps the result trustworthy, and yours.
Can I do it?
- What is the best first project? The best first project is small, visual and about something you already know well, so you can check every word yourself. A one-page site, not an app: you stay the authority, and the model builds without becoming it.
- How do I write a good first prompt? A good prompt is not a secret form of words, it is a clear brief: what you want, what to reuse, what not to touch, and how you will check it. Six short fields, and none of them needs a clever phrase.
- What if the first version looks wrong? The first version being wrong is the normal start, not a failure. You do not scrap it: you say what is wrong, look at a few alternatives side by side, and keep the best. The taste and the veto stay yours.
- What if I get stuck in a coding loop? A coding loop is when each attempted fix returns you to the same fault, creates a new one or reverses the last change. The answer is not a more forceful prompt. Stop changing the code, name what you can actually see, ask for a diagnosis, and test one explanation at a time.
- How do I fix a bug without reading the code? Two real bugs on this site's signature design component were caught by looking at the page, not by reading the code; the four-step discipline that fixed them is one anyone can run.
Can I trust it?
- Is AI-generated code actually good? AI-generated code can be good, but "the page appeared" is not proof. Good code does the right job, survives checks, works on a phone, and can be changed without quietly breaking something else. You do not have to read every line, but you do have to ask for evidence and inspect the result.
- Is it really mine, and can I take it away? Ownership is not one switch. Your words, code, images, domain, accounts, third-party packages and AI output can each have different terms. Portability is simpler to test: keep the source in an account you control, download a complete copy, know which services it depends on, and prove that someone else could rebuild it.
- What I will not teach you yet, and why I will not teach a beginner to add logins, store private data, take payments or build a password system by asking an AI for one. Those features are possible, but their failures are hard to see and can harm somebody other than you. "Not yet" is a safety boundary, not a verdict on what you can eventually build.
Can I ship it?
- How do I get it onto the actual internet? Getting a vibe-coded site online is three things: a GitHub account for the code, a host that watches it, and a push. Knowing what a commit and a push actually do is the whole of the confidence.
- How do I update it once live? Changing a live site is two moves, not one: a commit saves the work, a push ships it, and on this site only the push goes live. Knowing which command is which is the whole of the safety.
- How long does it take, and what does it cost? AI can produce a first version in minutes, but the first version is not the finished work. Time is spent deciding, checking and refining; money may go on the AI tool, a domain and any services the site needs. A small static site can be inexpensive. Complexity and responsibility are what raise the bill.
Going further
Method and craft sessions that sit alongside the numbered climb rather than on it. Reach for them when you want to go deeper; they are not steps you have to take in order.
- How do I write prompts that land first time?The first brief gets you going; this is the craft around it. Two fields most people skip, a way to size a task before you write a word, and knowing when a quick ask is secretly a big one. None of it needs clever wording.
- How do I hand a prompt to another AI?A prompt written for another model has two audiences: you and the model receiving it. Name the model and tool, separate the operating instructions from the execution prompt, test one handoff, and record what actually happened.
- When should I get a second opinion from another AI?One model is enough to start, but when a decision matters and you are not sure, putting the same question to a second model is a powerful check. The discipline is what makes it work: treat a disagreement as evidence to test, not a contest to win.
Resources
Material to download and keep, alongside the sessions.