My Account

Articles

6GuXBPUJE9KLl50G8n24A

OpenAI Apps, ChatKit and AgentKit – The Future of Productivity

October 7, 2025

I was interested to read yesterday about OpenAI’s new Apps, AgentKit and ChatKit features.

These updates push ChatGPT far beyond a chat box; it’s becoming a proper workspace where you can do things, not just talk about them.

Here’s the quick version:

Apps in ChatGPT


You’ll soon be able to use tools like Canva, Booking.com, and Spotify inside ChatGPT. No more copy-pasting links or switching tabs; you can ask, “Canva, create a LinkedIn post about time management,” and it’ll just happen.

I’ve not had a chance to play with this yet, as it’s only available outside of the EU (and OpenAI seems to include the UK as part of the EU/EEA regulatory zone for many feature rollouts). We’ll have to wait for that one!

Early research shows that the responses within each app will be managed by the app developer. So, if I ask the Booking.com app to find me a hotel, the Booking.com algorithm will decide what to show, not the agent.

I do wonder how likely it is that paid results come into the mix here, and how useful that will really make these tools. I am, however, super excited by the Canva app.

OpenAI AgentKit


A new system for building your own personal or business “agents” that can take action, connect to apps, and run tasks automatically. Imagine a virtual assistant that can organise files, book meetings or summarise your week.

This is going to be a direct challenge to systems like Zapier and N8N, which already have agents baked into their software. I’ve built some really useful agents in N8N that have definitely made an impact on productivity.

That said, I had a little play with AgentKit earlier today. The UI seems intuitive enough, but I couldn’t see enough ‘plug and play’ options for the everyday user.

It requires tools to be built and connected, and it seems to rely on MCP in some cases (Model Context Protocol) unless you can properly code your own tool using Python.

Promising, but so far I think I’ll stick with N8N.

OpenAI ChatKit


ChatKit lets developers embed ChatGPT-style assistants into websites and apps, so the same AI experience follows you wherever you work. I’ve not had a chance to play with this one yet, but I looked at a demo on HubSpot’s help site (which apparently uses this) and it looked decent enough.

Why It Matters


We’re heading into an era where AI becomes less about clever conversations and more about getting things done. The line between “chatting with AI” and “automating your day” is about to disappear.

If you’ve ever wanted one place where you can brainstorm, plan, design, and execute – all without leaving chat – this may be it.

Productivity is about to get a serious upgrade… or is it? For now, maybe just for those with the capability to code tools, or the patience to learn how to connect the available apps to their accounts.

Did you see the announcement? What are your thoughts?

Read more
AI Time Saving

How to Save an Hour a Day with AI in Everyday Workflows

September 24, 2025

What would you do with an extra hour in your day?

While artificial intelligence (AI) can’t add more minutes to the clock, it can help you reclaim time by reducing the effort spent on small, repetitive tasks. Too often, AI is talked about in terms of futuristic projects or replacing entire jobs, but the real power lies in how it can simplify your everyday workflow.

Whether you’re managing a business, leading a team or simply looking to get more done, AI can be your digital assistant for all the little tasks that usually slow you down.

Why Everyday AI Matters

Most people think of AI in terms of big, flashy innovations – self-driving cars, robotic assistants or large-scale data analysis. But the reality is that AI becomes most valuable when it supports you in small, practical ways.

Instead of overhauling your entire process, think of AI as a way to clear out the clutter. Every email, meeting note or draft document that used to take 20 minutes can now be handled in seconds. Multiply that across your day, and suddenly you’ve got time back for the bigger decisions and conversations that truly need you.

Five Everyday Tasks You Can Hand Off to AI

Here are some practical examples of how AI tools like ChatGPT, Claude or even Microsoft Copilot can help you save time every day.

1. Summarising Emails and Reports

Inbox overload is real. AI can scan long threads or dense documents and give you a concise summary of the key points. Instead of spending 20 minutes reading line by line, you can get the highlights in seconds.

  • Without AI: You skim, risk missing details and waste time.
  • With AI: You get a bullet-point overview and know instantly what matters.

2. Turning Meeting Notes into Action Lists

Meetings often generate lots of notes but little clarity. AI can transform rough notes into structured agendas or clear action lists ready to share with your team.

This saves you the hassle of rewriting everything and ensures tasks don’t fall through the cracks.

3. Polishing Bullet Points into Blog Drafts

Staring at a blank page is one of the hardest parts of writing. AI can take a list of bullet points and turn it into a draft blog post, article or LinkedIn update.

It won’t necessarily give you the finished piece, but you’ll start at 80% done rather than 0%. From there, you can add your personal insights, examples and style.

4. Generating Quick Quiz Questions

If you create learning materials, presentations or training resources, AI can instantly turn your content into multiple-choice questions or knowledge checks.

This is a quick win for trainers, teachers and team leaders who want to add engagement without manually writing each question.

5. Drafting Polite Follow-Up Emails

We’ve all spent too long rewriting a follow-up email to strike the right tone. AI can generate polite, professional templates in seconds, saving you the mental energy while still letting you customise before hitting send.

The Real Benefit: Reduced Friction

The key isn’t that AI does everything for you – it’s that it removes friction. Those small bottlenecks that slow you down are suddenly gone.

Instead of wrestling with wording, reformatting notes or digging through an email chain, you’re already moving on to the next important task. Over the course of a week, that could easily add up to five hours or more reclaimed.

Practical Tips for Getting Started

If you want to integrate AI into your everyday workflows, here are some simple ways to start:

  • Pick one task that frustrates you most (emails, notes, or writing) and test AI on that first.
  • Be specific in your prompts. For example, “Summarise this report in 5 bullet points for a busy executive.”
  • Review and refine. AI is fast, but it’s not flawless. Always add your personal insight before sharing.
  • Experiment with different tools. ChatGPT, Claude, Gemini and Microsoft Copilot each have strengths.

Final Thoughts

AI doesn’t have to be about huge innovation projects. Its real value comes when it quietly supports your everyday work, clearing away the repetitive and low-value tasks so you can focus on what really matters.

Think of it as a digital assistant that saves you from inbox overload, rewrites your notes into something useful and gives you a first draft instead of a blank page.

The result? Less frustration, fewer bottlenecks, and yes — potentially an extra hour in your day.

So, the question is: what everyday task would you happily hand off to AI this week?

Read more
LinkedIn AI Role Priming

Role Priming in ChatGPT: A Simple Trick to Get Better AI Responses

September 23, 2025

Artificial intelligence tools like ChatGPT are becoming essential for professionals in every industry. From writing content to analysing data, AI can save time and boost productivity. But there’s one simple trick that many people overlook, which can make your results dramatically better: role priming.

In this article, we’ll explain what role priming is, why it works and how you can use it in ChatGPT and other AI tools to unlock more relevant, accurate and engaging responses.

What Is Role Priming?

Role priming is the practice of telling the AI who it is supposed to be before you ask your question. Rather than jumping straight into a request, you set a role or context for the model.

For example:

  • ❌ “Explain what a risk log is.”
  • ✅ “You are a senior project manager coaching a junior. Explain what a risk log is in plain English.”

That small change makes a huge difference. Instead of a generic explanation, the AI adopts the vocabulary, tone and level of detail suited to the role you’ve assigned.

Why Role Priming Works

AI models like ChatGPT are trained on massive amounts of text. They’re designed to respond in ways that match the patterns of human communication. By priming the model with a role, you’re essentially narrowing its focus and shaping the “voice” it will use.

This has several benefits:

  1. Improved Relevance – The AI is more likely to give you an answer that fits your audience. A lawyer’s explanation of data protection will look very different from a teacher’s explanation of the same topic.
  2. Consistent Tone – If you’re producing content for a brand, role priming can help the AI stay aligned with your style.
  3. Better Clarity – Setting a role such as “coach,” “trainer,” or “facilitator” often results in explanations that are clearer and easier to understand.
  4. Time Savings – You don’t need to keep re-explaining your context. Once the role is set, the AI will stick to it throughout the conversation.

Practical Examples of Role Priming

Here are some real-world scenarios where role priming makes a noticeable difference:

  • Marketing Copywriting
    • Without role priming: “Write a slogan for a new coffee brand.”
    • With role priming: “You are a creative copywriter at a top advertising agency. Write a slogan for a new coffee brand that targets young professionals.”
  • Training and Coaching
    • Without role priming: “Explain emotional intelligence.”
    • With role priming: “You are a leadership trainer running a workshop. Explain emotional intelligence in a way that managers can immediately apply at work.”
  • Legal Simplification
    • Without role priming: “What is GDPR?”
    • With role priming: “You are a solicitor explaining GDPR to a small business owner with no legal background. Keep it simple and practical.”

The difference in tone, style and usefulness is clear.

Using Role Priming in ChatGPT

The easiest way to use role priming is to start your prompt with “You are…”. For example:

  • “You are a careers adviser helping a student write a CV.”
  • “You are a historian explaining the Industrial Revolution to a 12-year-old.”

Once primed, ChatGPT will adopt that persona and frame its responses accordingly.

Take It Further: Create a Custom GPT

If you find yourself using the same role often, you can go one step further and create a Custom GPT.

Custom GPTs allow you to add permanent instructions so that your assistant always starts with the right role. For instance, you could create:

  • A Project Manager Mentor GPT that always explains project management tools in plain English.
  • A Marketing Copywriter GPT that always produces punchy, brand-friendly content.
  • A Soft Skills Trainer GPT that delivers workshop-ready explanations and exercises.

Instead of typing “You are…” every time, your custom version of ChatGPT will automatically respond in that role. This saves time and ensures consistency across your projects.

Why Role Priming Should Be Part of Your AI Workflow

Whether you’re using AI for writing, training, research, or customer support, role priming is a low-effort, high-impact technique. It requires no technical knowledge, works instantly and can dramatically improve the quality of your results.

By setting the right role, you can:

  • Get answers tailored to your audience.
  • Produce more consistent content.
  • Make explanations clearer and easier to apply.
  • Save time on re-explaining context.

Combine this with other prompt engineering techniques, such as temperature prompting and you’ll have much finer control over how AI supports your work.

Final Thoughts

Role priming is one of the simplest but most effective tricks when working with ChatGPT and other AI tools. By starting with “You are…” or by building a custom GPT, you can ensure your AI assistant consistently delivers responses that are more relevant, useful and aligned with your goals.

Next time you open ChatGPT, don’t just ask a question. Prime it with a role first – you’ll be surprised at the difference it makes.

Read more
temperature-prompting-post
,

Temperature Prompting in AI: How to Control Creativity in ChatGPT and Other Models

September 19, 2025

Artificial intelligence tools like ChatGPT have become everyday companions for writing, research, brainstorming, and problem-solving. But have you ever noticed how sometimes the answers feel very matter-of-fact, while other times they come across as imaginative or even a bit quirky? That difference isn’t random, it’s often tied to something called temperature prompting.

In this article, we’ll explore what temperature prompting is, how it works in AI models, and how you can use it to control the balance between predictability and creativity in your outputs.

What Is Temperature in AI?

When developers connect to AI models through their API (Application Programming Interface), they can adjust certain settings in the request. One of the most important of these settings is called Temperature.

Think of temperature as a dial:

  • A low temperature makes the model’s responses predictable and precise.
  • A high temperature makes the responses more varied, imaginative, and sometimes surprising.

It’s essentially a way of deciding how adventurous or cautious you want the AI to be when generating text.

The Temperature Scale Explained

The temperature scale usually runs from 0.0 to 2.0. Each point on that scale shifts the way the AI produces language:

  • 0.0–0.3 → Very deterministic, minimal variation, straight facts. Perfect for when you want reliable, structured responses such as technical explanations or financial data.
  • 0.4–0.6 → Balanced, some variety in phrasing, still dependable. Good for professional writing that still feels natural.
  • 0.7–1.0 → Creative, exploratory, and varied. Great for brainstorming ideas, drafting marketing copy, or storytelling.
  • Above 1.0 → Highly imaginative and unpredictable. Useful for artistic experiments but less reliable for factual tasks.

Most applications, including ChatGPT, tend to sit in the middle by default. ChatGPT’s standard behaviour is roughly equivalent to a temperature of 0.6 to 0.7, striking a balance between clarity and creativity.

Does ChatGPT Let You Set Temperature?

If you’re using ChatGPT through the website or app, you don’t have a built-in slider to change the temperature. That control is usually only available to developers who are working directly with the OpenAI API or other AI service providers.

However, there’s a workaround. Even though the setting isn’t exposed in the interface, ChatGPT still understands the concept of temperature. If you include a request like “Answer this as if the temperature were 0.2” or “Give me a response at temperature 1.0”, the model will adjust its tone and style to match the instruction.

Why Temperature Prompting Matters

Temperature prompting is more than a technical curiosity. It’s a practical way to improve your results when working with AI:

  1. Factual Accuracy: For research, legal notes, or training material, using a lower temperature ensures consistency and avoids unnecessary creativity.
  2. Balanced Content: For blog posts, LinkedIn articles, or general communication, a medium temperature makes the writing approachable without being dull.
  3. Creative Exploration: For brainstorming slogans, drafting stories, or generating ideas, a higher temperature can break you out of predictable patterns.
  4. Testing Variability: If you want multiple takes on the same idea, raising the temperature will give you a wider range of outputs to choose from.

By understanding and using this setting, you gain more control over how AI supports your work.

Practical Examples

Let’s say you want an AI to describe reusable coffee cups:

  • Temperature 0.2: “Reusable coffee cups reduce single-use waste. Choose BPA-free materials and dishwasher-safe designs.”
  • Temperature 0.7: “Reusable coffee cups cut down on waste while giving you a practical, stylish way to carry coffee. Look for BPA-free, dishwasher-safe models that fit in your car’s cup holder.”
  • Temperature 1.0: “A reusable cup is like a portable hug for your coffee, saving the planet one sip at a time. Find one that slips into your car holder, feels good in your hand, and secretly makes coffee taste better.”

Same topic, three different vibes, all thanks to temperature prompting.

How to Use Temperature Prompting in ChatGPT

Since you can’t set the parameter directly in ChatGPT, you’ll need to do this through your prompting technique. Here are some simple ways to apply it:

  • Add an instruction like “Answer with temperature 0.2” for factual and concise responses.
  • Use “Respond with temperature 0.8” for creative and varied ideas.
  • Experiment with different numbers to see how the tone changes.

It’s a simple hack, but one that can transform the way you work with AI.

Final Thoughts

Temperature prompting is a powerful but often overlooked way to get better results from AI tools like ChatGPT. By learning to control this “creativity dial,” you can decide whether you want rock-solid facts, natural-sounding balance, or wild imaginative flair.

Next time you’re crafting content, researching a topic, or looking for a spark of inspiration, try adding a temperature instruction to your prompt and notice the difference.

Have you experimented with temperature prompting yet? Give it a try and share your experience.

Read more
LinkedIn AI Content Post
,

How to Spot AI Generated Content: 10 Giveaways and How to Avoid Them

September 18, 2025

AI writing tools are everywhere, which makes it harder to tell what was written by a person and what was assembled by a model. Detection is never perfect, and none of the signs below prove anything on their own. Put a few together, though, and you start to see the pattern. Here is a practical guide you can share with your team, plus tips for keeping your own AI assisted content sounding genuinely human.

10 common signs of AI generated content

  1. Overly polished sentences
    Natural writing has bumps, shortcuts, and variety. If every sentence follows the same structure, with similar length and rhythm, it can feel machine made.
  2. Lack of personal content and anecdotes
    Humans sprinkle in lived detail: “here is what happened when I tried this,” names, dates, little surprises. AI often skirts specifics and sounds impersonal.
  3. Similar sentence transitions
    Watch for repeated bridges like “moreover,” “furthermore,” or hedges repeated in sequence: “perhaps,” “it seems,” “it could be said that,” “maybe.” Patterns like this are a tell.
  4. Light on humour and emotion
    Unless prompted carefully, AI tends to be efficient and neutral. It can read like a manual instead of a conversation.
  5. Overuse of the em dash character
    Not unique to AI, and many humans love it too, but some models lean hard on it. If every other sentence leans on an em dash, raise an eyebrow. The em dash looks like this (—)
  6. Overuse of the Oxford comma
    Again, not proof on its own. Consistency matters. If the voice, punctuation, and spelling wobble between styles, it can be a sign of templated text.
  7. Vague citations
    Phrases like “experts say” or “a recent study found” with no source link. If you cannot verify it in two clicks, treat it as decoration, not evidence.
  8. Cliché soup
    “Fast-paced world,” “unlock your potential,” “game-changer,” “revolutionise your workflow.” A couple is fine. A bowl full is not.
  9. Awkward numbers
    Hyper-precise stats such as 37.41 percent with no source, or units that change mid-post. Credible data comes with context and consistency.
  10. Recycled or generic examples
    Case studies with no names, dates, or outcomes. Vague scenarios that could apply to any industry. If it reads like a placeholder, it probably is.

Quick checks you can run in seconds

  • Quote search: Drop a distinctive sentence, in quotes, into a search engine. If nothing credible appears, be cautious.
  • Consistency scan: Look for UK vs US spelling, date formats, and punctuation styles switching mid-article.
  • Source test: Follow every claim with a number or a quote. If the link does not support the point, or there is no link at all, mark it down.
  • Read-aloud test: Read a paragraph out loud. If it sounds flat or robotic, your readers will feel it too.

How to keep AI assisted content sounding human

Using AI does not have to make your writing bland. It is about owning the process rather than letting the model steer.

  1. Set clear instructions before you start
    In ChatGPT: click your name, choose Personalisation, then Custom Instructions. Tell it what to do and what to avoid. Specify voice, audience, tone, and any banned phrases or clichés. Ask for varied sentence lengths, fewer hedges, and minimal filler words.
  2. Provide real context
    Feed it your brief, target reader, offer, and examples of your previous work. The more grounded the prompt, the more specific the output.
  3. Inject lived detail
    Add your experience, data from your work, named clients (with permission), dates, and outcomes. Replace generic lines with anecdotes and lessons learned.
  4. Cite properly
    If you include a stat, link the original source, not a repost. Ask the model to propose sources, then verify and swap in the real links yourself.
  5. Vary the shape of the copy
    Mix short punchy lines with longer reflective ones. Use lists sparingly. Add questions. Remove repeated openers like “Moreover” or “In conclusion.”
  6. Edit like a human
    Trim hedges you do not need. Replace generic verbs with concrete ones. Swap clichés for plain English. Read it aloud, then cut anything you stumble over.
  7. Decide your style rules and stick to them
    Pick UK spelling, agree your date format, and make a call on the Oxford comma. Put it in a short style guide and keep it consistent across posts.

A short checklist for editors

  • Can I point to at least two specifics that only a practitioner would know?
  • Do claims with numbers link to credible sources?
  • Does the voice match our brand style and regional spelling?
  • Are sentence lengths and transitions varied?
  • Did a human add or approve anecdotes and examples?

Final thought

No single signal proves a piece was written by a model. Humans can be formulaic. Models can be lively when guided well. The goal is not to play detective for its own sake, it is to produce content that readers trust: accurate, useful, and unmistakably yours. Use AI to draft and accelerate, then rely on your brain to shape, sharpen, and sign it off.

What do you see in content that makes you think “hmmm.. that’s AI”? Drop your tell in the comments.

Read more
Untitled design-16
,

Using Notion: How It Helps With Productivity

September 7, 2025

In the world of productivity tools, few apps have made as much noise as Notion.

From startups to global businesses and from students to freelancers, millions of people are now using Notion to organise their work and personal lives. But is it just another note-taking app – or is it something bigger? Let’s take a closer look at how Notion actually boosts productivity.

What Is Notion?

At its simplest, Notion is a workspace app where you can:

  • Write and organise notes.
  • Manage tasks and to-do lists.
  • Create project dashboards.
  • Build databases, wikis and knowledge hubs.

It’s all drag-and-drop, customisable and shareable. That flexibility is what makes Notion stand out compared to traditional task managers or document tools.

How Notion Helps With Productivity

Notion can improve productivity in three key ways:

  1. All-in-one workspace – Instead of juggling separate apps for notes, tasks, calendars, and documents, you bring them into a single hub. Less switching = less friction.
  2. Custom workflows – Whether you want a Kanban board for project tracking, a reading list, or a personal CRM, you can shape Notion around your workflow rather than forcing your workflow into a rigid tool.
  3. Collaboration – Teams can share pages, comment, and update content in real time. This makes it easier to manage projects, keep documentation up to date, and cut down on endless email chains.
  4. Knowledge retention – Instead of files buried in email or scattered across drives, information stays accessible, searchable and organised.

Lots of People Don’t Get It – Here’s What It Really Does

Scroll through social media and you’ll see people showing off elaborate Notion templates – aesthetic dashboards, mood trackers and over-engineered task lists. That’s why many newcomers download Notion and think “What’s the point?”

Here’s the reality: Notion isn’t about pretty templates – it’s about building a system that works for you.

  • It’s not just another note-taking app – it’s a database in disguise.
  • It’s not just for personal use – it can run as your team’s project management tool.
  • It’s not just a digital diary – it can become a company knowledge base.

In other words, Notion is a flexible framework. You decide whether to use it as a lightweight to-do list or as the backbone of a complex business system.

Using Notion and AI Together

One of the biggest shifts in productivity is the rise of AI-powered tools, and Notion has embraced this with its own built-in Notion AI features. This makes your workspace not just a place to store information, but a tool that can actively help you think, write and plan.

What Notion AI Can Do

  • Summarise notes and documents – Perfect for meetings or long research articles, especially using the auto-meeting notes feature for Microsoft Teams.
  • Generate first drafts – From emails to blog posts, AI can give you a starting point directly inside Notion.
  • Brainstorm ideas – Use prompts to generate project names, creative angles, or new strategies.
  • Rewrite or improve text – Polishing rough notes into clear, professional writing.
  • Answer questions from your workspace – Instead of hunting through pages, ask AI to pull out what matters.
  • Your email inbox – Notion Mail ties your email into the Notion eco-system proving even more power and context
  • Link notes together – provide context and create maps of notes by adding connections and links to make things even more searchable

Combining AI with Your Notion Setup

  • For personal productivity: Let AI sort your to-do list by priority or suggest the next best action.
  • For team collaboration: Use AI to summarise project updates so everyone is aligned without needing another meeting.
  • For learning and development: Store training content in Notion, then use AI to quiz learners or provide summaries for revision.

By blending Notion’s flexible structure with AI’s generative power, you go from simply organising your work to actually accelerating it.

Practical Examples of Using Notion

Here are some ways different people use Notion to save time and stay organised:

  • Students: Create class notes, revision schedules and reading lists in one place.
  • Freelancers: Manage client projects, proposals, invoices and content calendars.
  • Businesses: Build company wikis, onboarding guides, project trackers and meeting notes.
  • Personal life: Track goals, habits, and personal projects like fitness or budgeting.

Why Notion Is Worth Trying

The beauty of Notion lies in its balance of structure and flexibility. Unlike traditional productivity apps that box you into one way of working, Notion adapts to you. That makes it incredibly powerful for anyone who wants to:

  • Reduce app overload.
  • Create personalised systems.
  • Keep everything – notes, tasks, projects and email – in one connected space.

Final Thoughts

Notion can feel overwhelming at first, but once you understand its true purpose, it becomes a game-changer for productivity. Whether you’re a student, a coach, a business leader, or just someone looking to organise personal projects, Notion helps you build a workspace that finally matches the way you think and work.

Ready to see what Notion can do? Start simple – create one workspace for tasks or notes and expand it as you go. Before long, you’ll see why it’s one of the most talked-about productivity tools today.

Read more