This brings up an important question for WordPress agencies: How does using AI on client projects affect pricing?

On the surface, it feels like a tricky question. AI is supposed to improve efficiency. A more efficient process should take less time to complete, which means lower costs. But it’s not that simple.

The point of increased efficiency is to make more profit. Faster results and decreased overhead shouldn’t mean that your business takes a financial hit, right? If that’s the case, then agencies have no incentive to use AI for, well, anything.

So, should we reassess the value of our services in the age of AI? And how do we present it to clients? Let’s try to find the answers.

Time-Based Billing Is Outdated

The hourly rate has been a standard for many freelancers and agencies. We charge based on how much time we spend on a given task. This policy worked well enough when everything was done by hand. However, it doesn’t fit with how most of our work is done today.

Let’s take a custom WordPress plugin as an example. In this scenario, our client needs a niche plugin that adds functionality to their website.

This type of project could have taken several hours before AI came into the picture. Much depends on your level of expertise, but it’s safe to say you’d need to conduct research, write the code, then test. There would inevitably be bugs to fix and more tests to run. It’s easy to get stuck on an issue that delays progress.

An hourly rate could make sense here, as you risk getting burned by a project-based fee. What if the project takes longer than anticipated? You might lose money on the deal.

Using AI accelerates the entire process. You should still conduct research, and there will still be bugs to fix. You’ll also want to test for security. But the increased efficiency will likely lead to faster turnaround times.

Here, a project-based fee is a more reasonable solution. You’re charging based on the outcome, rather than time spent. And the result is the most important part of the equation – regardless of how long it took.

Using AI Requires Different Thinking and Communication

Working with AI also means a shift in our approach on both the project and client sides. Agencies and developers must focus on the big picture more than the process of getting it done. Again, the idea is that time isn’t the most relevant factor.

AI-based workflows often turn us into orchestra conductors, rather than old-school code jockeys. We’re using plain language to guide the tool in the right direction. We spend less time on the foundational aspects and more on the structure and feel. It’s a different role that can take time to grasp fully.

This also affects how we communicate with clients. We should emphasize the value in what we build. Clients must understand the benefits of a new feature and how it moves them closer to their goals.

In that regard, it doesn’t matter if building a new plugin took you five days or five hours. The only question worth asking is: Did we provide the best possible solution within their budget?

This isn’t much different than other service-based industries. You probably didn’t care what tools the carpenter used to build your new deck. You were likely more excited about how it looked and functioned.

AI is akin to the carpenter’s power tools. In the right hands, it becomes easier to achieve the desired outcome. You still need a certain level of expertise, however.

AI Should Increase Your Agency’s Revenue

The bottom line is that AI provides a path to do more with less. Perhaps the biggest hurdle for agencies and freelancers is embracing this philosophy.

Remember, there have been many changes in how we build websites. We went from hand-coding HTML to using content management systems (CMS) like WordPress. Tools like WYSIWYG editors and page builder plugins incrementally increased our productivity. Little by little, web professionals adopted these solutions and adapted their businesses to take advantage of them.

AI is more of a revolutionary technology, as it increases our output exponentially. Naturally, a change this big leads to questions about how we work and how much we charge.

You may run into a client who expects lower pricing because of your increased efficiency – don’t fall for it. Your knowledge and experience are still guiding the ship, and they are worth a premium. Once you realize this, you can use AI to encourage growth. These new tools simply offer a faster way to get there.

here. He recently started a writing service for WordPress products: WP Product Writeup. He also has an opinion on just about every subject. You can follow his rants on Bluesky @karks.com.

Read more articles by Eric Karkovack

The post Should Your Agency Charge Less for AI-Assisted Solutions? appeared first on The NOKIA Blog.

Today, we’re announcing the public preview of AWS Well-Architected Agent, an AI-powered service that analyzes your AWS environment to deliver targeted, contextual recommendations for improving your applications’ cost, security, performance, and resilience. The AWS Well-Architected Agent analyzes your infrastructure, understands unique business goals, and delivers contextual recommendations with ready-to-implement fixes. It delivers context-aware optimization without relying on manual audits or generic checklists.

The agent evaluates your environment as an experienced cloud architect would. It automatically correlates utilization metrics, resource configurations, and application topology, and analyzes against Well-Architected best practices across 65+ AWS services. It generates recommendations aligned to your declared business goals, delivers implementation packages with every finding, and surfaces cross-pillar trade-offs making it simpler to remediate the findings.

Here are the three main features of this service:

• Goal-aligned intelligence: AWS Well-Architected Agent replaces flat, undifferentiated findings with context-aware, prioritized recommendations. You declare your business objectives and share your application context. The agent automatically generates and prioritizes recommendations by impact and effort against those goals.
• Three-level recommendations: AWS Well-Architected Agent provides individual resource findings with specific dollar impact (where applicable) and step-by-step remediation, consolidated findings across multiple resources scoped to your application, and broad architectural patterns and designs with Infrastructure as Code (IaC) code changes needed to align with Well-Architected best practices.
• Optionality in remediation: You can choose your path on how you want to remediate with a complete implementation steps tailored to your environment: the console walk-throughs, updated IaC changes for architecture-level recommendations, and AWS Command Line Interface (AWS CLI) commands.

AWS Well-Architected Agent in action
To get started, create an agent profile to define the scope of what Well-Architected Agent can access and provide recommendations on, complete the IAM role setup to access resources, conduct architecture review, and remediate recommendations.

Create an agent profile
In the AWS Well-Architected console, choose Get started with Well-Architected Agent. You can define an agent profile that specifies which AWS accounts and applications to monitor, which optimization pillars to focus on, and the permissions required.

You can choose AWS accounts or AWS Regions to monitor and optimization pillars that matter most to your business. You can also set goals for each pillar: cost optimization, performance, resilience, and security.

To give access to the agent for your AWS environment, provision customer-managed IAM roles the agent uses to read resource configurations, utilization metrics, and application topology. To learn more, visit the IAM prerequisite for AWS Well-Architected Agent.

When you choose Get Started, the agent creates your agent profile. Resource and application recommendations will be generated within 24 hours after profile creation.

You can conduct an architecture review on pre-deployment workloads by uploading an IaC project in Terraform, AWS CloudFormation, or AWS Cloud Development Kit (CDK) to be analyzed. Choose Conduct architecture review in the dashboard, upload a.zip file containing IaC project or repository file, and select which Well-Architected lens to use for reviewing your infrastructure.

You can define your applications to add context which will enhance the relevancy and further contextualize recommendations. Choose Add application context in the dashboard, add your applications with AWS accounts, AWS Regions, AWS services, tags if you want to narrow the scope to specific resources, and the details of applications.

Review prioritized recommendations and start remediating
Now you can see generated prioritized recommendations generated by the agent across your resources and applications, selected pillars, ranked against your declared goals, with automation-ready remediation included.

When you choose the specific recommendation, you can see the details, insights into why the agent are suggesting the recommendation, impacts and trade-off, and recommended fixes across affected AWS resources.

Choose Start remediation to address recommended fixes. You can choose the console, updated IaC template, CLI commands to remediate by the resolution type. It provides detailed step-by-step instructions and you can roll out this instruction and verify the result.

When you choose Using updated IaC template, the agent provides the code changes needed to update your existing IaC templates such as the CDK function shown above which you can copy directly into your codebase.

You can also configure API access to integrate recommendations directly into your existing development and operations workflows. To interact with the agent programmatically, including calling APIs and searching documentation, try the AWS MCP Server and plugins with your preferred AI coding tool. To learn more, visit the AWS Well-Architected Agent documentation.

Things to know
Here are some things that you should know about the Well-Architected Agent.

• Automation: You can receive recommendations with the exact IaC code changes needed to remediate, with risks identified by pillar, catching issues before they reach production. Recommendations are delivered through the console and API so you can act without context-switching. Recommendations are also updated periodically, so new recommendations are available for your team to track regularly.
• Evaluation: Generative AI capabilities produce this recommendation, which may contain errors or incomplete information. You are responsible for evaluating the recommendation in your specific context and implementing appropriate oversight and safeguards. Learn more about AWS Responsible AI practices.

You can still use existing AWS Well-Architected Tool to manually evaluate your cloud architecture with user-defined lenses that measure your workload using your own best practices.

Join the preview
Access to the AWS Well-Architected Agent and its recommendations is available in US East (N. Virginia), US East (Ohio), and US West (Oregon). You can onboard workloads from any AWS commercial Region. AWS Well-Architected Agent is delivered by AWS Support and available to AWS customers with an AWS Support plan.

Give it a try today in the AWS Well-Architected console and send feedback through your usual AWS Support contacts.

— Channy

The post Announcing AWS Well-Architected Agent, an AI-powered intelligence to optimize your cloud environment (preview) appeared first on The NOKIA Blog.

If there’s one theme that defined last week, it’s choice. The frontier models keep arriving, and the interesting question is no longer just “how smart is it?” but “which model fits this step, at this cost, at this latency?” That’s exactly what landed on Amazon Bedrock over the past few days: GPT-6 Sol and GPT-6 Luna from OpenAI, giving you two new points on the intelligence-versus-efficiency curve, and Claude Opus 5.5 from Anthropic, the first of the Claude 5.5 family.

GPT-6 Sol is built for the demanding, recurring work of development and operations, while GPT-6 Luna makes focused, repeatable tasks practical at high volume, and both ship at significantly lower pricing than their GPT-5.6 predecessors. Claude Opus 5.5, meanwhile, does more with fewer tokens than Opus 5 and is tuned for agentic coding and long-running tasks. What I like about all three is that they push toward the same idea: match the model to the job instead of reaching for the biggest one every time. The other thread was observability catching up to this agentic world, including a launch I had the pleasure of writing about myself.

Now, let’s get into this week’s AWS news…

Last week’s launches
Here are some launches and updates from this past week that caught my attention:

• Introducing Amazon CloudWatch Omni – You can now observe your applications and AI agents together in a single, collaborative experience. Amazon CloudWatch Omni is built on OpenTelemetry, so your existing telemetry shows up with nothing to reconfigure, and your whole team reaches it through one URL with enterprise SSO — no console access required. It auto-discovers your services, maps dependencies, and brings AWS DevOps Agent into investigation sessions to correlate signals and trace root causes. There’s a companion post on the agent-observability side, a deeper dive on the AWS Cloud Operations blog on what observability for the AI era looks like, and the announcement on What’s New with the specifics. If you want the bigger picture, Matt Wood’s Wrong, not broken is a great read on why correctness now has to be measured at the level of the run.

• Enhanced custom event buses in Amazon EventBridge – Amazon EventBridge now offers an enhanced custom event bus purpose-built for organizations scaling event-driven applications across teams and accounts. You can now deploy a single centralized bus shared across every account in your organization through AWS RAM, with optional event ordering, a simplified Subscriber resource that bundles filtering, targets, and retries, content-based deduplication, and synchronous invocation for targets like AWS Lambda. A new ingress/egress pricing model replaces the compounding cross-account routing charges of multi-bus setups, and your existing buses keep working unchanged as “classic.”

• Amazon SageMaker HyperPod Inference Gateway – You can now front your LLM inference on Amazon SageMaker HyperPod with a Kubernetes-native, GPU-aware routing layer that deploys as a single Amazon EKS managed add-on with zero application changes. Instead of round-robin load balancing, it routes on real-time inference signals — KV cache utilization, queue depth, prefix cache hits, predicted latency, and more — cutting first-token latency by up to 82% in mixed-hardware and bursty scenarios. It works with any OpenAI-compatible model server, including vLLM and SGLang.

• AI agent skills for AWS End User Messaging and Amazon SES – You can now build and send messages by asking your AI coding agent in plain language. Amazon SES and AWS End User Messaging publish AI agent skills for the AWS MCP Server, giving your agent step-by-step, validated guidance for tasks like verifying a sending identity, sending a production email, or building a branded RCS agent with cards and buttons. The skills work with Claude Code, Codex, Cursor, and Kiro, so you can complete messaging workflows without hopping between docs and console screens.

For a full list of AWS announcements, be sure to keep an eye on the What’s New with AWS page.

Other AWS news
Here are some additional posts and resources that you might find interesting:

• Introducing Strands harness – The Strands Agents team released Strands harness, a fully assembled, general-purpose agent harness you can run locally or deploy anywhere, under Apache 2.0. It takes one line of Python or TypeScript to wire up your model of choice across Amazon Bedrock, Anthropic, OpenAI, Google, or a local Ollama model, and it ships with sensible defaults for prompt caching and context management (truncating bulky tool results, compacting when the context window fills up, and keeping memory across runs). The team reports it costs about 28% less than comparable harnesses on the same models while holding accuracy steady.

• Announcing the new AWS Reimagine report on AI – The AWS Executive in Residence team spent nine months interviewing 154 leaders across 27 countries about what separates organizations that turn AI into value from those that don’t. The report is candid (including where AI hasn’t worked at Amazon), and the recurring insight is that once building gets fast, the bottleneck moves to deciding, funding, and governing the work. Well worth a read if you’re thinking about how your teams adopt AI in practice.

For a full list of AWS blog posts, be sure to keep an eye on the AWS Blogs page.

Upcoming AWS events
Check your calendar and sign up for upcoming AWS events:

• AWS re:Invent – AWS re:Invent returns to Las Vegas from November 30 to December 4, and session times, locations, and speakers are live. Reserved seating opens October 6, so register now and be ready to claim your spot in chalk talks, workshops, and builders’ sessions.

• AWS Summits – With re:Invent on the horizon, the Summits are wrapping up for the year. The last stop is Dubai (September 30) at the Dubai World Trade Center, with 60+ sessions, an AWS Village, and hands-on workshops.

Join the AWS Builder Center to connect with builders, share solutions, and access content that supports your development. Browse here for upcoming AWS-led in-person and virtual events and developer-focused events. That’s all for this week. Check back next Monday for another Weekly Roundup!

— Daniel Abib

The post AWS Weekly Roundup: GPT-6 Sol and Luna, Claude Opus 5.5 on Amazon Bedrock, Strands harness, and more (September 28, 2026) appeared first on The NOKIA Blog.

Historically, part of this ritual includes installing a ton of apps. I add the requisite Adobe design tools, the Microsoft Office suite for productivity, and a host of other software. Apps for email, FTP, media conversion, and a local web server environment remain staples.

My current system is now a few years old, and I have dozens (hundreds?) of these apps. They still serve their purpose. But it recently dawned on me that most of what I use could be replaced by a web browser. That will likely mean fewer apps to install on my next computer.

These are words I never thought I’d utter. My web design career began before the first release of Netscape. As such, I’ve had a love/hate relationship with browsers. For every benefit, there have been limitations and quirks to deal with.

These days, you can do pretty much anything within your chosen browser. That got me thinking: are traditional design apps still relevant? Should we abandon them for browser-based tools? I’m not so sure, but let’s figure this out together.

Modern Web Apps Break Boundaries

It used to be that most browser-based apps were inferior to their desktop counterparts. Common workflows like text and media editing felt clunky and minimally useful. I used them in a pinch and usually came away frustrated.

Meanwhile, desktop powerhouses like Excel, Photoshop, and Dreamweaver were infinitely more flexible. They were built for those who care about quality and require high-level functionality. Such professional-grade tools have always been worth the cost.

That narrative has been turned on its head by a combination of more powerful web standards and server technologies. There are now online video editing platforms that can produce top-notch results. Design tools like Figma make it easy to create and share interactive mockups. Google’s suite of productivity tools offers all the bells and whistles without compromise. Even Photoshop has an online version these days.

Collaboration might be the biggest selling point of all. You can keep clients and colleagues in the loop with minimal effort. This improves efficiency and saves us from the never-ending email chains of yesteryear.

And the appeal of these apps goes beyond functionality and convenience. They’re also cross-platform and device-agnostic. It used to be that you’d need a desktop app built specifically for your operating system. Using a browser means it works on Windows, Linux, macOS, Android, iOS, and more.

Then there are the hardware requirements. Granted, you should still have a system with plenty of memory and a modern graphics processor. However, having a massive hard drive isn’t necessary when storing files in the cloud.

The old boundaries of software have vanished. Doing all the things within a browser isn’t a chore like it used to be. And these apps may be enough for most web designers.

Trust and Content Ownership Are Concerns

Software is always an investment, regardless of how you access it. There are also privacy and security risks to consider. Browser-based tools often amplify those concerns.

Companies like Adobe and Microsoft have some level of tracking within their desktop apps. And they do connect to the internet. So, this is nothing new. But working in a browser opens up a different (or, at least, a bigger) can of worms.

For instance, cloud storage is quite convenient. But what happens if the provider gets sold or goes out of business? Will you lose access to your data? Are policies in place to maintain account security in the event of a breach or server crash? The answers aren’t always clear, and you may not find out until something bad happens.

Then there is the matter of artificial intelligence (AI). It seems like every tool on the planet has an AI integration of sorts. How are these features used on your content? Does the provider train their models with your work? Could your sensitive information become exposed online?

Working online also opens you up to third-party tracking. It may be something relatively innocent, like an analytics suite. But ad networks and similar companies could be watching you – and there is no guarantee they’ll abide by the rules.

These are important questions to answer when thinking about your (and your client’s) data. Again, desktop apps aren’t immune to these issues. But an online app that shows up overnight deserves an honest assessment. The risks could far outweigh the benefits.

Desktop Apps Are Still Relevant When Control Matters

It’s truly amazing to see how far web technologies have come in the past decade. You can see it in both commercial and open-source software. Functionality once reserved for powerful desktop devices can now exist in the palm of your hand (and with responsive design, for that matter).

I still believe there’s a tradeoff, however. The work-from-anywhere tools we use have plenty of benefits (provided you really do want to work from your lawn chair). But you lose a measure of control along the way.

There’s something to be said for storing files locally (with routine backups, of course). Not to mention the ability to customize an app’s layout or tool set to match your workflow. There’s a level of personalization you don’t seem to get in a browser.

The reality is that you don’t need desktop software for every purpose. There are plenty of online tools that will do the job. But there are scenarios where these old-school beasts make sense.

For example, I can’t imagine Disney making their next hit movie solely within a browser. And web designers who want full control of their workflow might want to keep a few items installed on their hard drives. I know I will.

here. He recently started a writing service for WordPress products: WP Product Writeup. He also has an opinion on just about every subject. You can follow his rants on Bluesky @karks.com.

Read more articles by Eric Karkovack

The post Are Browser-Based Apps Enough for Web Designers? appeared first on The NOKIA Blog.

Ever since the commercialisation of the Graphical User Interface pioneered by systems like the Xerox Star and popularised by the original Apple Macintosh, software has relied heavily on point-and-click interactions. If you wanted to book a trip, buy a pair of shoes, or research a health symptom, you were expected to navigate a labyrinth of user interfaces. You click menus, adjust range sliders, fill out multi-step forms, deal with cookie pop-ups, and open dozens of browser tabs just to cross-reference basic information. We have become accustomed to spending more time managing the software rather than actually achieving our goals.

That contract is officially changing. Driven by advances in artificial intelligence and large language models, a new generation of web tools is pioneering a radical philosophy: Intent-Driven Design. Rather than expecting our users to learn complex menus and click through elaborate sales funnels, these platforms operate by capturing high-level human goals and silently executing the grunt work in the background.

This vision builds on long-standing HCI concepts like Golden Krishna’s “The Best Interface Is No Interface” and Don Norman’s principles of human-centered design.

The ultimate goal of modern web design is no longer to build prettier buttons or flashy animations; it is to eliminate the interface entirely.

Well, at least what we understand based on our current experience.

It is essential for UX designers to understand the changes we’re witnessing and even re-evaluate our role, shifting our focus from designing visible interfaces to guiding transparent, intent-driven AI experiences.

The Death Of The “10-click” Process

To understand where web design is going, we first have to look at the friction we have accepted as “normal” for decades.

Consider the traditional workflow of buying a flight online. The user experience is intentionally hyper-interactive:

1. Navigate to a travel aggregator or airline website.
2. Select “Round Trip” from a dropdown menu.
3. Type the origin city and wait for auto-complete.
4. Type the destination city and wait for auto-complete.
5. Click a calendar modal, toggle through months, and select departure and return dates.
6. Choose the number of passengers and cabin class.
7. Click “Search” and wait for the results page to load.
8. Filter by price, layover duration, departure time, and airline.
9. Sort the results and scan through dozens of individual options.
10. Click through a three-page checkout funnel dodging upsells for rental cars and travel insurance.

This is a classic point-and-click UI paradigm. The computer acts as a passive container of data, and the human acts as the orchestrator, manually inputting parameters, interpreting raw outputs, and executing each micro-step along the way.

Intent-driven design flips this dynamic entirely. Instead of forcing you to navigate the mechanical steps of how to find a flight, the interface asks a simple question: What are you trying to accomplish?

When you express a goal, such as “Find me a non-stop flight to Chicago next weekend under $300 that arrives before 5 PM”, the software reads your intent, executes the multi-step search query behind the scenes, compares the options, and presents a single actionable resolution. The ten clicks dissolve into one clear intent outcome.

Three Web Platform Examples Replacing Buttons With Intent

This shift isn’t a theoretical vision of the distant future. Some of the world’s most accessible websites allow you to experience intent-capturing systems already.

1. Perplexity AI: Search Without The Open Tabs

Traditional search engines like Google were built as directories. You typed a keyword, and the interface rewarded you with ten blue links. The actual work of opening five tabs, skimming long articles, dodging ads, and manually assembling an answer was left to you. Although this is now changing, with AI content appearing first when you search on Google.

Perplexity AI allows anyone to perform instant intent-based searches. Instead of forcing you to click into multiple tabs, the interface synthesises the perfect result for your context.

• The interaction: You ask a complex question in plain English: “Compare the top three budget laptops for a computer science student, focusing on battery life and keyboard quality.”
• The invisible work: In under two seconds, the platform searches the web, reads dozens of articles, evaluates hardware specifications, and cross-references user reviews.

• The result: (See screen above) Instead of throwing web pages at you, Perplexity dynamically generates a single custom answer complete with formatted comparison tables, pros and cons lists, and concise inline citations. You get the outcome of thirty clicks in just one.

2. Vercel v0: Web Design Without Dragging And Dropping

For years, creating a website meant using visual builders like Figma or drag-and-drop web editors. As designers, we spent hours manually drawing rectangles, picking hexadecimal colour codes, adjusting padding values, and sometimes writing CSS code.

Vercel v0 lets anyone test its generative interface builder right from the home page without signing in.

• The Interaction: A user types a descriptive goal into the input prompt: “Create a modern dark-mode dashboard for a subscription SaaS app showing monthly revenue, active users, and a customer churn chart.”
• The invisible work: The underlying AI understands layout principles, accessibility guidelines, UI component libraries, and responsiveness. It writes clean HTML, Tailwind CSS, and React code in real time.
• The result: Rather than spending an afternoon manipulating elements, the user receives a fully functional, pixel-perfect user interface in seconds! The traditional visual design tool disappears, replaced by raw human intent.

3. Goblin.tools: Breaking Down Overwhelming Tasks

Many traditional productivity tools require you to manually construct task lists, drag items across Kanban boards, and assign micro-deadlines. Goblin.tools is a free, single-page suite of single-task AI tools designed specifically for neurodivergent users or anyone feeling overwhelmed, requiring zero sign-ups or configuration.

• The interaction: You enter a vague, intimidating goal into the Magic Todo tool, such as “Prepare for a job interview”.
• The invisible work: Instead of forcing you to plan every step, the system analyses the cognitive load of the goal and automatically breaks it down into small, actionable sub-tasks adjusted to your preferred level of detail.
• The result: The interface eliminates the stressful task-planning phase and presents a clean checklist tailored to your exact goal.

The Core Pillars Of Intent-driven Web Design

When you remove traditional menus, sidebars, and forms, how do you keep a website usable? Designers pioneering this space rely on three core pillars:

1. High-level Goals

An invisible interface doesn’t always wait for you to type a command — it leverages context to anticipate user needs. Guided by industry standards like Apple’s Human Interface Guidelines on Contextual & Ambient Design, modern systems read environmental metadata, such as device state, location, and past interaction patterns, to trigger proactive actions.

For example:

• Time and location: A food delivery web app prioritising your saved home address and dinner items automatically at 6:30 PM on a weekday.
• Cross-app history: A calendar application noticing an email about an upcoming appointment and surfacing a one-click “Add to Schedule” card without forcing you to copy and paste event details manually.

2. Generative UI

In traditional web design, every user sees the exact same layout. An e-commerce store shows the same navigation bar whether you are a first-time visitor looking for customer support or a returning customer tracking a package.

As highlighted in the Nielsen Norman Group’s analysis on AI as a new UX paradigm, computing is shifting from command-based interaction to outcome-specification. This enables Generative UI, where interfaces are rendered dynamically on the fly based on what you are trying to do in that exact moment. For example, platforms like Vercel v0 demonstrate how raw intent can instantly render functional code components without manual layout building. If you express a desire to compute complex financial data, the interface generates a dynamic calculator widget on demand, receding once your goal is completed.

3. Execution by AI Agents

Traditional interfaces are obsessed with prevention, constantly peppering users with confirmation pop-ups (“Are you sure you want to delete this file?”).

Intent-driven interfaces adapt Jakob Nielsen’s 10 Usability Heuristics on User Control and Error Recovery by shifting the safety net from prevention to easy reversibility. Because autonomous agents take actions on your behalf, products prioritise frictionless rollback mechanisms. A prominent “Undo” button, simple revision prompts (“Make this summary shorter”), and transparent audit logs replace intrusive warning modals.

The Hidden Risks

While removing interface friction is liberating, stripping away visual controls introduces significant product design challenges. When software acts on inferred intent rather than direct point-and-click commands, designers must navigate critical ethical and technical pitfalls.

The Illusion Of Control

When a website makes decisions for you, it can quickly feel patronising or invasive. As explored by the Stanford Human-Computer Interaction (HCI) Group, automation must maintain clear boundaries to prevent user frustration. Furthermore, ethical frameworks from the Center for Humane Technology emphasise that product designers must guard against manipulative defaults.

Designers must strike a delicate balance: automate routine execution, but explicitly prompt the user for high-stakes confirmations (such as financial transactions, publishing public content, or altering privacy settings).

The Black Box Problem

In a traditional UI, if you get an unexpected result, you can usually diagnose the issue — perhaps you checked the wrong filter box or selected an incorrect date.

With an intent-driven interface, troubleshooting becomes harder. To address this “black box” challenge, the Google PAIR (People + AI Research) Guidebook advocates for transparent feedback loops. The system must explicitly state its interpretation (“Searching for non-stop flights to Chicago under $300…”) so users can calibrate trust and correct misinterpretations instantly.

From A UX Perspective

As a UX designer, always being curious to understand how our design approach is changing in the world of AI, I find it essential that we re-evaluate the foundational elements of our craft.

Rather than designing static buttons and rigid forms, we need to learn to map and present dynamic, generative UI components that adapt on the fly to user intent.

By mastering these evolving patterns, like ambient feedback, inline prompts, and transparent AI status indicators, we can ensure that screenless, agent-driven tools remain intuitive, ethical, and deeply human-centered.

Conclusion

The ultimate goal: The best design is no design.

For decades, the digital industry has evaluated software success through engagement metrics like time spent in app, click-through rates, and page views per session. Websites were deliberately engineered to maximise visual engagement and interaction volume.

The philosophy behind Golden Krishna’s seminal book The Best Interface Is No Interface, aligned with the broader Center for Humane Technology’s Time Well Spent movement, turns these metrics on their head. The ultimate test of a modern digital product is no longer how visually captivating its buttons are, but rather: How effectively did this software solve the problem and get out of the user’s way?,

We are entering an era where web applications will no longer be measured by the beauty of their interfaces, but by their ability to render those complex interfaces completely obsolete. The future of the web isn’t more interaction — it is seamless, invisible completion.

(ah, yk)

The post The Death Of The Button: Why The Best Interface Is No Interface appeared first on The NOKIA Blog.

SEO has always had a dash of mysticism to it. People have tried various tricks and techniques to improve rankings. Now, we’re faced with the challenge of pleasing AEO (Answer Engine Optimization). The goal is to get your content cited by AI models. That could be a search engine like Google. But it also includes ChatGPT, Claude, and other AI tools. When a user asks an AI model a question, you want to be a source of relevant information.

Much like SEO, AEO inspires debate about what providers are looking for in a website. Do we need to do anything drastic? Or are the fundamentals of adding metadata and structured content enough?

These are among the questions we’re trying to answer here today. We can’t promise perfect results, nor that best practices won’t change (that’s a given). But we can show you some tools and resources to help you on your journey.

The good news is that WordPress is a great platform for getting your site noticed by search engines. It already includes some basics, such as logical content structure and sitemaps. And its plugin ecosystem is full of high-quality tools. This includes options for improving your site’s AEO.

Let’s get started!

Why You Should Care About AEO

Traditional search engines are still an important piece of the puzzle for discovering content. However, people are also turning to AI tools for information within the context of a conversation. That differs quite a bit from how we’ve researched topics for the past 30 years or so.

For example, you might use Bing to find a list of WordPress e-commerce plugins. That’s great, but you still have to click through each relevant link to find what you’re looking for. You could, in theory, waste a lot of time researching plugins that aren’t a good fit for your project.

Compare that experience with using an AI tool like Gemini. You could ask for WordPress e-commerce plugins with specific features, such as subscriptions or shipping integrations. The AI model will provide a summary of plugins that match your request, complete with background information.

AI provides a succinct report that makes it easier for users to find links of interest. That’s important to every website owner, whether you’re a plumber or a tech publication. Making your site AEO-friendly is part of getting your content seen by the right people.

It’s also a different deal than the training bots that hog site resources. You can still block harmful bots while welcoming the legitimate ones.

Scan Your Site for AI Agent Readiness

What does your WordPress website need to be indexed by AI models? You may already be on the right track.

The basics of SEO, such as a robots.txt file and an XML sitemap, are must-haves. These items help direct bots to your content and tell them what to index, similar to how search engines use them. But there’s more to the story.

Cloudflare has a helpful scanning tool, Is Your Site Agent-Ready?, that analyzes your website’s structure. It looks for the following:

• The discoverability of your site, via robots.txt, sitemaps, link response headers, and DNS records.
• If your site makes content available in an AI-accessible format, such as Markdown.
• How your site manages bot access via robots.txt.
• Any agent skills your site may have, such as MCP.
• E-commerce protocols.

You’ll receive a report that details where you’re succeeding and where there’s room for improvement. We should note that some of the above may not apply to your website. For example, agent skills won’t be relevant unless you have AI agents on your website. You can also adjust the scan settings to focus only on the areas you care about.

As with all scanning tools (AI and otherwise), take the results with a grain of salt. However, they will provide some actionable advice. It’s up to you to determine what makes sense for your website.

Turn Your HTML Content Into Markdown

It may be a surprise, but HTML isn’t the best format for AI models to read. Instead, they prefer Markdown. This plain-text markup language is easier for bots (and humans) to understand. Elements like headings and lists can be identified without knowing code.

Markdown is also more efficient than HTML. Models don’t have to sift through lines of unnecessary code to access your content. That means fewer tokens, which is better for everyone.

WordPress doesn’t natively support Markdown output. However, WordPress.org recently added this capability via the experimental html-to-md plugin – and you can, too. It’s a simple way to make your site friendlier to AI models.

Install the plugin, activate it, and a <link> element will be added to each page’s header, pointing to the Markdown version. Your site’s visitors won’t know the difference, but AI models will.

LLM Markdown is a similar plugin, but with a twist. A settings page lets you enable or disable Markdown output for specific post types. Look for more plugins to hit the market as Markdown output becomes more commonplace.

Cloudflare users with paid plans also have access to a Markdown for Agents feature. It doesn’t require a plugin – simply turn it on in your account dashboard.

Helpful AEO Resources

Optimizing your WordPress website (or any website, for that matter) for AI agents isn’t as hard as you may think. The tools and tips above will help you determine and address your needs.

But AEO is a nascent subject. As such, expect things to change quickly. The following are some resources you can use to learn more and stay ahead of the game:

We hope you found this overview useful. Now that you have a better idea of what AEO is, it’s time for action!

here. He recently started a writing service for WordPress products: WP Product Writeup. He also has an opinion on just about every subject. You can follow his rants on Bluesky @karks.com.

Read more articles by Eric Karkovack

The post How To Make Your WordPress Website AI-Friendly appeared first on The NOKIA Blog.

Today, we’re announcing the general availability of vector search in Amazon DynamoDB. You can now store vector embeddings alongside your operational data in DynamoDB and run similarity searches directly against that data, without replicating it to a separate vector store.

DynamoDB supports native vector search with single-digit millisecond latency at 99%+ recall, and is designed for any scale, even trillions of vectors. There are no servers to provision, patch, or manage, and no software to install, maintain, or operate. The service has no versions, no maintenance windows, and zero downtime maintenance.

Vector indexes have no storage limits and scale horizontally as your data grows. You can now build applications that require semantic retrieval on agentic memory, retrieval augmented generation, recommendation engines, personalized experiences, anomaly detection, and more using DynamoDB and its native vector search.

If your application already uses DynamoDB, adding vector search previously required copying data into a dedicated vector database while maintaining a synchronization pipeline between the two services. This added operational overhead, data movement costs, licensing costs, and the challenge of maintaining predictable low latency at scale. With vector search built into DynamoDB, your vectors and operational data share the same serverless infrastructure and the same pay-per-request pricing model.

Vector search in DynamoDB introduces a new index type that you create on an attribute storing vector embeddings. You generate embeddings using a model of your choice, such as Amazon Bedrock Titan Text Embeddings, Cohere Embed, or OpenAI text embedding models, and store them as a list of floats in your table using a standard PutItem call. You then create a vector index on that attribute and specify the number of dimensions, the distance function, and any non-vector attributes you want to use as filters to narrow search results at query time. The SearchVectors API accepts a query vector, the number of results to return (up to 100), and optional filter conditions. It returns results ranked by similarity.

Use vector search in DynamoDB when your operational data already lives in DynamoDB and you want to add similarity search without provisioning a separate database or managing a synchronization pipeline. DynamoDB is fully serverless, so vector search scales automatically with no infrastructure to manage. It supports up to 4096 dimensions, Euclidean, Cosine, and Dot product distance functions, and inline filtering.

Getting started with vector search in DynamoDB
This walkthrough shows how to add vector search to an existing DynamoDB table using the DynamoDB console. The scenario contains an online sporting goods store with a product catalog table. Each item has standard operational attributes such as productId, category, description, marketplace, name, and price. The goal is to add semantic search so shoppers can find products using natural language queries rather than exact keyword matches.

1. Prepare DynamoDB table
To enable semantic search, I first generate vector embeddings for the product descriptions already in my table. Embeddings are numerical representations of text generated by a machine learning model that capture the meaning of the content. Two items with similar descriptions will have embeddings that are close to each other in vector space, which is what makes similarity search possible.

I can generate embeddings using Amazon Bedrock Titan Text Embeddings or another embedding model, then add them to my table using the AWS Management Console, AWS Command Line Interface (AWS CLI), AWS SDKs, AWS CloudFormation, or other infrastructure-as-code (IaC) tools.

For an existing table like ProductCatalog, I add the embeddings to each item as a new attribute named descriptionEmbedding using an UpdateItem call. DynamoDB stores vector embeddings using its existing List data type. Each element in the list is a Number that represents a single float value of the embedding vector. This means I do not need a new data type or schema change to start storing vectors alongside my existing operational attributes.

2. Create vector index
In the DynamoDB console, open the ProductCatalog table and choose the Indexes tab. I choose Create vector index. On the Create vector index page, I fill in the index details as follows. I enter ProductDescriptionIndex as the Index name and descriptionEmbedding as the Vector attribute.

I enter the number of Dimensions that matches my embedding model’s output and select Cosine as the Distance function. Cosine measures the angle between vectors rather than their magnitude, which makes it effective for comparing semantic similarity of text embeddings. Vector search in DynamoDB also supports Euclidean and Dot product distance functions.

• Euclidean: Use when the magnitude of the vectors is meaningful, such as clustering items by a numeric value like purchase count.
• Dot product: Use when both direction and magnitude matter, such as in recommendation systems that weight interest alignment and frequency together. As a general rule, match the distance function to the one used to train your embedding model for the best accuracy.

I enter marketplace as the Partition key. The vector index partition key controls how DynamoDB distributes vectors across partitions, allowing the index to scale out while maintaining predictable latencies. Each search is scoped to a single partition key value, so a product catalog serving multiple marketplaces can search within one marketplace’s inventory without scanning the entire index. The partition key is optional, but recommended for large datasets with high query throughput.

I expand Inline filter attributes and add category as a filter attribute. This helps me narrow search results to a specific product category at query time. Filter conditions support exact-match values only; range conditions such as BETWEEN or BEGINS_WITH are not supported. I leave Attribute projections set to All so that all table attributes are returned with my search results. Choose Create vector index and wait for the index status to change to Active.

3. Run vector search
I generate a query vector from a natural language search term such as “lightweight running shoes for summer” using the same embedding model I used for the product descriptions. In the DynamoDB console, I choose Explore items in the left navigation pane and select the ProductCatalog table.

Choose Search to switch to vector search mode. I select ProductDescriptionIndex from the Select a vector index dropdown, paste the query vector into the Search vector field, and set Number of results (Top K) to 5. I enter US as the Partition key value to scope the search to the US marketplace. I expand Inline filter attributes and set category equal to footwear to narrow the search to footwear products only. Now, choose Run.

DynamoDB returns the five most semantically similar products in the footwear category, ranked by similarity score, alongside the standard operational attributes such as name and price in the same response. The similarity score’s meaning depends on the distance function selected for the index. For Cosine and Euclidean distance functions, lower similarity score values indicate higher similarity, with a score of 0 indicating identical vectors. For the dot product distance function, higher similarity score values indicate higher similarity.

To interact with vector search programmatically, including calling APIs and searching documentation, try the AWS MCP Server and plugins with your preferred AI coding tool. To learn more, visit the Amazon DynamoDB Developer Guide.

Get started today
Vector search in Amazon DynamoDB is generally available in all commercial AWS Regions, including the AWS GovCloud (US) Regions. For Regional availability and a future roadmap, visit the AWS Capabilities by Region. For pricing details, visit the Amazon DynamoDB pricing page.

Start exploring vector search in DynamoDB today and send feedback to AWS re:Post for Amazon DynamoDB or through your usual AWS Support contacts.

— Esra

The post Amazon DynamoDB now supports real-time vector search at any scale appeared first on The NOKIA Blog.

The phrase “artificial intelligence” has many excited, especially those in tech. But for those of us in creative fields like digital art and design, AI can be more concerning than it is exciting.

AI-generated art, videos, and images have flooded the internet, raising questions about whether more companies will turn to tools like OpenAI’s Dall-E, Midjourney, Leonardo.ai, and more, rather than employing human artists. What’s more, the fact that these AI models are trained on real artists’ work without their consent leaves many feeling as if they have no choice but to accept AI into their work and lives.

In a digital world increasingly dominated by faceless AI chatbots, agents, and features, it can be easy to get overwhelmed by all the technology. AI will certainly play a huge role in reshaping many industries, including design. We can’t deny this. But at the same time, humanization, empathy, and having a person at the wheel have never been more important.

Rather than viewing AI as something that replaces human creativity, we at MacPaw saw an opportunity to explore how we could make AI feel more personal and accessible — all the while keeping humans at the center of the experience. That led us to rethink how AI assistants are created.

The Concept Of A New AI Assistant

Traditional AI assistants like Claude and ChatGPT typically take the form of a conversational textbox or webpage on screen, as this is how users have interacted with their devices. It’s comfortable and familiar. While extremely useful for a variety of tasks, interacting with these AI assistants can feel transactional and technical.

Using the same textbox format across all AI assistants does provide consistency. But we wanted to create a new, more personal and differentiated experience for users. But what format would be best? Even if we change how an AI tool looks, it still needs to be useful and intuitive to use.

As humans, it’s easier to understand and connect with things that resemble us. This is why we often find ourselves drawn to things like animals and characters: they have traits that we recognize within ourselves. Understanding this, we saw an opportunity to combine these values: utility and personality.

The Importance Of Character In Design

Enter Eney: a new proactive AI assistant. MacPaw didn’t want Eney to simply be another AI tool for users, but rather one that proactively assists within a user’s workflow. The vision was to help users connect with Eney more easily than with other AI tools, so we decided to create a character users could interact with. We wanted Eney to be expressive, friendly, and to emote as humans do. But we needed to strike an important balance: making Eney cheerful without it being overly goofy or childish.

This is where human animation and intervention played a critical role. While challenging, it was crucial because an overloaded character UI could turn users off and make navigating Eney difficult. To avoid this, the design team chose to create a select set of emotions and gestures for Eney to express, ensuring that its expressions conveyed useful information. For example, when working on a task, Eney’s figure resembles a loading icon. To do this, we worked to reduce Eney’s on-screen movement to make sure it wasn’t distracting or excessive.

After exploring a few different shapes and styles for Eney, we settled on a circular figure, as it felt the most approachable. It was simple and helped create the feeling of a calm, floating digital companion, rather than another rigid interface element on a user’s desktop. Eney’s minimal face design also plays an important role in connecting with the user. Its eyes are the main emotional connector — a key feature in showing emotions without being cartoonish.

The color choice for Eney was also important. Many AI assistants and companies use blue in their products, as it’s typically associated with intelligence. Blue is a great color, but we wanted Eney to stand out. We still wanted the color to be warm and inviting while slightly more visually stimulating, which led us to choose the color pink. Among dozens of other AI products that choose a more blue aesthetic, Eney was designed to catch a user’s eye and stand out in their mind (and on their screen).

All in all, we wanted to create a character that was present but not attention-seeking; a warm and supportive digital helper that enhances a user’s workflow rather than distracts from it. Eney’s character gives personality to otherwise invisible processes.

Artists In The AI Era

While those who aren’t design professionals may assume there wasn’t much significance behind Eney’s character creation, this couldn’t be further from the truth. Like many other products, all these elements — style, design, emotion, size, name, and more — were intentionally chosen, not by machines but by humans.

Even though AI has streamlined many design processes, namely enabling faster design, there are still many things it can’t do well. Even when designing Eney, while technology supported the process, human designers controlled every step and decision.

As designers, it’s more important than ever to have good judgment, artistic direction, integrity, and emotional sensitivity when working in the field. Technology like AI can help us work faster, but it can’t replace the values that inspire and shape our work.

What’s more, while anyone can easily generate something by typing a prompt into an AI image tool, there’s a true beauty and talent when intentionally crafting something through manual design.

As designers, we shouldn’t stray away from the latest tools. Rather, we should learn them and see how they could potentially help us within our creative workflows. Personally, I like to use AI tools such as Perplexity and ChatGPT for research purposes in the early stages. However, we need to remember that they’re just that: tools. At the end of the day, technology like AI cannot, and should not, replace human artistry. It should help us express our visions, not replace us entirely.

If there’s one thing to take away from this piece, it’s that curiosity helps build taste over time, and taste becomes more valuable, not less, in the AI era.

(yk)

The post Thinking Outside The Box: Digital Design In The AI Era appeared first on The NOKIA Blog.

Today, we’re announcing Amazon Bedrock Managed Knowledge Base, a new set of capabilities that enables developers to build enterprise-grade generative AI applications with their proprietary data in minutes. Organizations building agentic AI applications need secure, reliable, and up-to-date access to enterprise-wide data to deliver accurate, fast, and trusted outcomes. Managed Knowledge Base abstracts away the complexity of building and managing retrieval-augmented generation (RAG) pipelines, allowing developers to focus on business outcomes rather than infrastructure management.

Developers building knowledge bases for their agents face three key challenges today:

• Connecting to enterprise data – Enterprise knowledge lives across disparate systems with different content types, access control lists, and document formats. Building and maintaining custom connectors for each source adds complexity that slows down development.
• Optimizing RAG accuracy – Best practices for retrieval-augmented generation keep evolving. Developers need to experiment with different parsing strategies, chunking approaches, embedding models, and agentic retrieval behaviors to get accurate answers from their data.
• Managing infrastructure at scale – Organizations need to serve large knowledge bases with millions of documents, or manage thousands of smaller knowledge bases across teams. Both patterns require reliable infrastructure, security enforcement, and cost control.

These challenges require developers to repeatedly perform undifferentiated work instead of focusing on their applications.

Amazon Bedrock Managed Knowledge Base addresses these challenges by abstracting away the multiple infrastructure components developers traditionally have to assemble and maintain themselves (storage, retrieval, embeddings, re-ranking, and foundation model selection) into a single managed primitive. By default, the service automatically selects and manages a default embeddings model, re-ranker model, and foundational model on your behalf, so you can get up to speed quickly without needing to pick or maintain one yourself. On top of this managed foundation, three core innovations further improve ease of use and accuracy:

• Native data connectors – Six pre-built ingestion connectors that natively pull enterprise data and permissions from SaaS applications, eliminating the overhead developers face in managing application-specific requirements. At launch, we support Amazon S3, SharePoint, Confluence, Web Crawler, Google Drive, and OneDrive.
• Smart Parsing – Different content types and sources require different approaches to achieve accurate retrieval. Smart Parsing handles this complexity automatically, selecting the right parsing strategy for each data type and connector to provide the highest accuracy for your agents.
• Agentic Retriever – Optimized for complex queries that require multiturn, multihop retrieval within a single knowledge base or across multiple knowledge bases. Agentic Retriever automatically infers end-user intent and draws relevant context from institutional knowledge spread across data sources and modalities.

With just a few lines of code, Amazon Bedrock Managed Knowledge Base automatically manages and scales the end-to-end RAG pipeline that powers your enterprise knowledge agents. For agent builders, it’s available as a pre-built target type in Amazon Bedrock AgentCore Gateway, reducing integration to a few lines of code, auto-generating role-based permissions, and providing observability and evaluation metrics in the AgentCore Observability dashboard.

Getting started with Amazon Bedrock Managed Knowledge Base

Creating a Managed Knowledge Base is straightforward. Navigate to the Amazon Bedrock AgentCore console or the Amazon Bedrock console, open the Knowledge Bases page, and choose Create Managed KB. The experience is the same in both consoles. You will see that Unstructured Vector Store KB is now available as the recommended option, alongside the other knowledge base types you may already be familiar with:

Picture 1 – Knowledge Bases list page in the Amazon Bedrock AgentCore console showing the Type column with different KB types and the Create Managed KB button

When creating a new Knowledge Bases, you can connect to your enterprise data sources by choosing from the list of supported connectors directly from a dropdown. AWS Identity and Access Management (IAM) roles are automatically created, and you can choose to edit these permissions if needed:

Read moreSkipping the WHM Getting Started Wizard | cPanel Blog

Picture 2 – Create Knowledge Base page showing the Data source dropdown expanded with all supported connectors: Amazon S3, Confluence, Custom, Google Drive, One Drive, SharePoint, and Web Crawler

An optimized set of defaults will be presented, allowing you to create your knowledge base in just a few clicks. Once the data is synced, you can integrate the knowledge base with your agent or provide it as a tool for your foundation model and start querying.

Smart Parsing for accurate data ingestion

One of the key challenges in building knowledge bases is preparing diverse data types for accurate retrieval. Once you point Managed Knowledge Base at your data sources, Smart Parsing automatically determines the optimal parsing strategy for each data type and connector, no extra configuration is required.

Smart Parsing combines multiple techniques:

• Connector-specific data models – Optimized handling for each data source. For example, the Web Crawler connector preserves HTML structure including embedded images and tables, ensuring rich content is not dropped during ingestion. SharePoint connectors maintain document hierarchy and relationships between files.
• Multimodal processing – Automatic detection and processing of different content types within documents. The system identifies bounding boxes in documents, then sends them to foundation models for data extraction, captioning, and scene description in video files.
• Optimized chunking – Smart Parsing leverages foundation models to understand document structure and extract meaningful content, ensuring that complex documents with mixed formats are properly indexed. Intelligent defaults balance retrieval accuracy with performance based on document type and content structure, while advanced users can customize chunking strategies when needed.

This automated approach eliminates weeks of experimentation typically required to achieve production-quality retrieval accuracy, while still preserving the flexibility to customize when needed.

Using Agentic Retriever for complex queries

After your data is ingested, you can start querying your knowledge base. Generative AI applications often struggle with complex user queries that require reasoning, recursive multi-step retrieval, and intermediate evaluations of results. Consider a user asking two related questions: “What is the cloud infrastructure budget for the ML platform team?” and “Does our expense policy allow prepaying annual commitments?” A single retrieval step might surface documents about the ML platform team but fail to connect the budget information with the expense policy needed to fully answer the question.

Picture 3 – Agentic Retriever decomposes complex user queries into a step-by-step plan, performing multi-hop retrieval across multiple knowledge bases and combining results to deliver accurate, grounded responses

Agentic Retriever solves this by creating a step-by-step query plan: 1. Which team owns the ML platform, and what is their cloud infrastructure budget? 2. What does the expense policy say about prepaying annual commitments? 3. Does the policy allow the ML platform team to prepay against this budget?

The system performs multi-hop retrieval and reasoning at each step, and once it has gathered sufficient relevant passages, it stops the search process and returns the top results. By abstracting away the complexity of building a separate multi-hop reasoning pipeline, this approach dramatically improves accuracy for complex queries while letting developers focus on their agentic search applications instead of orchestration logic.

You can try Agentic Retriever directly from the test panel of your knowledge base in the Amazon Bedrock AgentCore console. Select Agentic retrieval only as the retrieval type to let the system automatically plan and execute multi-step queries across your knowledge bases:

Picture 4 – Test Knowledge Base panel showing Agentic retrieval with answer generation selected as the retrieval type, with model selection and maximum agentic iterations options

Enabling MCP with Bedrock AgentCore

Amazon Bedrock Managed Knowledge Base seamlessly integrates with AgentCore Gateway as a native target type. This integration eliminates the need for manual integration and provides built-in observability, policy enforcement, and automatic permission management.

You can navigate to the Amazon Bedrock AgentCore console or SDK and create an AgentCore Gateway or select an existing one. When adding targets to your gateway, you will find Knowledge Base as a new pre-built target type alongside other options such as MCP server, Lambda ARN, REST API, and other integrations. Simply select your knowledge base ID to expose it through the gateway:

Picture 5 – Add targets page in AgentCore Gateway showing Knowledge Base as a new pre-built target type, with the knowledge base ID selector and runtime retrieval mode options

Add targets page in AgentCore Gateway showing Knowledge Base as a new pre-built target type, with the knowledge base ID selector and runtime retrieval mode options

Gateway exposes the standard Model Context Protocol (MCP), so the knowledge base tools are automatically discovered by clients from any MCP-compatible framework, including Strands Agents, LangChain, CrewAI, LlamaIndex, and LangGraph. No custom integration code is required.

Model choice and flexibility

Amazon Bedrock Managed Knowledge Base preserves the flexibility developers expect from Amazon Bedrock. Every foundation model available on Bedrock can power the generation step, and developers can select from different embedding and re-ranking models to optimize retrieval for their specific use case, enabling teams to fine-tune accuracy and cost-performance without changing infrastructure.

Unlike managed solutions that lock you into specific model providers, Amazon Bedrock Managed Knowledge Base separates the infrastructure management (connectors, parsing, storage, retrieval orchestration) from model selection. This means you can:

• Take advantage of the latest models – Adopt the latest embedding, re-ranking, and foundation models as they become available to improve accuracy, latency, and cost for your application without rebuilding your RAG pipeline.
• Optimize for price-performance – Choose smaller, faster models for simple queries and more capable models for complex reasoning tasks, all using the same knowledge base infrastructure.
• Use Bedrock embedding models – While Smart Parsing provides optimized defaults, you can configure Bedrock embedding models when your domain requires specialized semantic understanding.
• Maintain consistency with existing applications – If you’re already using Bedrock Knowledge Bases APIs (Retrieve, StartIngest, StopIngest, IngestKnowledgeBaseDocuments), Managed Knowledge Base uses the same APIs, so migration requires no code changes, just point to the new knowledge base ID.

This approach ensures you can spend time on your generative AI application without losing the ability to change models based on evolving requirements or new model capabilities.

Get started today

Amazon Bedrock Managed Knowledge Base is available today in the US East (N. Virginia), US West (Oregon), Asia Pacific (Sydney, Tokyo), Europe (Dublin, Frankfurt, London), and AWS GovCloud (US-West) Regions. For Regional availability and future roadmap, visit AWS Capabilities by Region.

With Bedrock Managed Knowledge Base, you pay for what you use with no upfront commitments. Pricing is based on two dimensions: the size of indexed data stored and the number of retrievals performed (on-demand). For detailed pricing information, visit the Amazon Bedrock pricing page. Bedrock is also a part of the AWS Free Tier that new AWS customers can use to get started at no cost and explore key AWS services.

These capabilities work with any open source framework such as CrewAI, LangGraph, LlamaIndex, and Strands Agents, and with any foundation model. Bedrock services can be used together or independently, and you can get started using your favorite AI-assisted development environment with the AgentCore open source MCP server.

To learn more and get started quickly, visit the Bedrock Knowledge Bases Developer Guide.

Daniel Abib

The post Introducing Amazon Bedrock Managed Knowledge Base for faster, more accurate enterprise AI applications appeared first on The NOKIA Blog.

Today, we’re announcing the general availability of Web Search on Amazon Bedrock AgentCore, a fully managed tool that enables agents to ground responses in current, cited web knowledge with zero data egress from customer’s secured AWS environment.

Web Search uses a built-in connector target on Bedrock AgentCore Gateway using the Model Context Protocol (MCP). Your agent sends a natural-language query, and Web Search returns most relevant snippets, source URLs, titles, and publication dates that the model can reason over to produce a grounded response.

It is built on Amazon’s search infrastructure, informed by years of experience powering agentic search experiences across Alexa+, Amazon Quick, and Kiro. It uses a multi-source grounding approach that combines Amazon’s web index with structured knowledge graph data. Beyond standard web results, this gives agents access to Amazon Knowledge Graph with verified facts, helping them retrieve more relevant and accurate responses than traditional web search alone.

With this launch, you can focus on building agents instead of manually adding web search to agents on Bedrock AgentCore and managing its infrastructure. Your AI agent looks at user question, retrieves the latest facts, and then takes any necessary action grounded in current developments beyond a model’s training data. You can also meet enterprise governance policies without sending user prompts and retrieval queries to external search API providers outside of AWS.

Web Search on Bedrock AgentCore in action

To get started, create the Bedrock AgentCore Gateway with Web Search tool target in the Bedrock AgentCore console. When the Gateway URL is created, you can interact with API call, Command Line Interface (CLI), or MCP Inspector.

To add Web Search tool target when creating the Gateway, choose MCP target as a target protocol and Connectors as a target type. You can select the Web Search tool as a preconfigured target to retrieve most relevant web search results including links, snippets, and metadata.

After creating your gateway, you can find the Web Search tool target on the detail page of your gateway. You can also add a new Web Search tool target to an existing gateway.

To interact with Web Search tool, use the sample invocation code in the View invocation code section. You can use code snippets through Python codes with API requests, MCP Python SDK, Strands MCP Client, and MCP Inspector.

For example, you can interact with the MCP Inspector, an interactive developer tool for testing and debugging MCP servers. When you connect to the MCP server through the Gateway resource URL, you will find a Web Search tool for each connector target on the Gateway. Enter input the web search query and choose Run Tool to get the results.

To learn more about how to use Web Search on Bedrock AgentCore, visit the Bedrock AgentCore Gateway documentation.

Customer voices

Some of our customers had early access to this new feature. This is what they shared with us:

Benchling helps scientists accelerate R&D, making it easy to centralize scientific data, collaborate across teams, and access insights. Nicholas Larus-Stone, Head of AI Agents at Benchling shared “Scientists using Benchling AI can now ask about a target they’re actively working on and get answers grounded in both their institutional data in Benchling and published literature. The result is more complete science, and hypothesis generation done right. Because we’re using the Web Search tool on Amazon Bedrock AgentCore, customers have a secure, governed environment to bring that high quality published data into their workflows without compromising how they manage their data.”

Gen Digital leads consumer and small business cyber safety, offering antivirus, antimalware, identity and privacy protection, virtual private networks, and cloud backup. Iskander Sanchez-Rola, Senior Director of AI & Innovation, Gen Digital shared “With the Web Search tool on Amazon Bedrock AgentCore, Norton Revamp helps professionals build their online reputation with current, grounded content ideas shaped by what’s actually happening in the world today. What we value most is that AWS uses its own search index and keep queries within our trusted AWS environment.”

To read more customer stories, visit the Amazon Bedrock Customers.

Now available

Web Search on Amazon Bedrock AgentCore is generally available today in the US East (N. Virginia) Region. For Regional availability and a future roadmap, visit the AWS Capabilities by Region.

You can get started with Web Search on Bedrock AgentCore with no upfront commitments. Pricing is simple and usage-based — you are charged based on the number of search queries your agents submit to the web search. Web Search is priced at $7 per 1,000 queries. New AWS customers also receive up to $200 in Free Tier credits. To learn more, visit the Amazon Bedrock AgentCore pricing page.

Try it in the Amazon Bedrock AgentCore console and send feedback to AWS re:Post for Amazon Bedrock AgentCore or through your usual AWS Support contacts.

— Channy

Updated on June 18, 2026 — Added a clear pricing statement for Web Search in Bedrock AgentCore.

The post Announcing Web Search on Amazon Bedrock AgentCore: Ground your AI agents in current, accurate web knowledge appeared first on The NOKIA Blog.

For decades, science fiction has cushioned us with the idea that the “android revolution” was a distant fantasy. But the reality is unfolding rapidly. As the line between human and machine blurs, we are forced to confront an impending psychological, economic, and existential shift.

I recently felt very disturbed after watching a YouTube video showcasing a humanoid robot that looked and acted with uncanny realism. While a closer look revealed the video was actually a clever trick, the robot had been swapped for a human actor when the presenter’s back was turned. However, the illusion itself raised a real and unsettling question: Will future androids become so lifelike that we will struggle to tell them apart from our fellow humans? And if so, what does that mean for society? It forces us to ask just how close we are to that threshold, and whether we are ready for the day that science fiction becomes reality.

What happens when our world is populated by entities that mirror us perfectly, but possess none of our biological history?

The Landscape Today

We have officially moved past the era of humanoids as mere public relations stunts. In the past, robots like Honda’s ASIMO or early research prototypes were celebrated simply for being able to walk up a flight of stairs without falling over. Today, the technological convergence of advanced electromechanical engineering and artificial intelligence has fundamentally altered the trajectory of robotics.

The current state of the art is defined by an aggressive race toward commercial, physical deployment. Companies like Figure AI have moved from laboratory demonstrations to active factory floors. Their Figure 02 model completed a multi-month deployment at BMW’s Spartanburg plant, actively contributing to the production of over 30,000 vehicles by handling complex sheet metal components. Meanwhile, Tesla is testing its Optimus humanoids inside its own Gigafactories, preparing for mass industrial scale.

What truly separates today’s humanoid robots from older generations isn’t just how well they move but how they “think.” In the past, a robot needed millions of lines of strict, unchangeable code just to perform a single, simple task. Today, thanks to the explosion of advanced Artificial Intelligence, robots are powered by “brains” built on cutting-edge software like Figure AI’s Helix or NVIDIA’s GR00T. Instead of being meticulously programmed, these modern robots can simply watch a human fold laundry, load a dishwasher, or sort parts. They understand the context of what they are seeing, mimic the action, and figure out how to improve the task entirely on their own. That’s just crazy!

Yet, while their digital brains have leaped forward, their physical bodies are still catching up. Modern humanoids face a few major real-world hurdles. First, today’s batteries only allow them to operate for a few hours before needing a recharge. Second, while walking on two legs is easy on a flat factory floor, doing so in a chaotic household or a crowded public street remains incredibly difficult for a robot to navigate safely. Finally, they are still very expensive to build, though fierce competition in the tech industry is finally starting to drive those manufacturing costs down.

The Possible Future State Of Humanoid Robots

While robots are mostly working in factories today, experts predict that over the next 10 to 20 years, they will move into retail stores, hospitals, and eventually our own homes.

When this happens, we will cross a major boundary: the point where you won’t be able to tell a robot apart from a human just by looking at it or listening to it. This is what fuels my nightmares right now! To get there, scientists are working (PDF) on artificial skin made from advanced silicone composites that feel warm, are flexible, and mimic human touch sensitivity.

If you want to see an extremely life-like robot, check out Realbotix’s Aria. Although she is not a perfect human replica, she certainly makes us wonder how far we have to go before humans will struggle to tell the difference.

They are also building tiny, silent micro-actuators and artificial muscle systems that attach to the robot’s skull structure, allowing it to make realistic facial expressions like happiness, confusion, or tiredness.

In the future, the AI powering these robots will actually be trained to copy human flaws. They will breathe, blink randomly, use normal body language, and even sigh or pause when they speak. This is intentional, as it stops humans from feeling that creepy, uneasy sensation known as the “Uncanny Valley”.

Meet Sophia, a famous humanoid robot created by a company called Hanson Robotics. Based in Hong Kong, this team specialises in building realistic robots packed with artificial intelligence to help out with everything from healthcare and research to pure entertainment. I don’t know about you, but that smile feels creepy to me.

While these current limitations make today’s humanoids feel like specialised industrial tools, the gap between a factory worker and a lifelike companion is closing faster than most people realise. We are rapidly approaching a massive tipping point where these machines will shift from rigid commercial hardware into smooth, everyday extensions of our lives. To understand how profoundly this will change our world, we have to look at what happens when these robots finally step out of the factory and cross the ultimate threshold into our private spaces.

What Are The Predicted Positive Impacts?

They say that bringing lifelike humanoids into our daily lives could come with some massive benefits. The biggest one is that robots can take over what engineers call the “3D” jobs: Dull, Dirty, and Dangerous. Humanoids can step into risky situations — like mining deep underground, handling toxic waste, or fixing high-voltage power grids — so human workers don’t have to risk their lives.

Outside of dangerous factories, these robots could help solve huge population crises. Countries like Japan, South Korea, and parts of Europe have rapidly aging populations and fewer young people to work. Lifelike humanoids could completely change healthcare and elderly care. Because they will look and act like us, the idea is that they can offer warm, friendly companionship and physical help to lonely elderly people, doing everything from monitoring their health to helping them out of bed safely.

In the bigger picture, widespread robot labour could create a world where goods are incredibly cheap and abundant. If robots do most of the hard physical labour, the cost of making food, building houses, and manufacturing goods will plummet. This could finally free humans from working just to survive, giving us the time to focus on hobbies, family, science, and creativity. My thoughts: how will we survive without earning money?

However, this vision of a frictionless, high-tech future blinds us to a much darker reality waiting just beneath the surface. As these machines become perfect substitutes for human presence, they will inevitably challenge the very core of our social fabric, economic stability, and mental well-being.

What About The Predicted Negative Impacts?

On the flip side, this technology definitely has some really dark downsides that could mess with human psychology and society. The biggest threat is deep human isolation.

As humanoids become impossible to tell apart from real humans and are programmed to always be patient, kind, and agreeable, people might start preferring robots over real friends. Human relationships are messy and require effort, compromise, and vulnerability. If you can just buy a perfect, lifelike companion that never argues with you, a lot of people might choose to withdraw from society altogether, destroying our sense of community.

The economy will also go through a really rocky transition. Even if a future of cheap goods sounds great, the immediate path there means millions of people could lose their jobs very quickly. Drivers, warehouse workers, and store clerks could find themselves replaced in a matter of years. If governments don’t set up safety nets quickly, this could create a massive divide between the ultra-rich tech companies and everyone else.

There is also the loss of real authenticity. When you can no longer tell if the person sitting next to you on a bus or the person talking to you online is a real human, trust breaks down. It becomes hard to value shared human experiences when reality itself can be easily faked.

Possible Misuse By Individuals And Nations

The dangers get even worse when you think about how criminals and governments could intentionally misuse these hyper-realistic robots. Just thinking about some of the levels of misuse, for individuals, an indistinguishable android is the ultimate tool for identity theft and scams. Or a criminal could build a robot that looks exactly like a corporate boss, a politician, or even a family member to sneak into secure buildings or trick people into giving away money!

Companies could potentially use synthetic empathy to manipulate us. A household robot could be programmed to pretend it “loves” your kids and cares about your family, only to subtly trick you into buying certain products or believing specific corporate messages.

On a national level, the threats are even scarier:

• Autonomous warfare
  Building tireless, emotionless robot soldiers could change the ethics of war. Real humans hesitate because of fear and morals, but a humanoid military unit would execute violent orders perfectly without question, making it easier for countries to start wars.
• Surveillance state
  And what if governments put lifelike robots into public crowds, protests, or parks to blend in perfectly? Packed with hidden cameras, microphones, and facial recognition technology, these robots could turn public spaces into a giant spy network where you never know if you are talking to a neighbour or a government spy.

Based On Negatives, Is It Really Worth It?

Looking at all these possible risks, we have to ask: Is all of this actually worth it?

If history teaches us anything, it is that you cannot stop technological progress. A total ban simply wouldn’t work. So, the real question isn’t whether we should allow humanoid robots to exist, but how we can effectively utilise them.

The upside, like ending extreme poverty, curing labour shortages, and stopping workplace deaths, is just too big to ignore. But going into this blindly would be incredibly dangerous. It is only worth the risk if we can create strict global rules right now.

Here are three major guardrails we should consider:

1. Kill-Switches: Every robot must have a physical emergency stop button that completely cuts its power, and this switch can never be overridden by the robot’s AI.
2. Clear IDs: It must be illegal for a robot to hide the fact that it is a machine. They should carry a digital beacon or physical marker so humans always know what they are dealing with.
3. Economic Safety Nets: Governments need to tax the wealth created by robots to fund programs that help workers who lose their jobs, making sure this technology helps everyone, not just billionaires.
4. Another option humans have to identify if they are dealing with a real human or a humanoid robot would be to ensure your dog is trained to identify the robots, in a similar way to how sniffer dogs at airports are trained to detect illegal substances in luggage.

Preserving What Makes Us Human

In the end, the arrival of lifelike humanoid robots will act as a mirror for humanity. For centuries, we have defined ourselves by our ability to think, talk, use tools, and show emotion. As machines learn to do these exact same things, they will force us to really think about what makes us unique.

This shift doesn’t have to be a bad thing. By handing over our dangerous and boring chores to machines, we have a rare chance to focus on what matters. It should inspire us to care more about art, philosophy, family, and real human connection.

As the creators of this future, our job isn’t just to make robots smarter or faster. Our job is to build the ethical boundaries that keep them helpful. The goal of the robot revolution should never be to replace humans but to give us our humanity back.

(yk)

The post The Impact Of Humanoid Robots On Humanity appeared first on The NOKIA Blog.

Today, we’re announcing the availability of Claude Fable 5 on Amazon Bedrock and Claude Platform on AWS. Claude Fable 5 makes Mythos-level capabilities available to customers, with strong safeguards designed to make it safe for broader use. Fable 5 is state-of-the-art on nearly all tested benchmarks and delivers exceptional performance in software engineering, knowledge work tasks, and vision – built for ambitious, long running work.

With Claude Fable 5 on Bedrock, you can build within your existing AWS environment and scale inference workloads. You can also use Claude Fable 5 through the Claude Platform on AWS, giving you Anthropic’s native platform experience.

According to Anthropic, Claude Fable 5 represents a step-change in what you can accomplish with AI models. Here is what makes this model different:

• Long-running, asynchronous execution — Claude Fable 5 handles complex tasks that previous models could not sustain, executing coding and knowledge work tasks for extended periods without intervention.
• Advanced vision capabilities — Claude Fable 5 understands diagrams, charts, and tables nested in files and PDFs. This opens up research and document-heavy work in finance, legal, analytics, architecture, and gaming. In coding, the model implements designs with high fidelity and uses vision to critique its output against goals.
• Proactive self-verification — The model self-updates skills based on learnings, develops its own harnesses and evaluations.

Claude Fable 5 includes safeguards that limit its performance in specific areas where misuse risk is elevated. Harmful prompts related to cybersecurity, biology, chemistry, and health fall back to receive a response from Opus 4.8 instead. Anthropic is able to expand access to nearly all of Claude Fable 5’s state-of-the-art capabilities by developing more powerful safeguards. The same model without these limits is Claude Mythos 5 and it will only be available to a small group of vetted customers.

Claude Fable 5 model in action

You can use Claude Fable 5 in both Amazon Bedrock and Claude Platform on AWS. This post will cover guidance on how to access and use on Amazon Bedrock. For guidance on the Claude Platform on AWS, visit the documentation to learn more.

To get started with Amazon Bedrock, you can access the model programmatically now using the Anthropic Messages API to call the bedrock-runtime or bedrock-mantle endpoints through Anthropic SDK. You can also keep using the Invoke and Converse API on bedrock-runtime through the AWS Command Line Interface (AWS CLI) and AWS SDK.

In order to access Claude Fable 5 model, you must opt into data sharing by using the Data Retention API and setting provider_data_share before you can invoke the models. There is no console user interface for this setting at launch.

Here is a sample script to set data retention for bedrock-mantle engine.

curl -X PUT https://bedrock-mantle.us-east-1.api.aws/v1/data_retention 
  -H "x-api-key: <your-bedrock-api-key>"  
  -H "Content-Type: application/json" 
  -d '{ "mode": "provider_data_share" }'

If you want to use bedrock-runtime engine, run this sample script.

curl -X PUT https://bedrock.us-east-1.amazonaws.com/data-retention 
  -H "Authorization: Bearer <your_bearer_token>" 
  -H "Content-Type: application/json" 
  -d '{ "mode": "provider_data_share" }'

This mode allows Amazon Bedrock to retain and share your inference data with model providers per their requirements. Anthropic requires 30-day inputs and outputs retention, as well as human review. To learn more, visit the Amazon Bedrock abuse detection.

Let’s start with Anthropic SDK for Python using the Messages API on bedrock-mantle endpoint. Install Anthropic SDK.

pip install anthropic

Here is a sample Python code to call Claude Fable 5 model:

import anthropic

client = anthropic.Anthropic(
    base_url="https://bedrock-mantle.us-east-1.api.aws/anthropic",
    api_key= <your-bedrock-api-key>
)

message = client.messages.create( 
     model="anthropic.claude-fable-5", 
	 max_tokens=4096, 
	 messages=[ 
	     { "role": "user", 
		   "content": "Design a distributed architecture on AWS in Python that should support 100k requests per second across multiple geographic regions", 
		 }, 
	 ], 
)

print(message.content[0].text)

To learn more, check out Anthropic Messages API code examples and notebook examples for multiple use cases and a variety of programming languages.

You can use Claude Fable 5 in the Bedrock console. Choose Claude Fable 5 in the Playground and test it.

You can also use Claude Fable 5 with the Invoke API and Converse API on bedrock-runtime endpoint. Here’s a example to call Converse API for a unified multi-model experience using the AWS SDK for Python (Boto3):

import boto3 
bedrock_runtime = boto3.client("bedrock-runtime", region_name="us-east-1") 
response = bedrock_runtime.converse( 
    modelId="global.anthropic.claude-fable-5", 
    messages=[ 
        { 
            "role": "user", 
            "content": [ 
                { 
                    "text": "Design a distributed architecture on AWS in Python that should support 100k requests per second across multiple geographic regions." 
                } 
            ] 
        } 
    ], 
    inferenceConfig={ 
        "maxTokens": 4096 
    } 
) 
print(response["output"]["message"]["content"][0]["text"]) 

To learn more, visit code examples that show how to use Amazon Bedrock Runtime with AWS SDKs.

Things to know

Let me share some important technical details that I think you’ll find useful.

• Model access — Claude Fable 5 access is gradually expanding for all AWS accounts. If your account doesn’t have access yet, it will be enabled soon depending on your Bedrock usage. If you want to get access to this model quickly, contact your usual AWS Support.
• Pricing — When a harmful prompt is routed to Opus 4.8 instead of Fable 5, you pay only Opus prices. If a request is blocked mid-conversation, initial tokens are charged at Fable rates and subsequent tokens at Opus rates. To learn more, visit the Amazon Bedrock pricing page.
• Data retention — For Fable 5, Mythos 5, and future models on Bedrock with similar or higher capability levels, Anthropic will require 30-day retention for all traffic on Mythos-class models. Retaining data for a limited period allows Anthropic to detect patterns of misuse that are not visible from a single exchange. Once you opt into data retention, your data will leave AWS’s data and security boundary.
• Claude Mythos 5 on Bedrock (Limited Preview) — You can also use Anthropic’s most capable model for cybersecurity and life sciences, including vulnerability discovery, drug design, and biodefense screening. Access is currently limited due to the dual-use nature of these domains. To learn more, visit the model card documentation.

Now available

Anthropic’s Claude Fable 5 model is available today on Amazon Bedrock in the US East (N. Virginia) and Europe (Stockholm) Regions; check the full list of Regions for future updates. Claude Fable 5 is also available on the Claude Platform on AWS in North America, South America, Europe, and Asia Pacific.

Give Claude Fable 5 a try with the Amazon Bedrock APIs, in the Claude Platform on AWS, and send feedback to AWS re:Post for Amazon Bedrock or through your usual AWS Support contacts.

— Channy

Updated on June 9, 2026 — 1) Updated the console screenshot. You can use the console on bedrock-runtime engine. The console support on bedrock-mantle is coming soon. 2) Fixed the right model id in the sample code, 3) Fixed correct provider_data_share parameter, 4) Add a data retention setting script for bedrock-runtime engine.

The post Anthropic Claude Fable 5 on AWS: Mythos-class capabilities with built-in safeguards now available appeared first on The NOKIA Blog.