I have been using AI long enough to be impressed by its speed and cautious about its judgment. For quick sketches, comps, infographics, and data visuals, the volume is remarkable. You can explore more directions in less time than ever before. The real skill is knowing what to reject. At first glance, a lot of AI-generated work looks polished. Then you look closer. The hierarchy is weak. The logic breaks down. The brand cues miss the mark. The chart looks finished, while the point remains unclear. The layout looks attractive, while the problem remains unsolved. That is where experience shows up. In knowing whether the work functions. AI can increase the number of directions we explore. That part is useful. Volume does not replace judgment. It makes judgment more important. AI can help generate the work. Judgment decides whether the work deserves to exist. #CreativeDirection #DesignThinking

Best AI design tools in 2026 - these are the 7 AI tools I use to run my design studio every single day. Not demos, not sponsored picks - real tools that ship real client work.

I tested over 50 AI design tools and narrowed it down to 7 that cover every part of the web design workflow: ideation, layout, assets, visuals, design, building, and the one tool that connects everything together. Each tool earned its spot by surviving real client projects at my studio, Klime.

My AI workflow I use to 10x my design work:

1. Inktrail.ai - For brainstorming, understanding PRDs, conducting market and competitor research and creating user flows

2. variant.com - To curate a moodboard of design directions and UI flows

3. figma.com/make - The HTML and CSS code that aligns to my need from the moodboard and curate a complete prototyping

4. figma.com - For creating the design artifacts, aligning with brand standards and design system

Inktrail.ai - To write the UX copies for the designs

Worthy of mention; windsurf.com - Creats a design.md file and implement the UI on frontend level.

This workflow cuts my design time from days to hours and still maintain the same level of quality.

Designers should perform human oversight and not manual work.

What’s your own process?

Repost to help a designer from your network.

These tools are powerful, but each one only works well when you know exactly what job to give it.

I’ve been using AI tools as a core part of my design workflow. Here’s what actually works and what doesn’t.

ChatGPT: My content partner. Great for UI copy, microcopy variations, and translating engineer-speak into user-speak.

Figma Make: Good at generating initial wireframes and scaffolding a starting flow. The frustrations: credit limits are brutal and burn fast when iterating (which is… the entire point of design). It struggles with large context, you need to feed it bite-sized chunks. No plan mode like VS Code, so you can’t orchestrate a multi-screen flow strategically. For these reasons, it’s much easier to go from Figma Make to VS Code than the other direction.

Figma: Still the source of truth. After Make generates a starting point, I always move into Figma to manually refine. AI-generated layouts need a human hand- spacing, hierarchy, consistency.

VS Code + Claude: Where designs come to life. Like Figma Make, works best with focused prompts, not massive context dumps. But the speed is transformative. Things that used to require a developer friend and a weekend now take an afternoon.

Google Stitch: Strong at generating polished visual UI and great for design system exploration. But the content and UX structure is consistently weak- page hierarchy, flow logic, information architecture all need significant rework. Better for visual inspiration than building experiences.

Updated stack as a designer using ai to streamline my workflows; for those that find it useful.

AI tech stack: Claude (research, strategy assistant), Claude Code (coding), Figma Make (prototyping), v0 (structural explorations), Vercel (hosting), Nano Banano Pro (image gen), Notion (second brain), Shadcn & Tailwind (styling)

Let’s talk AI tools… What’s working and where it still falls short

I use it to move faster on the parts that used to eat time without adding much creative value.

Mockups • Instead of spending an hour hunting for the right shot, I generate one. Specific context, right proportions, on-brand. Done in minutes.

Illustrations and icons • When budget doesn’t stretch to a custom illustrator, AI gives me a starting point I can direct.

Photoshop AI editing • Generative fill, extending a shot that’s almost right — quietly one of the most useful tools in my daily edit.

Copy placeholder • When good copy isn’t ready, AI holds the layout together without me staring at Lorem Ipsum.

Now the honest part.

Visuals fall apart when prompts get complex — the more elements you add, the more it starts dropping details or adding things you never asked for.

It writes in a way that isn’t you. Perfect grammar, clean structure, sounds like nobody in particular.

And it won’t tell you when something isn’t working. No second opinion unless you ask. As a solo designer, that gap is real.

It works best when you bring the direction, the taste and the critical eye.

#AITools #CreativeProcess #DigitalDesign

How I design mobile apps using AI ( in under 2 hours )

Most People spend weeks on this.

Here's my exact workflow:

1/ Inspiration hunting

Skip Google.

Go straight to Pinterest Most people sleep on it but it's the BEST source for mobile design inspo

Mobbin for real app patterns and Dribbble for visual eye candy

Screenshot everything that matches your theme

2/ Design system with Claude

Take all your references and start a conversation Talk through fonts, spacing, padding, colour schemes Get your entire design language locked before touching any tool

This alone saves 5+ hours of back and forth later

3/ User flow mapping

What screens do you need?

What questions are you asking the user and HOW are you asking them?

Map the full content flow inside Claude first If the flow makes sense in text, it makes sense on screen

4/ Build in Framer or Figma

Connect Claude to your design tool Start pulling screens together using your locked design system No guessing. Every decision already made in step 2

5/ Asset generation with Higgsfield
Custom visuals, illustrations, hero assets No stock photos.

No generic AI slop Assets that actually match the vibe you built

Old way: 2 weeks of revisions and Figma rabbit holes
New way: Full mobile app design in one sitting

The tools are free. The workflow is the edge.

Social media moves fast. One day, you post a design that performs well, and the next day, the algorithm wants something completely different. If you run a blog, manage a brand, or promote affiliate products, you already know how much time design work can take.

Not long ago, creating social media graphics meant opening Photoshop, searching for stock images, adjusting layers, and tweaking fonts for hours. Now things are different. AI tools have made the process faster, simpler, and honestly more fun.

These days, I can create clean, professional social media designs in about 10 minutes using AI tools. No complicated design skills required. If you’ve ever wondered how people post polished graphics consistently, this article will show you exactly how the process works.

...

Creative projects often reveal more about a process than we expect.
Recently, while designing a poster for my daughter’s student film (a pub-based tale of transatlantic love tension in 1940s wartime Britain!) I decided to pay close attention to what actually happened when I invited AI tools into the workflow.

I trained as a graphic designer many years ago (art college in nineteen hundred and something something… ahem!). Poster design isn’t something I do much of these days, but this felt like a fun opportunity to revisit the craft while seeing how these new tools behaved inside a real creative project.

The results were...quite interesting!
And the interesting part wasn’t the speed, but other stuff - like how much judgement, knowledge and taste were still required after getting back ‘instant’ results. How converge and diverge really matters, and how slowing down and 'incubating' is still very much a thing.

You'll see that some of the AI mock-ups were genuinely helpful, others completely off the mark, though even the misses occasionally suggested something I could build on.

Instead of writing a “how-to”, I decided to document the process: the good bits, the frustrating bits and the slightly surreal experience of collaborating with machines that can create images but don’t actually understand anything.

If you’re after a guide to prompting or a comparison of tools, I’m gonna be honest and unapologetic here - look elsewhere!

I’m no ‘AI expert’ (plenty of them around it seems these days!) but I experiment and noodle about - I'm a creative person playing with the tools available and reflecting on what that achieves and what it actually feels like.

All that said...you might find it interesting if you are:
• a designer wondering what all this means for your craft
• someone curious about where AI might fit into a creative process
• a leader thinking about how these tools will affect the people you work with
• or just someone trying to make sense of the hype without either existential panic or blind optimism

I certainly don’t have definitive answers. But I do think there’s value in exploring all of this with curiosity, and paying attention to what actually happens when these tools enter the creative process.

The more we experiment, notice and reflect, the more we can begin to understand how to work with them. I’m convinced that if we can do that, we may well feel a little less intimidated by them.

So, if you are curious...
Read all about it 👉 https://lnkd.in/eknT-mEn

And if you like it, please feel free to subscribe!

In the past few months I've replaced or automated a lot of the work that used to sit around my design process - managing projects, writing briefs, searching for prompts I made a while back, building interactions I could picture but couldn't code.

Here are the tools that actually made that happen and how I use them to keep track & automate everything boring in my process.



Claude + Midjourney

Midjourney has been a cornerstone for a lot of what I've been doing in the past year or so. The speed of style exploration is hard to match, and once I'm locked in a direction the consistency I can get out of it is something clients are actually happy with. Lately I've had a couple of people reach out specifically wanting a visual style/system they could use for their own content.

What changed how I use it was bringing Claude into the process on the prompt side. I learned early to store favourite prompts, profiles, images and styles somewhere, but they'd end up spread across notes, different Notion pages, message threads - everywhere. Now they live in Notion in a structured way, and since Claude already has access to that, I can just ask for a style I built months ago instead of searching for it.

This also works for helping me put together prompts and styles in batches for clients. Instead of handing someone a finished image, I can give them a repeatable structure - a set of parameters and style descriptors that means every image they generate looks on-brand, even if they've never written a Midjourney prompt before. It removes a lot of back and forth and gives clients something useful as an additional deliverable.



A custom Gem agent

Workshop is probably my favourite Framer feature of them all - being able to create complex code components with simple prompts is a huge deal and it handles most of what I need day to day.

But I've always loved WebGL shaders, advanced scroll interactions, infinite galleries, or anything with more complex logic than what's native in Framer. For more complex and detailed prompts I found Workshop just doesn't do well and that's where I switch to Gemini with a custom Gem I put together.

The Gem is trained on Framer's best practices for code components, so it already understands the structure, how property controls need to be set up, and how to write things so that whoever uses the component - myself, a template user or a client - doesn't need to know anything about the code. They just configure it through the UI like any other component.

This custom Gem really opened a door for me that always felt out of reach before, so if you're using Framer I'd definitely recommend it!



Claude + Notion

I have separate Notion pages for each Framer template I'm working on, client projects, and my own website redesign. I use them as simple project management tool where I cross off tasks to myself about where I'm at, what I want to come back to and just keeping track of things.

My problem with Notion has always been the friction of having to actually write and update things. I've been documenting my process because I know it's important, yet it's always been the most tedious thing to do.

The Claude connection to Notion fixed that. Now I just write to Claude - what I finished for the day, what I'm thinking, what I need to follow up on - and it updates the relevant pages for me. Took me less than an hour to set up and I've used Notion every day since.

For client projects it's been helpful for keeping short notes on where things stand. I also store client briefs in there and document my process on current Framer template work, which makes it easier to reflect on what worked, where and when I was slowed by something and what didn't work at all. It all ends up being useful source material for content to post on socials, too.



Flora Fauna

Midjourney is still where I do most of my visual exploration, but Flora Fauna has become the tool I reach for when I want to stay in one place and iterate quickly.

The node-based system is the main reason. Instead of rewriting long prompts from scratch, I'm working visually, branching off from generations I like, adjusting and building on what's already working. Having everything in one place rather than scattered across different chats or folders on my computer makes a real difference when I'm trying to keep a project coherent.

The video generation is worth a mention as well. Mostly useful for when a client project needs some motion or I want to push something further, being able to switch to a better video model from the same workspace - without starting over somewhere else - saves some time and nerves.



The point of all this

The stack will keep changing as these tools evolve, and I'm also aiming to build more custom setups and even small apps for myself based on specific use cases and workflows I haven't fully solved yet.

But the idea behind all of my AI use remains the same - I want to automate all of the mundane, repetitive and boring work, so I can give more time and attention to the creative work that I love doing myself!