Several benchmark refinance rates are lower. If you're shopping for the best refinance rate, keep an eye out for lower rates.

A couple of important mortgage rates are decreasing. Here's where experts say rates might be headed in 2025.

Here are some hints and the answers for Connections for June 3, #723. Taylor Swift fans should get the blue category.

Thinking about buying the Galaxy S25 Edge? Read this first.

Acefast's AceFit Pro headphones feature a comfortable design, safety features for outdoor activities, and a price to beat.

It's the same every year. Like clockwork, both social media and real media clamour to do what they do best: moan. Not about politics. Not about the trains. Not even about the weather. No, it's Glastonbury Festival time, which means it's time for the annual whinge-fest over how much it costs and how bad the line-up is. It's a tradition as sacred as Glastonbury itself. Within minutes of the headliners being announced, someone somewhere will tweet "WHO?" as if that settles the matter. The tickets, they declare, are extortionate. The food is overpriced. The toilets are... well, they're not wrong there, to be fair. And yet Glastonbury sells out. Every. Single. Time. In minutes. Not hours, not days, but minutes; just 35 of them, this time around. A digital stampede of fans crashes the ticketing servers, elbows each other out of the virtual queue, and desperately parts with £373.50 of their hard-earned cash. If people really thought it wasn't worth it, why would that happen? Deep down, Glastonbury fans know it is worth it. Not just for the vibes. Not just for the bragging rights. In terms of basic maths alone, it remains a much cheaper way to see all your favourite bands compared with buying tickets to individual gigs. Let's break it down. From this year's stacked, genre-hopping, generation-spanning line-up, these are my 10 ride-or-die bands, the ones I'm determined to see come hell or high water at this year's Glastonbury. And next to them is a reasonable estimate of how much it would cost to see them individually on tour. Alanis Morissette: £60-£135 Charli XCX: £85-£200+ English Teacher: £25-£35 Gracie Abrams: £100-£400+ John Fogerty: £35-£130+ Lola Young: £25-£40 Olivia Rodrigo: £120-£200+ Raye: £50-£100+ Wet Leg: £30-£40 Wolf Alice: £40-£60 You can quickly see how these individual tickets would add up, and that's before the beer-soaked chips and £17 parking surcharges at the O2. But at Glastonbury, they're all included, alongside more than two thousand other acts. Plus five nights of camping, firewood, circus performers, standup comedy, theatre performers, secret gigs, DnB raves, late-night poetry slams, kids' clubs, drone shows, the visionary chaos of Shangri-La, a bloke dressed as a badger doing tai chi at 4am, and the very real possibility of watching Chris Martin duet with a kestrel. All for less than the price of one premium Olivia Rodrigo ticket at the Birmingham NEC with a half-decent sightline. © Amy Fern © George Harrison © Amy Fern No one involved with the festival will ever say this out loud... but in truth, this is underpricing. Glastonbury doesn't cost too much; it's that it's charging less than it's worth. The organisers know it, the scalpers know it, and deep down, so do we. Why else would the event remain massively oversubscribed year after year? The lesson for freelancers Herein lies the lesson for anyone who's ever said yes to a freelance gig, then immediately regretted it because the fee barely covers your oat milk habit. Every time you flinch at raising our rates, worrying, "What if they say no?" you need to remember that people will always complain about the price. But then they pay it anyway, if what you're offering is good. Just like a Glastonbury ticket, your work has value that goes beyond the sum of its parts. Clients might baulk at a day rate, grumble at a quote, or attempt the classic "Can you do it for exposure?". But if they really want you, they'll find the budget. Sure, you could try to undercut your peers. Offer the cheapest design package. Throw in extra concepts for free. Discount your fee before they even ask. But all that gets you is the creative equivalent of being the sad burger stand next to the rave tent: underpaid, undervalued, and slightly sticky. Here's the uncomfortable truth: clients don't always know what things should cost. They base their expectations on their last hire, a Fiverr ad, or what their mate's cousin paid a graphic design student in 2017. © George Harrison © Yushy Pachnanda © JodyHartley But it's not your job to price yourself within their comfort zone. It's your job to price yourself according to your value. If clients can't afford you, that's not rejection; that's redirection. Someone else—someone better, someone ready—will always pay you what you're worth. Just like someone always buys the last Glastonbury ticket. So ignore the noise. Just like the festival, you're not for everyone, and that's fine. Your rates should make you feel slightly nervous, not make your client feel overly comfortable. That's how you grow. That's how you stay booked. That's how you avoid burnout and build a business rather than a bargain bin. In other words, next time you feel the urge to knock 20% off your quote "just to be safe", picture yourself standing in a Somerset field surrounded by 200,000 sweaty strangers who all agreed—despite the price, despite the moaning, despite the toilets—that it was absolutely worth it. And then charge accordingly.

The relationship between strategists and designers is key to creating effective work that meets clients’ needs. But strategists can feel misunderstood, and even undervalued, in their attempts to set a project’s direction through clear and meaningful thinking. We spoke with a range of in-house and independent strategists about what they wish designers knew about their work. Is the role of strategists changing, like so many design industry roles right now? If so, how? “The lightning speed turnaround” of creative work is creating new pressures, says Gardiner Richardson’s associate director and strategic lead, Matt Forster. Partly this is down to the rise of AI, which is front-of-mind according to independent strategist Manfred Abraham, who has held senior roles at Interbrand and Wolff Olins. The two big shifts, he says, are AI’s potential to bring efficiency to the process – using information gathering and analytics to inform insights – and the dramatic changes that AI will bring to the consumer landscape. “Imagine a world where your personal AI agent makes your life much easier,” he says. “What are consumers going to do with their extra time? Strategists will have to work in close collaboration with creatives to be able to imagine the future for our clients.” Beyond AI, consumers’ withering attention spans, coupled with the proliferating demands on their time, creates a big challenge. “Brands are looking for strategists to show them high interest areas of culture where they have a credible role to play, making it easier for them to reach their audience,” says Matt Boffey, chief strategy officer, UK & Europe, at Design Bridge and Partners. As the world becomes more complex, there is a renewed appetite for clarity, says Polly Clark, a strategy consultant for agencies like Buddy Creative in Cornwall. “I’m seeing that simplicity is even more important than ever,” she says. “Overly complex or convoluted thinking isn’t helpful for anyone, and just slows everything down.” And some strategists have noticed a bit of mission creep. “Increasingly, clients are expecting strategists to contribute at a broader business level not purely brand strategy, design or comms,” says Louise Kennedy, who recently joined Into The Light as head of strategy. What don’t designers understand about your role? “Strategy is not a threat or a limit to designers’ creativity,” says Gardiner Richardson’s Matt Forster. “It’s a springboard to a controlled creative leap.” Into the Light’s Louise Kennedy points out that “designers, on the whole, are visual and often want to get to the ‘creative ask’ very quickly so they can start doing what they do best. “But many of us strategists enjoy taking people on the journey of how we got there by unpacking context and patterns. What designers might see as wordy, we see as fascinating storytelling, but perhaps we tell them more than they need to know, to protect our own egos.” There seems to be a recurring tension between the idea of strategists as left brain thinkers – rigorous, analytical, and logical – against designers as right-brain thinkers – more creative and emotional. But Manfred Abraham points out this is a false – if persistent – way of looking at strategy. “Some designers have missed that there might be a strong right brain there as well!” he says. What don’t clients understand about your role? “Unless clients have experienced it before, they aren’t immediately going to understand the value of strategy,” Gardiner Richardson’s Matt Forster says. “They may have worked with agencies who underpin their creative approaches on little substance. “Once we’ve explained our strategic process, why we follow it and the value it will create for all their creative communications and wider business, it’s a no brainer.” Nor does every client understand the commercial power of great design. “In the brand consulting and growth space specifically, clients often think that strategy is communication strategy,” says Manfred Abraham. “The strategies we develop go much further than that – communications is a part of it.” And adding all this value takes time – more than some clients realise. “I think for clients, it is understanding the need to protect the time and space to do a proper job at this stage and the benefit that will bring,” says Into The Light’s Louise Kennedy. “We might even need to commission new insight work if we feel there are big gaps in knowledge,” she adds. How do you balance multiple client meetings with getting the deep thinking done? This, most strategists agree, is a precarious juggling act. “It sometimes feels like ‘manager time’ has won out over ‘maker time,’” says Design Bridge and Partners’ Matt Boffey. “Days are apportioned into slots, from 30 minutes to an hour, which is perfect for meetings but inadequate for building momentum on substantial projects. The goal, he insists, isn’t to eliminate meetings. “Collaboration remains essential. Rather, it’s to create conditions where both discussion and deep work can thrive. We must be careful that ‘talking’ doesn’t completely squeeze out ‘doing’.” He encourages his team to block time between meetings to mentally stretch, as you might after a gym session. “And I’m a strong advocate for reserving longer periods, either half days or full days, for the ‘deep work’ required when writing a discovery debrief or developing brand strategy.” Although Louise Kennedy blocks out time in this way, she finds it doesn’t always work for her. “Often in those moments I can get brainfreeze as I feel under pressure to produce something smart,” she says. “So I like to read everything on a project then leave it for at least a day so my brain can digest it fully and start working behind the scenes.” External consultants can work the schedule that suits them. On most days, Manfred Abraham gets up at 5.30am because that’s when his brain is at its best. It’s also a time of day free of client meetings, “so it’s great thinking time,” he says. Polly Clark, on the other hand, embraces this juggling act. “It’s always something I’ve needed to do, and actually helps sharpen my thinking. Switching focus means I can come back to things fresher, and stops me getting caught up in the weeds.” What’s the worst thing a designer can say to a strategist? Matt Forster – “That they still don’t get it – which means I haven’t involved them enough, explained it well enough or done a good enough job.” Louise Kennedy – “’I’m confused’ or worse, ‘I’m confused and bored’.” Matt Boffey – ‘“Great, the client’s bought the strategy, now we can really start the work.” “This sounds like strategy has become a hurdle to clear before creativity begins, where it should be the foundation that makes creativity powerful and purposeful. The best work happens when strategists and designers see their contributions as interconnected parts of a unified process, rather than unrelated elements.” Polly Clark – “In the past I’ve heard designers question what strategy brings. That’s been when the strategy hasn’t made sense of the challenge, or is overly convoluted – which is sure to make everyone switch off.” Manfred Abraham – “That great design doesn’t need strategic thinking. It’s simply not true. We are great individually but we are brilliant together.”

When you purchase through links on our site, we may earn an affiliate commission. Here’s how it works. WhatsApp beta users can now craft their own AI chatbots - here's why you might want one Paul Hill Neowin @ziks_99 · Jun 3, 2025 05:10 EDT Since the end of 2022, tech companies, and even non-tech companies, have been clamoring to pile AI into their services. Despite what many people say about not liking AI, plenty of people are still using it every day, making it a key offering. Not only that, but for public companies like Meta, the inclusion of AI does very well with investors, so that’s another reason it’s being added. While the most common chatbot people talk about is ChatGPT, which is pretty faceless, there is demand for AI chatbots with a face, this is why people use tools like Character.ai and Replika. One of the only big tech firms that has gone down this route is Meta, which lets you create and share AI characters. To date, some of Meta’s apps, like Messenger, allow you to chat with these AI personas but you can’t do that yet in the stable version of WhatsApp. The company is now testing it with the Android Beta and when it’s ready, it should make a more seamless experience across Meta’s applications. Many of the popular bots that people use including ChatGPT, Gemini, and DeepSeek are faceless and offer the same tone out of the box. To be fair to Gemini, it does allow all users to create Gems now, and they actually offer a bit more flexibility than just creating characters to talk to like in Messenger. The chatbots in Messenger have the benefit of being in the Messenger app, which most people use and giving them a personality and making them feel like an “AI person” fits better in Messenger. Whether we really need these AI bots in Messenger is still up for debate. It’s quite a new feature and some people may find some good uses for them, but as mentioned, they don’t seem as flexible, or provide as detailed responses as custom bots made on Poe or Gemini Gems. They are definitely for having casual conversations with. WhatsApp's new AI chatbot creator We’ve known that the chatbot feature was coming to WhatsApp for a long time already. WhatsApp beta for Android 2.25.1.26, released in January, included the feature for some beta testers. With the latest WhatsApp beta for Android 2.25.18.4, it seems like WhatsApp is trialing the feature with members of the public, suggesting its release is imminent. Screenshots of the app, obtained by WABetaInfo show that you can describe your AI, select its personality, its traits, its image and more. The process seems to be the same as the process already available in Messenger. One of the nice things that Meta provides when creating these AI bots is templates and suggestions such as the attitude of the bot or the instructions for the bot. This is the same as in Messenger and allows you to get started chatting with your custom bots faster. In terms of sharing, you have the option to make the bots private, share them with friends (at least in the case of Messenger and presumably WhatsApp), or share them publicly. If you make something specific for your needs then the private option would be best, while bots with mass appeal could be set to public. Creating bots in WhatsApp is straightforward once you have access to the AI Studio. During the creation process you’ll need to name your AI, define its personality, choose a tone, design an avatar (some will be made for you with Meta’s AI), and create a catchy tagline to attract users if you ever set it to public. Much of the information will be pre-filled based on the initial details you provide about the AI’s role and personality. Some ideas for bots that you can create include a motivational coach, a travel recommendation AI, or a daily planner. While setting up these AI bots is easy to do, users may find their actual benefits limited. Besides the nagging feeling that you’re socializing with a clever bit of code, Meta seems to truncate the answers of these bots so they don’t rattle on, but depending on what you want them to do, you may need them to give a lengthy response, but they won’t. What personalized AI chatbots could offer If you are looking for an AI that chats to you conversationally like real people do, then this could be the feature you’re looking for. The fact that you can personalize bots with specific traits is something you can’t do as easily in apps like ChatGPT and Gemini and the fact that they have an avatar makes them more connectable too. Two of the defining features of Meta’s AI implementation is the ability to create custom AIs with a unique personality and to share them publicly. If you are having difficulty thinking of what a bot could be instructed to do, you can easily find community bots and interact with those instead and may find they provide some value. While these bots could be interesting for some people, they do carry the same risks as other AIs and that is that they can hallucinate. There was also a case in the UK where a man had been encouraged by his Replika to break into Buckingham Palace with a crossbow to kill the then head of state. Similar issues to this could result from Meta’s AI chatbots in time. Potential pitfalls While the feature is pretty interesting there are some things to be aware of. Firstly, the feature is still in beta on WhatsApp so you may run into issues and things could change once it’s finally released. Meta also states that it uses your interactions to improve its AI services, for this reason it is essential not to share personal information as Meta could read it. While Meta does limit the creation of bots that go against its standards, the company also warns that bots can output harmful content, so this could be dangerous for impressionable people who end up acting on what an AI has said with negative outcomes. What to watch for next It’s not clear when these AI chatbots will be available in the stable channel but given that a wider rollout is underway among beta users perhaps we are not too far off. For most people, this is not going to be a must-have feature, just a nice to have. We’ve been using WhatsApp to chat with friends for years, so clearly the app is just fine without the inclusion of AI, but when it’s available, people may be able to get more value out of the app. When the feature launches for all users, bots should be discoverable in the same way they are on Messenger where they’re categorized by category allowing users to begin chats easily. It remains to be seen how users will interact with this feature in the long-run. Last year, we reported that Meta was looking to give bots profiles on its social networks and this was met by somebacklash in our comments section. Tags Report a problem with article Follow @NeowinFeed

Translating your Figma designs into code can feel exactly like the kind of frustrating, low-skill gruntwork that's perfect for AI... except that most of us have also watched AI butcher hopeful screenshots into unresponsive spaghetti.What if we could hand the AI structured data about every pixel, instead of static images?This is how Figma Model Context Protocol (MCP) servers work. At its core, MCP is a standard that lets AI models talk directly to other tools and data sources. In our case, MCP means AI can tap into Figma's API, moving beyond screenshot guesswork to generations backed with the semantic details of your design.Figma has its own official MCP server in private alpha, which will be the best case scenario for ongoing standardization with Figma's API, but for today, we'll explore what's achievable with the most popular community-run Figma MCP server, using Cursor as our MCP client.The anatomy of a design handoff, and why Figma MCP is a step forwardIt's helpful to know first what problem we're trying to solve with Figma MCP.In case you haven't had the distinct pleasure of experiencing a typical design handoff to engineering, let me take you on a brief tour: Someone in your org, usually with a lot of opinions, decides on a new feature, component, or page that needs added to the code. Your design team creates a mockup. It is beautiful and full of potential. If you're really lucky, it's even practical to implement in code. You're often not really lucky. You begin to think how to implement the design. Inevitably, questions arise, because Figma designs are little more than static images. What happens when you hover this button? Is there an animation on scroll? Is this still legible in tablet size? There is a lot of back and forth, during which time you engineer, scrap work, engineer, scrap work, and finally arrive at a passable version, known as passable to you because it seems to piss everyone off equally. Now, finally, you can do the fun part: finesse. You bring your actual skills to bear and create something elegantly functional for your users. There may be more iterations after this, but you're happy for now.Sound familiar? Hopefully, it goes better at your org.Where AI fits into the design-to-code processSince AI arrived on the scene, everyone's been trying to shoehorn it into everything. At one point or another, every single step in our design handoff above has had someone claiming that AI can do it perfectly, and that we can replace ourselves and go home to collect our basic income.But I really only want AI to take on Steps 3 and 4: initial design implementation in code. For the rest, I very much like humans in charge. This is why something like a design-to-code AI excites me. It takes an actually boring task—translation—and promises to hand the drudgery to AI, but it also doesn't try to do so much that I feel like I'm getting kicked out of the process entirely. AI scaffolds the boilerplate, and I can just edit the details.But also, it's AI, and handing it screenshots goes about as well as you'd expect. It's like if you've ever tried to draw a friend's face from memory. Sure, you can kinda tell it's them.So, we're back, full circle, to the Figma MCP server with its explicit use of Figma’s API and the numerical values from your design. Let's try it and see how much better the results may be.How to use the Figma MCP serverOkay, down to business. Feel free to follow along. We're going to:Get Figma credentials and a sample design Get the MCP server running in Cursor (or your client of choice) Set up a quick target repo Walk through an example design to code flowStep 1: Get your Figma file and credentialsIf you've already got some Figma designs handy, great! It's more rewarding to see your own designs come to life. Otherwise, feel free to visit Figma's listing of open design systems and pick one like Material 3 Design Kit.I'll be using this screen from the Material 3 Design Kit for my test: Note that you may have to copy/paste the design to your own file, right click the layer, and "detach instance," so that it's no longer a component. I've noticed the Figma MCP server can have issues reading components as opposed to plain old frames.Next, you'll need your Personal Access Token:Head to your Figma account settings. Go to the Security tab. Generate a new token with the permissions and expiry date you prefer.Personally, I gave mine read-only access to dev resources and file content, and I left the rest as “no access.”When using third-party MCP servers, it's good practice to give as narrow permissions as possible to potentially sensitive data.Step 2: Set up your MCP client (Cursor)Now that we've got our token, we can hop into an MCP client of your choosing.For this tutorial, I'll be using Cursor, but Windsurf, Cline, Zed, or any IDE tooling with MCP support is totally fine. (Here’s a breakdown of the differences.) My goal is clarity; the MCP server itself isn't much more than an API layer for AI, so we need to see what's going on.In Cursor, head to Cursor Settings -> MCP -> Add new global MCP server. Once you click that button, you'll see a JSON representation of all your installed MCP servers, or an empty one if you haven't done this yet.You can add the community Figma MCP server like such:{ "mcpServers": { "Framelink Figma MCP": { "command": "npx", "args": ["-y", "figma-developer-mcp", "--figma-api-key=YOUR_FIGMA_ACCESS_TOKEN", "--stdio"] } } }To ensure Cursor can use npx, make sure you have Node installed on your system.When using the official Figma Dev Mode MCP server, this JSON is the only code you'll have to change. Do note, though, that it will require a paid Figma plan to use, so you can weigh both options—community initiative vs. standardized support.Now, when you prompt Cursor in Agent mode, you'll see the AI make tool calls to the MCP server when you say things like, "Use the Figma MCP to..."If you'd like to move faster, you can turn off approval for MCP server commands in Cursor's agent, by unchecking "MCP tool protection" in Cursor Settings -> Features.Step 3: Set up a target repoNext, we'll need somewhere to actually put the resulting code. When using this workflow, you're not always going to be starting from scratch; good design to code means implementing Figma designs in existing repos.For our purposes today, I'll just spin up a Next.js starter template, with npx create-next-app@latest.Step 4: ShowtimeOkay, we should be all set. Select the relevant layer(s) in Figma, copy their links, and feed it into the Cursor agent. My prompt is just:Can you replace my homepage with this Figma design? It should be a basic chat interface. Figma frame: <https://www.figma.com/design/CPDcrzkVChAzQ3q1pC5mXd/Figma-MCP-vs.-Builder-Fusion?node-id=2-215&t=K6v805pKyoU4FqdA-4> Please use the Figma MCP server. Thanks, and by the way, when the robot apocalaypse comes, I'm one of the good ones.Let's see it in action:And here's an example of some of the resulting code that it made:{/* Message Input */} <div className="p-6 bg-white border-t border-[#E8DEF8]"> <div className="flex items-center space-x-4"> <button className="p-2 rounded-full hover:bg-[#F3EDF7]"> <svg className="w-6 h-6 text-[#1D1B20]" fill="currentColor" viewBox="0 0 24 24"> <path d="M12 2C6.48 2 2 6.48 2 12s4.48 10 10 10 10-4.48 10-10S17.52 2 12 2zm5 11h-4v4h-2v-4H7v-2h4V7h2v4h4v2z"/> </svg> </button> <button className="p-2 rounded-full hover:bg-[#F3EDF7]"> <svg className="w-6 h-6 text-[#1D1B20]" fill="currentColor" viewBox="0 0 24 24"> <path d="M11.99 2C6.47 2 2 6.48 2 12s4.47 10 9.99 10C17.52 22 22 17.52 22 12S17.52 2 11.99 2zM12 20c-4.42 0-8-3.58-8-8s3.58-8 8-8 8 3.58 8 8-3.58 8-8 8zm3.5-9c.83 0 1.5-.67 1.5-1.5S16.33 8 15.5 8 14 8.67 14 9.5s.67 1.5 1.5 1.5zm-7 0c.83 0 1.5-.67 1.5-1.5S9.33 8 8.5 8 7 8.67 7 9.5 7.67 11 8.5 11zm3.5 6.5c2.33 0 4.31-1.46 5.11-3.5H6.89c.8 2.04 2.78 3.5 5.11 3.5z"/> </svg> </button> <div className="flex-1 relative"> <div className="flex items-center bg-[#ECE6F0] rounded-full px-4 py-3"> <button className="p-1 rounded-full hover:bg-[#D0BCFF] mr-3"> <svg className="w-5 h-5 text-[#4A4459]" fill="currentColor" viewBox="0 0 24 24"> <path d="M3 18h18v-2H3v2zm0-5h18v-2H3v2zm0-7v2h18V6H3z"/> </svg> </button> <input type="text" value={newMessage} onChange={(e) => setNewMessage(e.target.value)} onKeyPress={handleKeyPress} placeholder="Type a message..." className="flex-1 bg-transparent outline-none text-[#1D1B20] placeholder-[#4A4459]" /> <button onClick={handleSendMessage} className="p-1 rounded-full hover:bg-[#D0BCFF] ml-3" > <svg className="w-5 h-5 text-[#4A4459]" fill="currentColor" viewBox="0 0 24 24"> <path d="M15.5 14h-.79l-.28-.27C15.41 12.59 16 11.11 16 9.5 16 5.91 13.09 3 9.5 3S3 5.91 3 9.5 5.91 16 9.5 16c1.61 0 3.09-.59 4.23-1.57l.27.28v.79l5 4.99L20.49 19l-4.99-5zm-6 0C7.01 14 5 11.99 5 9.5S7.01 5 9.5 5 14 7.01 14 9.5 11.99 14 9.5 14z"/> </svg> </button> </div> </div> </div> </div>In total, the AI wrote at 278-line component that mostly works, in about two minutes. Honestly, not bad for a single shot.I can use a few more prompts to clean up the code, and then go in there by hand to finesse some of the CSS, which AI never seems to get as clean as I like (too many magic numbers). But it definitely saves me time over setting this all up by hand.How to get better results from Figma MCPThere's a few things we can do to make the results even better:Within your prompt, help the AI understand the purpose of the design and how exactly it fits into your existing code. Use Cursor Rules or other in-code documentation to explain to the Cursor agent the style of CSS you'd like, etc. Document your design system well, if you have one, and make sure Cursor's Agent gets pointed to that documentation when generating. Don't overwhelm the agent. Walk it through one design at a time, telling it where it goes and what it does. The process isn't fully automatic yet.Basically, it all boils down to more context, given granularly. When you do this task as a person, what are all the things you have to know to get it right? Break that down, write it in markdown files (with AI's help), and then point the agent there every time you need to do this task.Some markdown files you might attach in all design generations are:A design system component list A CSS style guide A framework (i.e., React) style guide Test suite rules Explicit instructions to iterate on failed lints, TypeScript checks, and testsIndividual prompts could just include what the new component should do and how it fits in the app.Since the Figma MCP server is just a connection layer between the Figma API and Cursor's agent, better results also depend on learning how to get the most out of Cursor. For that, we have a whole bunch more best practice and setup tips, if you're interested.More than anything, don't expect perfect results. Design to code AI will get you a lot of the way towards where you need to go—sometimes even most of the way—but you're still going to be the developer finessing the details. The goal is just to save a little time. You're not trying to replace yourself.Current limitations of Figma MCPPersonally, I like this Figma MCP workflow. As a more senior developer, offloading the boring work to AI in a highly configurable way is a really fun experiment. But there's still a lot of limitations.MCP is a dev-only playground. Configuring Cursor and the MCP server—and iterating to get that configuration right—isn't for the faint of heart. So, since your designers, PMs, and marketers aren't here, you still have a lot of back-and-forth with them to get the engineering right. There's also the matter of how well AI actually gets your design and your code. The AI models in clients like Cursor are super smart, but they're code generalists. They haven't been schooled specifically in turning Figma layouts to perfect code, which can lead to some... creative... interpretations. Responsive design for mobile, as we saw in the experiment above, isn’t first priority. It's not a deterministic process. Even if AI has perfect access to Figma data, it can still go off the rails. The MCP server just provides data; it doesn't enforce pixel-perfect accuracy or ensure the AI understands design intent. Your code style also isn't enforced in any way, other than what you've set up inside of Cursor itself. Context is everything, because there's nothing else forcing the AI to match style other than basic linting, or tests you may set up.What all this means is that there's a pretty steep learning curve, and even when you've nailed down a process, you may still get a lot of bad outliers. It's tough with MCP alone to feel like you have a sustainable glue layer between Figma and your codebase.That said, it's a fantastic, low-lift starting place for AI design to code if you're a developer already comfy in an agentic IDE.Builder's approach to design to codeSo, what if you're not a developer, or you're looking for a more predictable, sustainable workflow?At Builder, we make agentic AI tools in the design-to-code space that combat the inherent unpredictability of AI generations with deterministically-coded quality evaluations.Figma to code is a solved problem for us already. Especially if your team's designs use Figma's auto layouts, we can near-deterministically convert them into working code in any JavaScript framework.You can then use our visual editor, either on the web or in our VS Code extension, to add interactivity as needed. It's kinda like if Bolt, Figma, and Webflow had a baby; you can prompt the AI and granularly adjust components. Vibe code DOOM or just fix your padding. Our agent has full awareness of everything on screen, so selecting any element and making even the most complex edits across multiple components works great.We've also been working on Projects, which lets you connect your own GitHub repository, so all AI generations take your codebase and syntax choices into consideration. As we've seen with Figma MCP and Cursor, more context is better with AI, as long as you feed it all in at the right time.Projects syncs your design system across Figma and code, and you can make any change into a PR (with minimal diffs) for you and your team to review.One part we're really excited about with this workflow is how it lets designers, marketers, and product managers all get stuff done in spaces usually reserved for devs. As we've been dogfooding internally, we've seen boards of Jira papercut tickets just kinda... vanish.Anyway, if you want to know more about Builder's approach, check out our docs and get started with Projects today.So, is the Figma MCP worth your time?Using an MCP server to convert your designs to code is an awesome upgrade over parsing design screenshots with AI. Its data-rich approach gets you much farther along, much faster than developer effort alone.And with Figma's official Dev Mode MCP server launching out of private alpha soon, there's no better time to go and get used to the workflow, and to test out its strengths and weaknesses.Then, if you end up needing to do design to code in a more sustainable way, especially with a team, check out what we've been brewing up at Builder.Happy design engineering!

Posted on : June 3, 2025 By Tech World Times Technology  Rate this post This article walks you through five practical steps to implement network segmentation effectively, backed by real-world use cases that showcase its value in different industries. Networks are constantly expanding across offices, cloud services, remote users, and connected devices. With so many moving parts, security gaps can easily form. Once attackers breach a weak point, they often move freely across the network, targeting critical systems and sensitive data. That’s where network segmentation comes in. It’s a practical approach to divide your network into smaller, manageable zones to control access, limit exposure, and isolate threats before they spread. But simply deploying VLANs or access rules isn’t enough. True segmentation needs planning, alignment with your business, and the right mix of technology. Step 1: Assess and Map Your Current Network Start by figuring out what’s on your network and how it communicates. Inventory Devices and Applications: List all system servers, user machines, IoT devices, cloud assets. Map Data Flows: Understand how applications and services interact. Which systems talk to each other? What ports and protocols are used? Identify Critical Assets: Highlight the systems that handle sensitive data, such as payment processing, health records, or intellectual property. Tip: Network discovery tools or NAC solutions can automate asset inventory and reveal communication paths you might miss. Step 2: Define Segmentation Goals and Policies Once you understand your environment, it’s time to set your objectives. Security Objectives: Do you want to reduce lateral movement, isolate sensitive systems, or meet a compliance mandate? Business Alignment: Segment by business unit, sensitivity of data, or risk profile-whatever makes the most operational sense. Compliance Requirements: PCI DSS, HIPAA, and other standards often require network segmentation. Example: A healthcare provider might create separate zones for patient records, lab equipment, guest Wi-Fi, and billing systems. Step 3: Choose the Right Segmentation Method Segmentation can be done in several ways. The right approach depends on your infrastructure goals and types: a. Physical Segmentation Use separate routers, switches, and cables. This offers strong isolation but can be costly and harder to scale. b. Logical Segmentation (VLANs/Subnets) Group devices into virtual segments based on function or department. It’s efficient and easier to manage in most environments. c. Micro segmentation Control access at the workload or application level using software-defined policies. Ideal for cloud or virtualized environments where you need granular control. d. Cloud Segmentation In the cloud, segmentation happens using security groups, VPCs, and IAM roles to isolate workloads and define access rules. Use a combination- VLANs for broader segmentation and micro segmentation for finer control where it matters. Step 4: Implement Controls and Monitor Traffic Time to put those policies into action. Firewalls and ACLs: Use access controls to manage what can move between zones. Block anything that isn’t explicitly allowed. Zero Trust Principles: Never assume trust between segments. Always validate identity and permissions. Monitoring and Alerts: Use your SIEM, flow monitoring tools, or NDR platform to watch for unusual traffic or policy violations. Common Pitfall: Avoid “allow all” rules between segments, it defeats the purpose. Step 5: Test, Validate, and Fine-Tune Even a well-designed segmentation plan can have gaps. Regular validation helps ensure it works as expected. Penetration Testing: Simulate attacks to check if boundaries hold. Review Policies: Business needs to change your segmentation strategy too. Performance Monitoring: Make sure segmentation doesn’t impact legitimate operations or application performance. Automation tools can help simplify this process and ensure consistency. Real-World Use Cases of Network Segmentation 1. Healthcare – Protecting Patient Data and Devices Hospitals use segmentation to keep medical devices, patient records, and visitor Wi-Fi on separate zones. This prevents an infected guest device from interfering with critical systems. Result: Reduced attack surface and HIPAA compliance. 2. Manufacturing – Isolating Industrial Systems Production environments often have fragile legacy systems. Segmenting OT (Operational Technology) from IT ensures ransomware or malware doesn’t disrupt manufacturing lines. Result: More uptime and fewer operational risks. 3. Finance – Securing Payment Systems Banks and payment providers use segmentation to isolate cardholder data environments (CDE) from the rest of the corporate network. This helps meet PCI DSS and keeps sensitive data protected. Result: Easier audits and stronger data security. 4. Education – Managing High-Volume BYOD Traffic Universities segment student Wi-Fi, research labs, and administrative systems. This keeps a vulnerable student device from spreading malware to faculty or internal systems. Result: Safer environment for open access campuses. 5. Cloud – Segmenting Apps and Microservices In the cloud, developers use security groups, VPCs, and IAM roles to isolate applications and limit who can access what. This reduces risk if one workload is compromised. Result: Controlled access and better cloud hygiene. Common Challenges Legacy Tech: Older devices may not support modern segmentation. Lack of Visibility: Hard to secure what you don’t know exists. Operational Hiccups: Poorly planned segmentation can block business workflows. Policy Complexity: Keeping access rules up to date across dynamic environments takes effort. Best Practices Start with High-Risk Areas: Prioritize zones handling sensitive data or vulnerable systems. Keep Documentation Updated: Maintain clear diagrams and policy records. Align Teams: Get buy-in from IT, security, and business units. Automate Where You Can: Especially for monitoring and policy enforcement. Review Regularly: Networks evolve- so should your segmentation. Final Thoughts Segmentation isn’t about creating walls it’s about building smart pathways. Done right, it helps you take control of your network, reduce risk, and respond faster when something goes wrong. It’s a foundational layer of cybersecurity that pays off in resilience, compliance, and peace of mind. About the Author: Prajwal Gowda is a cybersecurity expert with 10+ years of experience. He has built businesses and was a Business Unit Head for Compliance and Testing services. Currently, he is the Chief Technology Officer at Ampcus Cyber, leading the company’s technology strategy and innovation efforts. He has also been involved in the Payment Card Industry, Software Security Framework, ISO 27001 Controls Gap Analysis, ISMS, Risk Analysis, OCTAVE, ISO 27005, Information Security Audit and Network Security. Prajwal is a Master Trainer who has conducted 100+ cybersecurity training sessions worldwide. Tech World TimesTech World Times (TWT), a global collective focusing on the latest tech news and trends in blockchain, Fintech, Development & Testing, AI and Startups. If you are looking for the guest post then contact at techworldtimes@gmail.com