Checking whether you are signed in…
Your sign-in link is ready. Click the button to sign in.
CoachSteff.live
Your learning space
Your learning-space account: the free articles with Learn, the rest with a subscription. You sign in with a link in your inbox, no password needed.
Step 1: create your free account, or sign in if you already have one. Step 2: you go straight on to the payment.
Check your inbox
Thank you, your subscription has started! Your new level appears here in a few moments.
My overview
View →You have read everything. New articles appear every day.
To the articlesMy learning path
See allNo course chosen yet. Pick one you really want to follow.
See the coursesMy material
See allYour next step
-
Your SWOT only starts after the four lists
Four lists of strengths, weaknesses, opportunities and threats are just step one. With the confrontation matrix, you turn them into priorities and an action plan.
Four sheets on the wall, or four columns in a document. Strengths, weaknesses, opportunities and threats, neatly filled in with post-its in four colours. You might have spent a whole afternoon on it, together with your team. And yet, afterwards, you do not really know what to do with it. It feels like finished work, but nobody knows what needs to change on Monday.
In a training course on strategic thinking, I asked who already knew the SWOT analysis. A few participants had already worked with it. What most people call a SWOT is actually just the first step. I see people say that their four lists are ready, and then they stop. After that, the real exercise begins, and it is called the confrontation matrix.
Read -
Separate your handout from your slides
If you put everything on your slides to send them out afterwards, you get an audience that reads along instead of listening. Here is how you separate your slides and handout.
Read -
Template, a README that your successor and their agent understand
A README to fill in, with the prompt that makes your agent write it and a test with a fresh agent, so someone else can install your tool without calling you.
Read -
In an online meeting, sound comes before video
People forgive a blurry picture faster than bad sound. Here is how you sort out your online setup, with a backup in case something does fail.
Read -
You can steer a meeting, even if you are not leading it
You can steer a meeting that gets bogged down in talk as a participant. With a few good questions, you bring it back to decisions and actions.
Read -
Let your agent write the manual before you deploy
What you build with AI must be readable by someone else later, human or agent. Ask your agent to write the documentation before you put something live.
Read -
Swipe file, prompts for Copilot in Word, Excel and Outlook
Prompts to paste into Copilot next to your open document in Word, Excel or Outlook, so it does the work in your file and you no longer have to copy and paste.
Read -
Start on time, even if not everyone is there
A meeting that waits for latecomers costs the time of those already sitting there. This is how you respect the clock, from the first to the last fifteen minutes.
Read -
You do not need to know everything in advance to build
Writing everything out in advance or building in short loops? Both are possible, but those who only see the result at the end often get a kitchen they did not want.
Read -
Make Copilot work in the app where your document is
In the standalone chat, Copilot mostly gives you text back. Open it in Word, Excel or Outlook, and it does the work itself right there in your document.
Read -
Prompt pack, the tidy-up for your AI's memory
Four prompts to tidy up your AI's memory: first testing what it still believes, then proposing, deciding and keeping the map small. You decide what can go.
Read -
Shareable card, which thinking level for which task
One card to hang next to your screen: four settings for your AI's thinking level, two questions to set the dial and two prompts for your own rule of thumb.
Read -
Let AI prepare the work and an ordinary workflow send it
You do not have to choose between an agent and a workflow. Let the agent create what is different every time, and a fixed workflow do what is always the same.
Read -
Your AI's memory needs a clear-out too
Let your agents keep track of what they do, and their memory grows faster than you think. A regular clear-out keeps it small, a bit like dreaming.
Read -
Worksheet, your monthly review with your AI
A fifteen-minute worksheet for your review with your AI: first your own guess, then its answer, one choice, and two prompts to close the loop.
Read -
Are you stuck? Talk it out first, even to a rubber duck
If your building project with AI gets stuck, pushing on a bit longer rarely helps. Stop in time, and talk your problem out loud, to a rubber duck, a colleague or your agent.
Read -
Who decides at each fork in your workflow?
Every workflow has points where it must choose which way to go. Here is how you determine for each fork whether a rule, an agent or you yourself decide.
Read -
Your AI does not always need to think deeper
Alongside your model is a second button: how deeply your AI thinks. Higher is not always better. Here is how you choose the right thinking level for each task.
Read -
Clicking approve is not control
If your agent asks for permission at every step, you will eventually click approve blindly. This is how you put control where it actually makes a difference.
Read -
Swipe file, phrases to open and close your meeting
Phrases you can say word for word to open a meeting, explore together, work with resistance and close. Plus a prompt for your notes.
Read -
Why your AI refuses in one app and not in another
The same question, the same model, and yet a different answer? Then the app is deciding too. Here is how you read a refusal and know what to do with it.
Read -
All your instruction files count
Is there an AGENTS.md in your home folder and in your project, and you do not know which one counts? They both count. This is how you organise them without contradictions.
Read -
Checklist, cleaning up your agent's instructions
A checklist to clean up your agent's instruction file in fifteen minutes, with the signs that it is getting too big and two prompts for a fresh session.
Read -
Ask your AI what you are missing
Have you been working with your AI for months? Let it look back at what you did together. The answer can be confronting, and that is exactly why it is useful.
Read -
Building it yourself means maintaining it yourself
Your AI can easily build you a custom CRM. But if you build it, you maintain it. Here is how you decide what to build yourself and where to let an existing tool do the work.
Read -
Open first, then decide
Do you want to get to the conclusion as quickly as possible in a meeting, and is that exactly where it gets stuck? The participation diamond shows why opening first is faster.
Read -
Prompt pack, your agent as orchestrator
Five prompts to let your agent divide the work: breaking down your plan, defining roles and handovers, asking for the status, adjusting and learning afterwards.
Read -
Ask what kind of meeting it is first
Do you never quite know what is expected of you when you get an invitation? One question about the kind of meeting tells you how to prepare.
Read -
Clean up your agent's instructions now and then
Your instruction file grows with every project, and your agent loses track. Let it check for itself now and then what is duplicated, redundant or contradictory.
Read -
A new role is growing between your team and IT
You know your work, IT knows the systems, and together you often talk past each other. A new role is growing in between: someone in your team who builds with AI, within the framework of IT.
Read -
Resistance in your meeting has more than one face
Is someone being difficult in your meeting? First look at what resistance you are facing: not understanding, not wanting to, or not trusting. Each requires a different response.
Read -
Worksheet, what your own morning newsletter needs to know
A ten-minute worksheet for your own newsletter in n8n: your topic, your sources, what counts as important, and a completed instruction for your agent.
Read -
Your app works on your laptop, what next?
Deploying and publishing are not the same. Here is how you choose between a web app on a server and a real app in the store, and how you test it on your own device first.
Read -
Let one agent distribute the work
Does your chat with your agent go on endlessly during a larger project? Turn it into an orchestrator that distributes the work across other agents, while you keep talking to it.
Read -
Let your agent set up your server
Your app is ready, but setting up a server feels like a separate profession. Give your agent access to your own server and let it propose and arrange the technical side.
Read -
Step-by-step plan, your own content machine with one prompt
Five steps and one central prompt to turn what you already do into a small content machine that writes in your voice. And you remain the one who publishes.
Read -
Build your own newsletter that is ready every morning
Too many newsletters and still not keeping up? A workflow with a timer searches for news about your field every morning and emails you the three most important stories.
Read -
Your chatbot gets smarter from a narrower document
Is your chatbot answering vaguely or missing the point? Give it a narrow knowledge document, separate instructions and tell it explicitly where to look.
Read -
Let the agent that knows your business build your workflow
The assistant in your automation tool knows nothing about your work. Connect the agent on your computer to n8n and let it build, with up-to-date documentation included.
Read -
Template, an agenda item where everyone gets to speak
A script to fill in for one agenda item in 1-2-4-All, with the sentences you can say word for word and a time schedule. Ready in ten minutes.
Read -
If your agent is stuck in a loop, send in a second one
Is your agent trying to fix the same thing for the tenth time? Open a new session, point them to the stuck session and ask for the root cause.
Read -
Let every brainstorm with your AI end in a briefing
Many good ideas die in a chat. Brainstorm out loud with your AI, in the car or on a walk, and always ask for documents at the end.
Read -
Prompt pack, a report that leads to action
Five prompts to close your meeting with agreements that happen: checking your report, getting actions confirmed and opening the next meeting.
Read -
Test your app outside the golden path too
Testing your own app feels thorough, but you often just follow the ideal path. Let your agent, and ideally a second AI, look for the edge cases.
Read -
Are you an expert, coach or facilitator in this meeting?
Do you lead a meeting and do most of the talking yourself? Here is how you choose your role for each moment: expert, coach or facilitator, depending on what the group already knows.
Read -
Prepare your meeting like you prepare a game
Do people in your meetings always seem completely lost? With the rules, the referee and the scoreboard of a game, everyone knows where they stand.
Read -
Let everyone think alone first, then together
Do the same three people always talk in your meetings? By going alone first, then in pairs and then in small groups, everyone gets a turn.
Read -
Worksheet, which box does your AI idea fall into
A ten-minute worksheet that runs your own AI idea through the four boxes of the AI Act: four questions, what you arrange per box and a prompt that interviews you.
Read -
A meeting request is actually a question
Are you going from meeting to meeting and not getting to your real work? With a small filter, you decide for yourself where your contribution counts.
Read -
Every to-do opens a loop in your head
Do you have to say you had no time again in the next meeting? This is how you see the open loops in your head, and close them one by one.
Read -
Swipe file, ten questions for your notebook
Ten questions to copy for your notebook in Copilot or Gemini, for a client conversation, your own organisation, a job interview and checking the answers.
Read -
What goes into a good meeting report
Do you get a long report after every meeting that nobody reads? With five fixed parts, everyone knows what was decided and who is doing what.
Read -
A shared chat is not a private message
Worried that your AI is leaking your data? Often the leak is in the share button. Here is how you check what you have shared in the past and what your AI is allowed to do with your conversations.
Read -
Am I allowed to do this with AI? The AI Act as a quick check
Are you doubting whether you are allowed to do something with AI? The four risk levels of the European AI Act help you to categorise your own use case in a few minutes.
Read -
Template, the mandate for your server agent
A mandate to fill in that says what your agent is allowed to solve on your server by itself, when, and what it always leaves to you. Ready in fifteen minutes.
Read -
Lock down AI and you get shadow AI
Are you barely allowed to use AI at work? Then people will find their own way, and that usually involves their private chatbot. Here is how you prevent that.
Read -
Checklist, ready to switch AI tools tomorrow
A short checklist to see where you are tied to a single AI provider, with the prompt that makes your instructions and your context portable.
Read -
Give your AI one file with your brand style
Let your AI make slides or a website and everything looks like what everyone else makes. With one file containing your brand style, it looks like yours again.
Read -
Nothing is too crazy to imagine
Lots of ideas and no idea where to start? A small project for yourself, without a boss or a deadline, is in my opinion the most fun place to learn how to build with agents.
Read -
Create a notebook if you just want to know something
Do you need to build an agent for a stack of documents? If you mainly want to extract insights from them, a notebook in Copilot or Gemini actually works better.
Read -
Start with the boring chore
Anyone who wants to automate usually thinks of the biggest process right away. I would start with the small tasks you do the same way every time.
Read -
Let your AI discover how you write
You often do not really know how you sound yourself. Your AI can extract it from your own emails, and then it will write a bit more like you from now on.
Read -
Prompt package, from design to screen in six prompts
Six prompts to copy that take you from a briefing to a built screen that really looks like your design, with a description that you read through yourself first.
Read -
What is your agent allowed to fix on your server?
An agent that patches your server itself needs a mandate. This is how you decide which sources it believes, what it is allowed to do itself and what it leaves to you.
Read -
Tell your agent when it is finished
An agent keeps working until it is done, if you tell it what done means. This is how I describe in advance what a good result looks like, as a checklist.
Read -
How to help build a stronger internet together
Did you put something online yourself after a workshop? After a week full of security leaks, you can read here how an agent guards your server for you, including the prompt.
Read -
You do not have to write out your skill yourself
Building a skill sounds like a lot of writing. Today I leave that to my AI. Four ways to let your AI create a skill, including by demonstrating it.
Read -
Not every workflow is a chain
Before I build a skill or an agent, I look at the shape of my work. A chain, a branch, a nest or a diamond, and what that changes.
Read -
Step-by-step guide, your first email agent in six steps
Six steps with ready-to-use prompts to build an agent that goes through your emails every morning and tells you what needs your attention today. Ready in half an hour.
Read -
Why I do not tie myself to a single AI provider
The big AI companies are bringing you in cheaply right now. I prefer to spread my work across multiple tools, and I explain why and how you can do that yourself.
Read -
Do not just download a skill from the internet
A skill is a folder, and it can contain more than just text. This is how I let my agent look at an interesting skill first and make its own version of it.
Read -
Let your agent tell you what it sees first
An agent that has to build a design often turns it into something else. I let it describe the design first, and only build it afterwards.
Read -
Template, onboarding your AI in six messages
Six fill-in-the-blank messages that tell your AI who you are and how you work, plus the question to check what sticks afterwards. Done in fifteen minutes.
Read -
How to get IT on board when you start building yourself
Anyone building tools themselves with AI will sooner or later run into IT. Why that resistance is there, and why a small, concrete request works much better.
Read -
AI feels free, but the bill is coming
AI feels almost free today, because someone else is paying the bill. I would already work as if you are paying the real price.
Read -
Your first agent only sees your mailbox
An agent that checks your emails every morning is an ideal first agent. This is how you write the instruction and how you give it only what it needs.
Read -
Ask your AI how sure it is first
If you translate into a lesser-known language or about something sensitive, I would ask your AI how sure it is first, and then translate it back with a second AI.
Read -
Worksheet, which documents can go into which AI
A fifteen-minute worksheet that divides your documents into three buckets: leave as is, business or European, and local. With the prompt that helps you sort.
Read -
The enquiry that got left behind
No enquiry gets left behind and no follow-up gets forgotten. How AI helps you reply quickly and follow up on time, without it feeling cold to your clients.
Read -
The email mountain on Monday morning
The manual work that returns every week does not have to stay with you. What AI can take over from your emails, reports and quotes, and how you start small.
Read -
Share card, the babysitting loop for vibe coding
One card to hang next to your screen or share with your team, plus six sentences to adjust your AI in plain language while it builds for you.
Read -
Give your AI an onboarding, just like a new colleague
A new colleague gets an onboarding, your AI usually does not. I use six questions from my coaching practice to teach my assistant how I work.
Read -
Read the deviation, not the gesture
Crossed arms or looking away say little on their own. I first look at how someone usually is, and then I pay attention to what deviates from that.
Read -
More personal than your competitor
Your advantage lies in working more personally. AI helps you work faster and more tailored to your client, with your own voice included.
Read -
Two sides of yourself, one in each hand
You rarely solve an inner conflict by choosing. With the Visual Squash you look for what both sides of yourself want, and that is often the same thing.
Read -
What are you still paying for every month?
Many small costs keep running because no one looks at them. Which tasks you can take into your own hands with AI, and how you start small without stacking subscriptions.
Read -
Checklist, building safely with AI before your app goes online
A short checklist for those building apps with AI, including the security paragraph for your brief and the prompt to have a second agent attack your app.
Read -
No connector for your tool? Let your AI build one
If your tool is not in the list of connectors, your AI can often build one itself. This is how I tackle that safely.
Read -
Your private AI subscription is not a company vault
An expensive personal AI subscription does not give you business agreements about your data. I explain the difference, and what I keep local myself.
Read -
Let your AI think in English, even if you work in Dutch
Dutch costs your AI more working memory than English. So I let my AI work in English, and one sentence in your instruction is enough for that.
Read -
Complex is not the same as complicated
You repair a car by looking for the cause, but not a team. I explain why that difference matters and where we often go wrong.
Read -
Swipe file, ten sentences so your AI does not lose the thread
Ten sentences to copy for the start, the middle and the end of a long AI task, so you work with a handover.
Read -
Why your SMART goal remains a wish
A SMART goal sounds solid, and yet often nothing comes of it. What is missing when a goal only comes from your head, and how I make it SMARTER.
Read -
We think in lists, not in connections
Deleting one line in Excel cost an organisation its collaboration. Why lists hide what is going on, and how you learn to draw arrows.
Read -
Babysit your AI, even if it can do it itself
You can give an agent a goal and let it go, or watch along step by step. I teach the second in my workshops, and I explain why.
Read -
Give your AI a small brain, not a library
Anyone who puts all their documents into a knowledge base for AI will see their assistant drown in it. A short index that points the way actually works much better.
Read -
Fewer agents, more skills
I used to build a separate agent for every task, until I no longer knew who did what. Now I work with a few agents that share skills.
Read -
Prompt pack, six metaprompts that ask you questions first
Six prompts to copy that make your AI ask the right questions first, for an email, a plan, a doubt, a difficult conversation or your own assistant.
Read -
Git is just pressing save
Anyone building with AI will sooner or later be asked if they can commit. I explain what Git, a repo and GitHub are, without jargon.
Read -
Model, app, environment: know which layer you are in
ChatGPT, Claude, VS Code, Cursor, Craft Agents: those who start out often lump them all together. I work with three layers, and they help you choose.
Read -
Brief your AI with TOUCH instead of a superprompt
I now brief my AI with five letters: task, outcome, unknowns, context and handover, because today's models guess the rest themselves.
Read -
Your feeling is there first, your mind comes afterwards
Our feeling is already there before we start thinking. I explain how that works, and why emotional awareness actually begins in your body.
Read -
Ask your AI for lessons, not excuses
When my AI made a mistake, it started defending itself. I asked it for a lesson, and that is now in its memory.
Read -
Use their words, not yours
If you repeat someone's words in your own words, the connection breaks for a moment. Why I reflect things literally, even in an age of chatbots.
Read -
Give your AI a few custom shortcuts
Two colons and a short word, and your AI knows what you mean. This is how I put custom commands in my custom instructions, for things I ask every week.
In a workshop this week I showed my custom instructions on the screen. It says that I do not want to see any emojis. And not too many bullet points, and normal capital letters. And below that is a list of lines that start with two colons. Those are the rules I use most often, and they are barely a word long.
Feel free to copy the prompt at the bottom of this article, and you can write your first shortcut together with your AI.
What you type again every week
Take a look at your own chat history. Chances are you formulate the same questions over and over again. Translate this to Dutch. Write a short bio about me. Make this text a bit looser. Every time you type a sentence, sometimes two. And every time it is slightly different, so the result is too.
Read -
Create your skill at the end of the chat
Not every task needs a skill. I would create one for work you do often, and only at the end of a good chat.
Read -
One agent for everything is like one employee for everything
One assistant who knows everything and is allowed to do everything loses the overview. That is why I work with smaller agents, each with its own defined context.
Read -
Take your AI out of the browser
An AI on your own computer can read, organise and edit files. I explain what that changes, and how you start safely.
Read -
The most important file in your AI project is not code
Anyone who builds with an AI agent explains where everything is over and over again. One Markdown file solves that, and I tell you what belongs in it.
Read -
Learn to see through AI, not memorise the buttons
Your workflow works today and might break next month after an update. That is why understanding how AI works pays off more than memorising buttons.
Read -
Security belongs in your briefing, not at the end
Building an app with AI is fast. If you want it to be secure too, you put security in your briefing and let a second agent attack your work.
Read -
Before you build an agent, you draw the process
Can AI handle the reservations for a B&B? I always start with a drawing of the process, because that is really what determines whether an agent works.
Read -
What Copilot can and cannot see
Sometimes Copilot seems to know everything, and sometimes it cannot find a document that is right there. I explain how its index works and what you can do about it.
Read -
AI is not Google: you are the answer machine
Those who use AI as a search engine get confident nonsense and think less for themselves. Those who use AI as a thinking partner become sharper. The difference lies in the direction.
Read -
The critic in your group is your best creative asset
Good ideas often die in the second after they are born. Why real creativity needs the critic, and why you should make something tangible as quickly as possible.
Read -
Three types of agents, and why the middle one does the work
Knowledge agents, work agents and autonomous agents. Why the autonomous dream often derails today, and where the real gain is for those starting now.
Read -
First your backlog, then your delegation list, then something new
Anyone who works well with agents goes through three phases. The first two are about efficiency. The third is about work you could never have done before.
Read -
Memory or instruction? Facts and behaviour belong apart
Why your AI keeps forgetting your tone of voice. Put your facts, your rules of behaviour and the knowledge per client each in their own place, and it will work faster.
Read -
The document that gives your AI a different instruction
As soon as your AI reads files and emails, a hidden sentence can give it a different instruction. What prompt injection is and which rule you add today.
Read -
Choose the smallest model that can handle the work
The smartest model is not always the best. If you choose consciously per task, you gain control, time and space in your subscription.
Read -
Let AI ask you questions first
You do not write the best prompt alone. With one sentence at the end, you let AI question you first, and you become sharper in your thinking.
Read -
Markdown is the native language of AI
Why a PDF burdens your AI more than the same text in Markdown, and two small habits that immediately improve your output and your instructions.
Read -
Human in the loop or human on the loop?
With every automation you choose how much oversight you keep: approving every step, or watching along with your hand on the brake. This is how you choose what suits your process.
Read -
Edit your question instead of chatting on
If the answer is wrong, correcting it in a new message is the natural reflex. Editing your first question often works better, and your AI stays sharper.
Read -
Write a handover instead of compressing
A summary of a summary loses something every time. With a handover document and a phased plan, your AI will not lose the thread.
Read -
Skills or flows: when plain language is the wrong format
Describing a work process in plain language for an agent is flexible, but not always smart. When you are better off building a fixed workflow, and how you spot the difference.
Read -
Tell your agent what not to do as well
An agent does what it can, unless you provide a framework. Why boundaries in your instructions are just as important as the task itself.
Read -
Vibe coding does not start with the code
If you start building with AI straight away, you often get stuck. With a short discovery phase and a few early choices, you save days of work later.
Read -
Why your longest chat is your worst chat
A long chat does not train your AI, it fills the context window. Why the quality drops halfway through, and the habit that solves it.
Read -
Six coloured cards and no advice
A simple peer coaching exercise using the colours of the Six Thinking Hats. You just hold up a card and learn to listen in the meantime.
Read -
The EPIC Method: from AI strategy to daily practice
Four habits that turn an AI strategy into daily practice, for individuals, teams and entire organisations.
Read -
The Cognitive Agility Framework: five human capabilities
Five human capabilities that AI cannot take over, and a prompt to help you discover which ones you already use in your work.
Read -
The CRAFTER SuperPrompt Framework, step by step
Seven questions you answer before you press enter: this is how you turn a vague prompt into a reliable brief, for older and simpler AI models.
Read -
The Superworker Model: five levels of working with AI
From Status Quo to Elevate: five levels that show how professionals and teams grow their relationship with AI, and what each level requires of people.
Read -
The Drift and Human Compute: what you do not outsource to AI
Why your judgement gets weaker if you give all your thinking to AI, and why human attention remains the scarce computing power.
Read -
From chatbot to workflow: building your first AI workflow
A chatbot waits for your question, an agent completes a goal. Here is how you build your first own AI workflow this week, with a prompt to help you.
Read
Leap
Leap is the smallest circle and goes by request. Tell us briefly who you are and why Leap suits you; you will get a personal reply.
Your request has arrived. You will get a personal reply by e-mail.
Your request for Leap has been approved. Choose how you would like to pay.