Articles

News about Artificial Intelligence

<hr /> It's a regular Wednesday eve, and you are rushing against the clock to update the material on your website. A product launch is approaching, and every second matters. While you're methodically fine-tuning the pages of your website, you're bombarded with consumer questions, each begging for your attention. It appears like the digital world never sleeps.A friendly AI-powered <a target="_blank" href="https://en.wikipedia.org/wiki/Chatbot">chatbot</a> on your <a target="_blank" href="https://cmscritic.com/what-is-a-content-management-system-cms">Content Management System (CMS)</a> is here to improve your website. It's not a human intern or an overwhelmed support person; it's designed to help.The deployment of chatbots has revolutionized AI-driven conversational interfaces in CMS. In this article, we'll delve into the evolution of chatbots and their crucial role in Content Management Systems. <h3>Defining the significance of chatbots in Content Management Systems (CMS)</h3>Chatbots are AI-powered virtual assistants designed to engage users in natural language conversations. Think of them as the digital world's Swiss Army knives – capable of autonomously handling customer inquiries, providing product information, and processing orders. Chatbots have become indispensable companions for website owners and businesses of all sizes in Content Management Systems. They assume the role of intelligent gatekeepers, enabling efficient web content management while ensuring your customers' voices are heard and their needs met. Whether you're a budding software unicorn or an e-commerce startup, integrating chatbots into your CMS can yield transformative results.<h3>Advancements in technology</h3><a target="_blank" href="https://en.wikipedia.org/wiki/Artificial_intelligence">Artificial Intelligence (AI)</a> has traversed a considerable distance, transcending its initial status as a mere buzzword to emerge as a catalytic force driving transformation across diverse industries. Within the domain of chatbots, AI's relentless progress stands as the chief catalyst propelling their evolution.Keeping this in mind, let’s have a look at some innovations in AI technology:<ul><li>Natural language processing: AI has evolved to grasp human language remarkably akin to our comprehension. NLP algorithms empower chatbots to discern context, tone, and even sentiment within the text, adding user interactions with a heightened sense of humanity and empathy.  </li><li>Machine learning: Chatbots have transcended the confines of rule-based responses. Machine learning algorithms enable them to glean insights from every conversation, progressively enhancing their intelligence with each interaction. They adeptly tailor recommendations and solutions based on user behavior and preferences.  </li><li>Voice and visual recognition: The future of chatbots extends well beyond text-based interactions. Voice and visual recognition technologies empower chatbots to communicate through speech and images, expanding their applications within CMS and across diverse domains.  </li><li>Integration with CMS platforms: Contemporary CMS platforms embrace chatbot integration with open arms, furnishing APIs and plugins that simplify the process. This mutually beneficial relationship between CMS and AI chatbots streamlines content management and augments the quality of customer interactions.</li></ul><h3>Benefits of AI chatbots in CMS</h3>Integrating chatbots into CMS platforms is transformative. Here's how it could revolutionize content management:<ul><li>Simplified content updates: Content updates and revisions are part and parcel of managing a website or application. Content marketers may additionally expedite these processes via integrating chatbots into CMS. Chatbots might also assist with content material identity, recommend pertinent updates, or even make minor modifications, releasing up human sources for extra tough obligations.   </li><li>Content recommendations: Chatbots can also examine consumer interactions with website content and provide content material writers with important information. They can propose subjects currently trending or in excessive demand, helping content managers create more relevant and pleasing content.   </li><li>Real-time analytics: Understanding user behavior is critical for developing a powerful content strategy. This is when chatbots come in handy! Chatbots utilize actual-time analytics to reap insights into personal behavior and preferences, which may be used to enhance content, layout, and the general user experience.  </li><li>SEO Optimization: <a target="_blank" href="https://en.wikipedia.org/wiki/Search_engine_optimization">Search Engine Optimization (SEO)</a> is critical for driving organic website traffic. Chatbots can assist in SEO optimization by analyzing keyword trends, suggesting relevant keywords for content material, and tracking the internet site's search engine ranking. This guarantees that the content stays visible to the target market. </li></ul><h3>Crucial challenges in AI integration to CMS</h3>While the integration of AI-driven chatbots into CMS brings significant benefits, it also presents some challenges:<ul><li>Data quality and availability: AI algorithms require outstanding and relevant data to function correctly. Many corporations seek to acquire and keep the necessary data for AI integration, and CMS systems might not usually offer clean admission to the required data resources.   </li><li>User acceptance and training: Users, including content material creators and administrators, might also withstand AI integration due to worry of activity displacement or the accuracy of AI-driven decisions. Providing good enough training and demonstrating the advantages of AI can be tricky.   </li><li>Ethical and regulatory compliance: Ensuring that AI-powered CMS solutions adhere to ethical standards and comply with relevant regulations, such as data privacy laws (e.g., GDPR), can be complex. Organizations must be vigilant in handling sensitive information and averting bias in AI algorithms.   </li><li>Scalability: Scalability is essential as organizations grow and produce more content. Maintaining the performance and responsiveness of AI-driven CMS features as the content volume and user interactions increase can be a significant technical challenge.</li></ul>Addressing these challenges requires careful planning, resources, and a clear strategy for integrating AI into CMS effectively. It also involves monitoring and adapting to evolving technologies and user needs<h3>What lies ahead for generative AI and Chatbots?</h3>The next step in generative AI for chatbots involves creating more advanced conversational agents that naturally understand and respond to human language. This includes integrating generative AI with deep learning, neural networks, and natural language processing technologies.One potential advancement is enabling chatbots to recognize and respond to human emotions by integrating emotional recognition technology. For instance, a chatbot could detect when a customer is frustrated and respond empathetically.Another area of improvement is enabling chatbots to have more complex conversations. This involves integrating generative AI with advanced natural language processing to understand and respond to intricate sentence structures, idiomatic expressions, and context.<h3>Conclusion</h3>The future of chatbots in CMS involves AI and human-machine interaction. As technology advances, businesses and website owners must adapt, harnessing AI-driven chatbots to enhance user experiences and streamline operations. Don't lag; let AI-driven chatbots guide you into a future where your website thrives, and your customers always feel heard and valued!

The Future of Chatbots: AI-Driven Conversational Interfaces in CMS

hardik-shah

As generative AI continues to march its way across the digital experience stack, platforms are looking to public cloud providers like <a target="_blank" href="https://cmscritic.com/aws-joins-mach-alliance-as-enabler-member-reflects-growth-of-cloud-native-solutions">AWS</a>, <a target="_blank" href="https://cmscritic.com/contentstack-offers-microsoft-azure-becomes-only-multi-cloud-saas-cms-qa-with-cto-nishant-patel">Azure</a>, and GCP to help scale their innovation and get AI-powered products to market faster. Now, <a target="_blank" href="https://cmscritic.com/optimizely-brings-real-magic-to-opticon-2022-in-san-diego-kicks-off-tour-in-london-and-stockholm">Optimizely </a>– a leading digital experience platform (DXP) provider – has announced a new integration with <a target="_blank" href="https://cmscritic.com/optimizely-partners-with-google-cloud-to-take-experimentation-to-the-next-level">Google Cloud’s</a> large language models (LLMs) via <a target="_blank" href="https://cloud.google.com/vertex-ai?utm_source=google&amp;utm_medium=cpc&amp;utm_campaign=na-US-all-en-dr-bkws-all-all-trial-e-dr-1605212&amp;utm_content=text-ad-none-any-DEV_c-CRE_665735422037-ADGP_Hybrid%20%7C%20BKWS%20-%20MIX%20%7C%20Txt_AI%20and%20ML%20General-KWID_43700077225650913-kwd-553582750299&amp;utm_term=KW_vertex%20ai-ST_vertex%20ai&amp;gclid=CjwKCAjw6eWnBhAKEiwADpnw9u2BMXURvDZHFlNL_A4gB-a8YkjypIddWQ1nMdG43MWUdp4TY1E6cxoCg-gQAvD_BwE&amp;gclsrc=aw.ds">Vertex AI</a>, with the goal of building and launching new generative AI features. With this integration, Optimizely’s customers and product engineering teams will gain direct access to Google Cloud’s cutting-edge foundational models, which will dramatically increase the pace of innovation in a rapidly emergent field.<h3>Sowing the AI seeds in Optimizely's model garden </h3>According to the company's press release, Google’s PaLM 2 models from Vertex AI will be used in Optimizely’s internal model garden, supporting rapid prototyping and development of generative AI features. This pairing will span the entire portfolio of Optimizely’s products, including content, commerce, and experimentation.Coupled with Feature Experimentation, Optimizely engineers can strike the perfect balance between cost, quality, and response time across Google Cloud’s growing family of models, which are rooted in a 20-year legacy and commitment to responsibility, security and compliance. “As AI is adopted at an unprecedented clip, Google’s LLMs and Vertex AI ensure that we can innovate and implement the functionalities that our customers need to scale and deliver the best digital experiences,” said <a target="_blank" href="https://www.linkedin.com/in/anielsud/">Aniel Sud</a>, CTO at Optimizely. “With these models, we can quickly and consistently add new AI features that will greatly enhance our product suite. We are excited to highlight some of these new features at Opticon in October and we look forward to continually strengthening our partnership with Google.” Optimizely customers can expect upcoming features powered by Google Vertex AI to be far more fine-tuned for the intended use cases. <h3>Focusing on high-value AI use cases</h3>On the AI front, Optimizely is exploring high-value use cases to bring generative AI to marketing and digital teams, empowering them to transform digital experiences for customers. These use cases include: <ul><li>A knowledge bot trained specifically on Optimizely’s technical documentation, so customers can utilize a chat interface to get instant answers to questions during implementation and use </li><li>A variation generator for brainstorming, allowing Optimizely customers to utilize AI to generate new ideas when designing a test </li></ul>This innovative partnership builds upon the success of leveraging Google Cloud for Optimizely Web Experimentation and Feature Experimentation, as well as the availability of both products on <a target="_blank" href="https://console.cloud.google.com/marketplace/product/optimizely-public/optimizely-gcp-marketplace">Google Cloud Marketplace</a>.  “Users of Optimizely’s digital experience platform will benefit from new capabilities, powered by Google Cloud’s Vertex AI,” said <a target="_blank" href="https://www.linkedin.com/in/rodrigoprocha/">Rodrigo Rocha</a>, Head of Global AI &amp; ISV App Partnerships at Google Cloud. “By building with Vertex AI and expanding access to Google Cloud’s powerful models, Optimizely will enable its customers to build new online experiences and products that add real value with generative AI.” <h3>Partnering to power experimentation with AI</h3>Optimizely and Google have already cemented a strong partnership. In February of 2022, the companies jointly <a target="_blank" href="https://cmscritic.com/optimizely-partners-with-google-cloud-to-take-experimentation-to-the-next-level">announced a strategic initiative</a> to move Optimizely's experimentation to the Google Cloud, leveraging a secure and scalable infrastructure for investments in AI and analytics. In 2022, Optimizely also achieved over $1B in incremental revenue for its customers. This partnership with Google Cloud and innovation with Vertex AI will continue to allow businesses to make data-driven decisions and scale their digital experiences.

Optimizely Partners with Google Cloud to Expand Generative AI Capabilities 

cms-critic-staff

What can I say? I’m obsessed with Halloween.But it’s not just me.For the last 17 years, my wife and I have spent the months of September and October avoiding zombies, dodging demons, and thwarting chainsaw-wielding psychopaths at <a target="_blank" href="https://www.universalorlando.com/hhn/en/us">Universal Studio’s Halloween Horror Nights</a>.Man, 17 years is a long time.For context, we started going when our son could barely crawl, eventually bringing him for the first time in 2018. Now, he accompanies a terrified mob of fellow University of Florida students as part of an annual pilgrimage to the park. The next morning, we have random college students strewn across spare beds and splayed on sofas, most having survived the night in one piece. I love it. This Labor Day weekend, we attended the opening of the 32nd year of HHN, which will feature a record-breaking 48 nights of festivities. Attendance is already expected to be high, and the first night was sold out. <img src="https://cmscritic.com/ms-content/uploads/2023/09/halloween-horror-nights.jpg" />Clearly, Halloween is more than just a holiday in America – it’s a season. A unique phenomenon celebrated by people from all walks of life, young and old. It gives us permission to transform, to be something other than ourselves and revel in the exhilaration of being scared. As it turns out, Halloween has its roots in pagan rituals, and some version of it is celebrated in countries around the globe. Last year, Americans <a target="_blank" href="https://www.forbes.com/sites/jiawertz/2022/10/20/halloween-spending-projected-to-hit-a-record-106-billion-for-2022/?sh=735967bf7d4b">spent over $10.6 billion</a> on Halloween. That includes the pricetag for events like HHN, which is considered “monster mecca” for rabid fans. For me, it's fun watching the mix of fear and delight as people traverse the bevy of haunted houses and “Scare Zones" around the park. This year was no exception, as streaming properties like Stranger Things and The Last of Us came to life in terrifyingly ornate detail. At the same time, original concepts showcase the depth of Universal’s creative teams, sporting new characters like the mysterious Dr. Oddfellow (caution: a physical with this MD might result in bites to the neck and a fear of garlic). The production quality at HHN is simply off the charts. It requires months of development and thousands of people to pull off, including the event's signature “Scare Actors,” costume and prosthetics designers, set builders, lighting techs… the list goes on and on.To be sure, there are still challenges for the faint of heart. The lines can be notoriously long, and you need an expensive Express Pass to see everything. Heck, the scariest thing might be the price tag for food and memorabilia. But overall, the experience is second to none, and digital has helped deliver more thrills and chills than nightmares.As Unlimited Frequent Fear passholders, we have the opportunity to indulge in HHN multiple times throughout the season. Working in the DX industry, I’ve paid close attention to the ways digital transformation has made Halloween Horror Nights a blood-curdling success over nearly two decades – and it’s something to behold.One of the best examples is the evolution of Universal's mobile app. Not only has it eliminated paper-based ticketing and scanning, but it also features current wait times for each event. Super handy when making decisions about what venue to hit when the park is packed. Feedback is also being collected from willing parkgoers via tablets as they leave the property, and social listening has become something of an art form as devoted fan communities have arisen over the years (yup, we're part of them). On the content side of the Necronomicon, text and assets are being pushed across multiple screens and devices, and integrated <a target="_blank" href="https://cmscritic.com/top-10-open-source-ecommerce-platforms">eCommerce payment systems</a> are as commonplace as ghouls and goblins. Universal has also been pioneering virtual reality in its park rides, so I’m just scratching the surface.No doubt, AI is part of the witch's brew. While not visibly evident, it's most certainly at use behind the scenes, analyzing customer data at scale to improve decisions about food distribution, queue management, and merchandise. With the sheer number of data points and interactions at play, these are tasks no human (or the undead) is capable of doing.While the world wrestles with the ethical dilemmas around AI, I think Universal and HHN demonstrate how technology and innovation have continuously supported immersive physical experiences. There would be no "spine-tingling" without the presence of performers and artisans. At the same time, new technologies are enriching productivity, shortening creative cycles, and improving the customer experience in every dimension. Could some roles be displaced? Tarot cards aside, it's more than probable. But the night is always darkest before dawn, and the potential for new jobs and opportunities will likely outweigh the perceived negatives. On some level, we all fear the future. In fiction, we're quick to demonize technology, tapping some innate mistrust of ourselves and what we endeavor to create. It’s easy to let our imagination get the best of us, especially with the rapid adoption of ChatGPT. And while many technologies have rushed to integrate <a target="_blank" href="https://cmscritic.com/tinymce-brings-advanced-ai-to-cms-text-editing-interview-with-fredrik-danielsson-elise-bentley">generative AI</a> with their offerings, I see most of them assuring their audiences that they're mindful of the ethics… and this is not Frankenstein's monster.Halloween might not be your jam, but embracing the unknown and understanding its pros and cons is how we face the future. Brands like Universal are leveraging it to improve its theme park experiences, a place where the physical and digital are now locked in a danse macabre.So why not brave the new world? If you’re lucky, you might have a little fun along the way.  So fun, it’s scary.

Fear the Future of AI? Not at Universal's Halloween Horror Nights

matt-garrepy

Highlights:
<ul>
<li>Christine Masters is driving product management for Contentstack's AI roadmap</li>
<li>The company's new AI Assistant offers generative content capabilities powered by ChatGPT</li>
<li>Contentstack’s AI approach is helping to mitigate concerns like data privacy</li>
<li>The combination of AI Assistant and Automation Hub delivers unique advantages</li>
</ul>
<hr />
 
Artificial Intelligence has long been a popular trope in the sci-fi genre. Most of us could rattle off a string of films about machines gone amuck, from 2001: A Space Odyssey to Ex Machina.
The stories are almost always identical: Humans create AI. The world marvels at its promise. People check out. AI becomes self-aware and decides humans need to be exterminated. Epic battles ensue.
And it’s all downhill from there.
While advancements in real-world AI have been profound, they’re a far cry from the popcorn pop-culture dystopias we see in the movies. Sure, there’s trepidation, but no threat of total machine domination (we hope). And AI models like <a href="https://openai.com/chatgpt" target="_blank">ChatGPT</a> – which has captured the moment's zeitgeist – are already proving their value in multiple use cases. 
Generally speaking, the AI features being added to CMS platforms show promise, not peril. At the same time, they’re fraught with challenges – and if there’s one Schwarzenegger-level threat suffering from a bit of time dilation, it might be the customer experience. Compounded by pressure to seize the opportunity and a need to remain in competitive lockstep, many AI features have been rushed to market at hyperbolic speed.
But what makes them different? And are they really delivering value? That depends a lot on how a user creates content in a CMS.
When I was in Europe last month, I met with <a href="https://www.linkedin.com/in/nehasampat/" target="_blank">Neha Sampat</a>, <a href="https://www.linkedin.com/in/conoregan/" target="_blank">Conor Egan</a>, and <a href="https://www.linkedin.com/in/susancbeermann/" target="_blank">Susan Beerman</a> – the leadership team at Contentstack. One of the discussion topics was Contentstack's new AI Assistant, which I had previewed and found quite compelling. I wanted to dive deeper, so they sent me to the source: Senior Product Manager <a href="https://www.linkedin.com/in/masters/" target="_blank">Christine Masters</a>.
Christine’s bailiwick is Emerging Products, where she’s working on the front line of innovation. Her months-long mission to launch Contentstack’s new AI features has yielded dynamite results, and she gave me a guided tour. We also talked about the big challenges the market is wrestling with, and how Contentstack's approach to generative AI – from content to code – is supercharging their composable DXP.
<h2>Mastering product management</h2>
Christine joined me on Zoom from her home in Iowa – an easterly track from her California roots, but a more temperate 80 degrees on an otherwise sweltering summer day.
“I remember 119 degrees,” she reminisced. It’s worth noting that the <a href="https://www.pbs.org/newshour/nation/californias-death-valley-sizzles-near-record-temperatures-as-brutal-heat-wave-continues#:~:text=The%20hottest%20temperature%20ever%20recorded,as%20keeper%20of%20world%20records." target="_blank">record in Death Valley</a> is 134, which makes 80 sound downright cool.
And cool is precisely the right word for Christine. She's easygoing, confident, and genuinely passionate about her work. From an experience perspective, she's a fluent industry stalwart that’s seen the evolution of content into the digital realm, starting in print at a newspaper in Fort Wayne, Indiana – where she used tools like QuarkXPress.
After operational roles in media, she managed CMS platforms at BLOX Digital, focusing on digital transformation for media applications in cloud and SaaS. She later became a senior director of core platforms, where she conducted focus groups to help build better CMS experiences.
Coming from a more traditional monolithic CMS background, Christine brings an unmatched perspective to her work in Emerging Products, specifically with Contentstack’s new AI features. The company <a href="https://demandgenreport.com/features/news-briefs/contentstack-adds-openai-chatgpt-integration-to-its-platform" target="_blank">announced</a> its ChatGPT integration in late March, relatively early in the hype cycle.
The new AI initiative was ambitious, enabling in-line user extensions that assist in creating brand-specific content in seconds. The stated capabilities were simple but powerful: editors would be able to quickly publish summaries, outlines, metadata descriptions, keyword-optimized blogs, and more – all by using prompts. But that was just the beginning.
In April, Contentstack <a href="https://community.contentstack.com/podcast-media-and-more-81/introducing-contentstack-live-383" target="_blank">hosted a webinar</a> introducing its ChatGPT connector and the future of AI-driven composability. The messaging established that the company sees AI and automation technologies touching virtually all facets of the digital experience stack – transforming content creation, code development, and asset creation.
Quite a charter, and one that will keep Christine busy for some time to come.
<h2>Understanding customer concerns with AI </h2>
Death by PowerPoint is a common fatality in the tech world, but Christine offered a single yet poignant slide before diving into the demo – one that crystallized the key challenges most companies face when considering AI. This educational entry point has become common for her.
“We’ve had a ton of interest, but a lot of concerns as well,” she said. “Many companies are asking, what should we be doing with AI? I’ve been on maybe 30 or 40 calls not just consulting, but talking and listening to their concerns. Some people are much more AI-friendly, and some are very nervous. There’s kind of this fear that when we let ChatGPT in, it’s going to suck up all our data to learn things and use it elsewhere, even with my competition.”
It’s a real concern – and one I’ve heard repeatedly from platforms and users. Will my company’s proprietary content become fodder for the training model? Or will <a href="https://www.aljazeera.com/news/2023/3/23/chatgpt" target="_blank">another bug</a> allow my competitors to see my chat sessions?  
I asked Christine how Contentstack is assuaging these fears. She quickly pointed out that their new service taps the ChatGPT API, but none of the data is being trained by the broader model. Additionally, only prompt data is stored for troubleshooting purposes and cleared out after 30 days. All of these tactics meet <a href="https://gdpr.eu/" target="_blank">GDPR compliance</a>, providing greater assurance around data privacy.
<hr />
<h4>"You need to make sure you have humans at the right step, particularly if it’s content created from scratch."</h4>
<hr />
That said, OpenAI has become a powerhouse tech company with more than 100 million users, making it a prime target for hacking. Last month, <a href="https://mashable.com/article/chatgpt-stolen-accounts-passwords-dark-web" target="_blank">Group-IB reported</a> that thousands of ChatGPT login credentials were leaked to the Dark Web, forcing Google and other companies to warn employees not to add sensitive information to the large language model. Contentstack addresses some of these risks with a combination of optimization and policy.
Accuracy is another blocker, and ChatGPT’s well-documented <a href="https://www.securityweek.com/chatgpt-hallucinations-can-be-exploited-to-distribute-malicious-code-packages/#:~:text=The%20issue%20is%20related%20to,information%20that%20may%20look%20plausible." target="_blank">hallucinations</a> have caused significant challenges to trust. “Sometimes it sounds very convincing, but it’s a total lie,” Christine added. “You need to make sure you have humans at the right step, particularly if it’s content created from scratch.”
Given this, Christine focuses on the use cases where ChatGPT excels, such as creating short summaries from longer-form content or extracting keywords. “We’ve been doing things like this for years now, so it’s become table stakes,” she said, noting that AWS has been making AI scalable for quite some time with products like <a href="https://docs.aws.amazon.com/managedservices/latest/userguide/rekognition.html" target="_blank">Amazon Rekognition</a>.  
But what is novel are the prompts being used to simplify and execute – and how Contentstack is harnessing its automation capabilities to streamline AI at exactly the right places in the content creation experience.
“That’s where we’re coming from with these products,” she punctuated.
<h2>Conjuring content with AI Assistant </h2>
Contentstack’s ChatGPT integration has two main products it intersects with: AI Assistant and Automation Hub. The combination of the two provides a unique ecosystem of capabilities that enriches the generative creation of content and the automation and streamlining of its entire AI workflow.  
As Christine pointed out, an important distinction with the AI Assistant is its nature as an app in Contentstack’s composable ecosystem. I knew other platforms had instrumented their AI with a more coupled architecture, so I asked her to elaborate on the advantages.
“One really great thing about our CMS is the extensibility,” she explained. “You can build your own apps and modules to extend the capabilities through a marketplace approach. With monolithic CMS platforms, you might keep adding features – but after ten years, it gets bloated and filled with toggles. By extending CMS through apps, you can keep it agile and lean.”
With the AI Assistant being an app, Christine began her demo in the most logical place: the installation process. This is critical, as users can choose to connect ChatGPT using their own API keys, or use Contentstack – which is free. In either case, the whole piece is painless.
<img src="https://cmscritic.com/ms-content/uploads/2023/07/contentstack-screen-installation-1024x727.jpg" alt="Contentstack screen showing the installation process" />
Inside the tool, there are lots of pre-configured features that allow you to build prompts for almost anything. You can add a pre-defined set of icons that conform with your brand standards or build custom prompts aligned with your organization’s content style. (Sidenote: <a href="https://learnprompting.org/" target="_blank">prompt engineering courses</a> have now emerged to help assist users with this new skill. Go figure.)
In Contentstack’s AI, the prompts can get very granular. For example, a customer can enter explicit instructions like when to use associated trademarks or which competitor should never be mentioned. 
From a UI perspective, the AI Assistant “lives” where the content writer creates new entries, enhancing the experience without disrupting the editorial flow. The whole experience is lightweight and elegant, and reflects thoughtful analysis of where the elements should co-exist. Users can interface with the tool via custom actions already configured for spelling and grammar, then add functions to write summaries, extract keywords, and even provide translations. 
As Christine pointed out, writers and editors aren’t typically creating content from scratch with AI. In most cases, they use it to augment their writing in different ways.
“As a quick example, let’s say I want to write a blog post about something,” she said. “You can use our pre-built Idea Generator to create ideas and use custom prompts to be in the tone and voice of your brand. Most of the time, writers want ideas and outlines, so they have more control.”
<img src="https://cmscritic.com/ms-content/uploads/2023/07/contentstack-screen-ai-ideas-1-1024x747.jpg" alt="Contentstack screen showing the AI idea prompt." />
From a success standpoint, Christine offered some experience-based advice about prompting, explaining how the assistant can produce better and more accurate results when properly fed. This includes prompt curation around overused terms that might seem cliché or incompatible with a brand’s voice.
“You might tell ChatGPT to ‘make it more exciting’ and it returns words and phrases like ‘trailblazing’ or ‘revolutionary.’ Everything can start to sound the same. ‘In the realm of digital experiences’ is another example that you see out there. These would be my guidelines for what not to use.”
Looking at the prompt capabilities, I asked if there was a plan to make the customizations more repeatable and sharable. Christine said that’s on the roadmap – along with other features.
“We really want to make sure that we’re providing something very useful for our customers they can actually use.”
<h2>Adding some magic with Automation Hub</h2>
The 1-2 punch of Contentstack’s AI offering is the unique combo of AI Assistant and <a href="https://www.contentstack.com/automation-hub/?creative=650999267431&amp;keyword=contentstack%20automation%20hub&amp;matchtype=p&amp;network=g&amp;device=c&amp;campaign=19810684522&amp;adgroup=146523337843&amp;placement=&amp;utm_campaign=fy24-glob-dg-automation-hub-us-ca&amp;utm_medium=paid-search&amp;utm_source=google&amp;gclid=Cj0KCQjwwvilBhCFARIsADvYi7L-bNoQPTRPXR4ba5lah7uPBz6xovMlmKayTKrMh-G4nO9xaoVQ8XUaAuRDEALw_wcB" target="_blank">Automation Hub</a>.
If you’re unfamiliar with the service, it’s an existing feature of the Contentstack DXP that delivers an easy, no-code solution for streamlining business processes. It starts with a trigger or action and allows you to define a specific workflow using a graphical interface – which is incredibly lithe and intuitive. The tool is designed to help simplify the complexity of integrations and automate routine tasks. 
“Now [with Automation Hub], you can build up a series of automated steps with the ChatGPT connector, which brings in an automatic prompt trainer,” Christine described. “It’s a webhook with a trigger – like publishing a new article – and you build steps afterward that are API calls or snippets of code performing functionality.”
According to Christine, Automation Hub is ideal for applications like translations, where ChatGPT can be automatically tapped to return languages based on specific fields and requirements. ChatGPT does a decent job with translations, and there’s already broad market trust with third-party tools like <a href="https://www.weglot.com/" target="_blank">Weglot</a> that leverage AI.
<img src="https://cmscritic.com/ms-content/uploads/2023/07/contentstack-screen-translation-1024x749.jpg" alt="Contentstack screen showing translation with ChatGPT and Slack connector." />
In just a few minutes, she demonstrated how simple it is to activate the "ChatGPT for Translation" automation in the UI and configure both the connector and the associated actions. Once the translation was completed, we even added a step with Slack, automatically letting team members know the task was completed. Pretty slick. 
“Summaries, keywords, translations – if you do something a hundred times over and you never have to change it, this can take the place of people. But you always want a human in the loop knowing what’s going on.”
In an upcoming version, Christine mentioned that users will be able to add in multiple prompts, but also specific function calls via API or http connections. For example, ChatGPT could be harnessed to tap a stock or sports score database at 9 AM and send an email to a list of recipients in a pre-defined format.
“Text enhancement is really the starting point,” she said. “I can’t wait to get this into the hands of more users. I don’t think we’ve even started to think about the cool ideas they’ll be able to implement.”
<h2>What’s ahead for Contentstack and AI</h2>
We’ve been on the ChatGPT “hype train” for well over six months now. I asked Christine how the landscape is unfolding, particularly with similar offerings from other platforms. She agreed that competitors are driving AI in a commoditized direction, but that Contentstack’s app architecture – and its focus on streamlining and automating processes – is unique.  
So what’s driving that value quotient for customers in these early days?
“We’re seeing a lot of use with things like extracting keywords, tapping language translations,” she motioned, “but there are also cost savings when you consider replacing other tools for things like SEO optimization. And if you’re using our Contentstack API keys, it’s even free.”
Free is good, but will it last? Christine did suggest that large organizations will likely opt to use their own ChatGPT keys – and if more translation is required, costs may increase with the scaling token requirements. But it's clear that Contentstack sees its AI features as a value-add, and having a free entry point is a smart move to build adoption. 
Based on the demo, there’s ample room to streamline the clicks required within Contentstack's AI experience. This is where Automation Hub really sings, delivering both efficiency and control to users. As she noted, it’s the “boring” integrations – the undifferentiated heavy lifting – that Contentstack is endeavoring to supplant. By doing so, users can focus on building high-value, high-utility apps and experiences. You know... the cool stuff. 
“Whatever you trust AI to do, we can automate that,” she declared.  
<h2>Get started with AI Assistant</h2>
If you want to join Contentstack’s AI Assistant program, sign up by <a href="https://explore.contentstack.com/ai-assistant?utm_medium=internal_docs" target="_blank">filling out this form</a>. After agreeing to a few terms, you’ll receive a link to install the app – which, as mentioned, is currently free.
Christine said we can expect more announcements in the coming months. You can also check out Contentstack’s recent <a href="https://www.contentstack.com/docs/changelog/#ai-assistant-june-release-highlights" target="_blank">June release highlights</a> for current details.  
All challenges aside, the introduction of AI in CMS platforms has tremendous potential to improve productivity for content editors and developers. I’ve always contended that AI should stand for augmented intelligence, because it’s really about enhancing our creativity and productivity – not replacing it.
“Humans are great at the interesting things,” Christine observed.
Exactly. Like writing sci-fi scripts... about AI.

A Closer Look at Contentstack's AI Features with Christine Masters, Senior Product Manager

If <a href="https://www.linkedin.com/in/vojtechboril/" target="_blank">Vojtech Boril</a> has a crystal ball in his possession, it’s time to come clean.
Maybe it was sheer luck that his company, <a href="https://www.cmscritic.com/kontent-ai-introduces-industrys-first-headless-cms-with-native-ai-capabilities/">Kontent.ai</a>, would embrace the “AI” domain in 2022. Or was their official <a href="https://www.linkedin.com/pulse/taking-kentico-kontentai-next-generation-digital-petr-palas/">spinoff from Kentico</a> some mystical prognostication of things to come?
I wasn’t sure, but Vojtech settled the question for me.
“Bringing AI into the CMS world has been part of our vision for a long time,” he said. “Our company name – which we chose a year ago – is good proof that this launch is not just a quick reaction to the new ChatGPT trends.”
Tarot cards and tea leaves aside, this is an exciting time for Vojtech and Kontent.ai. Since introducing <a href="https://openai.com/" target="_blank">OpenAI’s</a> large language model late last year, many content management vendors have entered the AI race. In several cases, they leverage ChatGPT as a basic plugin or integration.
But last week, Kontent.ai announced the early availability of the first native AI capabilities to a headless CMS.
Native, you say? How so? I had a thousand questions – none of which <a href="https://www.cmscritic.com/from-chatbots-to-contentops-how-ai-is-coming-to-your-cms-whether-you-like-it-or-not/">ChatGPT</a> could answer.
Thankfully, <a href="https://kontent.ai/events-and-webinars/first-look-at-native-ai-capabilities-in-kontent-ai/" target="_blank">during a recent webinar</a>, Kontent.ai offered an informative first look at these AI features. This filled in many blanks, but I still connected with Vojtech to ask why he thinks these new capabilities are game-changers. As the Vice President of Growth &amp; Marketing, he combines content and platform POVs into one brain. He's also an avid runner with some intimidating pace times – so he's accustomed to staying ahead of the pack. 
<h2>A first look at native AI capabilities</h2>
One would assume that a content management vendor would produce quality content to promote its products and services. That’s not always the case, but Kontent.ai has consistently delivered the goods. Last week’s webinar on its native AI was no exception and provided a solid overview of the new features.
The session – hosted by <a href="https://www.linkedin.com/in/hrubytomas/" target="_blank">Tomas Hruby</a>, Lead Product Manager, and <a href="https://www.linkedin.com/in/jordan-torpy-82087b4a/" target="_blank">Jordan Torpy</a>, Product Marketing Manager – opened on the new “Gold Rush” into the AI market, and how ChatGPT has ignited every CMS vendor to jump on the bandwagon. Both commented on seeing many different approaches across the digital experience market, which has undoubtedly informed their innovation.
According to Tomas, ChatGPT seems easy to repurpose, but in reality isn’t that simple. Large language models become challenging to master for prompt creation and obtaining accurate results. He called these skills more of an “art,” contrary to the promise of automation.
In the webinar, the duo focused on three key challenges with current AI solutions: understanding context, composing AI, and integration. Jordan provided an example of how large language models struggle to incorporate brand guidelines, tone of voice, and other factors exclusive to a given company. This training is time-consuming and difficult to orchestrate for content creation.
One of the big concerns for enterprises is around the unknowns of integration. For example, does the customer or vendor maintain the AI capabilities? Is it a plugin built by an open source community? They also discussed the increased API surface area that may be vulnerable to attacks – and that many enterprises are reluctant to share proprietary content with public models.
In each case, it’s clear there are gaps with current AI solutions – and Kontent.ai’s native capabilities promise to bridge those gaps to usability.
<h2>The vision for AI in a headless CMS</h2>
Given the challenges that AI presents when integrating into a CMS, what was the vision guiding Kontent.ai’s native capabilities? Tomas and Jordan boiled it down to a couple of key pillars during the webinar.
First, Kontent.ai is a fully integrated experience designed for what they call “fluent content creation.” As a native set of platform features, the AI respects internal formatting across your work, making it all more conformant. Content creators will also find the AI tools highly intuitive from a UI perspective, and available where they would expect them to be.
The second pillar is delivering accurate suggestions. This is a big one, as most large language models provide questionable results. Much of this concerns prompt design, or the ability to feed the AI with the proper context. With Kontent.ai, the native capabilities are built with context in mind, so it respects your company’s brand guidelines or tone of voice, and doesn’t “hallucinate” as it often does with open learning models.
Kontent.ai also provides what Tomas calls a “hidden sophistication” driven by complex pipelines designed to streamline tasks like converting notes into formatted content.
<img src="https://cmscritic.com/ms-content/uploads/2023/06/kontent-image-3-1024x620.jpg" alt="Composite of Kontent.ai native AI user experience with multiple windows of functionality" />
<h2>What really sets native AI apart?</h2>
First and foremost: Kontent.ai’s native capabilities are not a plugin. This is a marked difference from other platform strategies that leverage basic connectors to ChatGPT. Tomas states this distinction will allow users to work more efficiently and effectively as part of a CMS toolkit.
Another big difference is that the solution is fully GDPR compliant. This is achieved in large part by the <a href="https://azure.microsoft.com/en-us">Azure</a> backbone. Kontent.ai has a strong Microsoft relationship and is leveraging its AI services stack via ChatGPT 4 and a new service called <a href="https://learn.microsoft.com/en-us/semantic-kernel/overview/">Semantic Kernel</a> – an open source SDK for building custom AI apps and orchestrating complex pipelines.
Finally, Kontent.ai delivers peace of mind around privacy and control. Enterprise users can be assured that their sensitive content and data is secure and not publicly available to any OpenAI learning pipelines. The native AI capabilities are aware of content and context only within your system, and it’s not even used to train future LLM iterations.
I asked Vojtech to give me the big picture around these key differentiators through the content creator’s lens. What really stands out?
“A key difference is that our AI capabilities are native to our platform and provide a fully integrated experience for content creators,” he said. “We’re not adding a prompt window to our CMS. Instead, we’re adding new capabilities that perfectly fit with the tasks a content creator does on a daily basis.”
He cited an example: “We have a skill called ‘Improve writing.’ To use it, you select some text you want to improve to better suit your tone of voice, style guide, or other similar criteria. Then, you choose a piece of content already in your Kontent.ai project that meets your standards. Kontent.ai will then adjust your original text to match the style and tone of your chosen text.”
During the webinar, there was a great demo of this feature. The use case featured a single paragraph with a noticeably sarcastic tone of voice compared to the rest of the article. The native AI was asked to improve the writing by injecting prompts for a more professional tonality, as required by brand guidelines. It did – in minutes. The entire process was convenient, accurate, and a huge time saver.
As Vojtech further noted, what’s great is that content creators don’t need to fiddle around with making the right prompt, or string several different prompts together. Everything they need is in Kontent.ai, and it’s all a natural extension of the work they already did in the platform.
<h2>What’s the price tag for native AI?</h2>
Currently, Kontent’s new AI capabilities are fully functional, but only available to early adopters via a special access program – and seats are limited. The company is interested in collaborating with enterprise customers, so they’re inviting companies to provide their use cases.
The solution isn’t quite out of the box (yet). According to the webinar, most users can be up and running in roughly two weeks. The services should be generally available later this year.
Regarding cost, that’s still unknown – but the company seems to be focused on aligning it with real utility and value. As Vojtech pointed out, “We know everyone can go and use ChatGPT for free, so we didn’t just add a prompt window to Kontent.ai. Instead, we created tailor-made capabilities that solve real problems content creators face.”
The Kontent.ai team is working on pricing models, which will hopefully be available before the service is in GA. If you’re interested in early access, visit the <a href="https://kontent.ai/events-and-webinars/first-look-at-native-ai-capabilities-in-kontent-ai/">Kontent.ai</a> website for more details.
<h2>What other AI features can we expect?</h2>
There were some interesting questions about Kontent’s AI roadmap during the webinar. The hosts discussed the current advantages of reducing time and research. But they also described how AI might be capable of assisting with tedious, large-scale CMS tasks such as mass migrations.
One area where ChatGPT and other large language models are still struggling is translation. With accuracy being such a critical requirement, it’s still reliant on other workflows to deliver quality results. Still, this seems to be an area ripe with opportunity.
I asked Vojtech if other capabilities might be more near-term on the roadmap, and what the process looks like for onboarding new AI features.
“We've been working on [the capabilities that are part of this launch] for the past couple of months, but simultaneously we're working on many other prototypes,” he said. “Anything that reaches our development team through prioritization typically goes through a thorough research phase. We even have a dedicated UX research team, which is not always the norm in companies of our size.”
I also wanted to know how customers have responded in the rollout's early phases.
“We are absolutely thrilled with how the AI launch has been received,” he said. “We have some great initial feedback from existing customers, prospects, and major analysts. I've also had the chance to talk to some of our existing enterprise clients in person already, and there are specifically two main areas they appreciate the most. One, that our AI capabilities are fully native to the product, which currently makes us very unique in the CMS market. And two, the security aspect of being GDPR-compliant and knowing their content is not populated into global GPT environments.”
He also said that the webinar has resulted in registrations going through the roof – a clear sign that interest is swelling into action.
<h2>Consulting the crystal ball about the future of AI</h2>
As informative as the webinar was, I wanted to know how important the AI investment was to Kontent.ai. We might still be early in the hype cycle, but what does the future look like?
“This AI launch is only the beginning of our AI product focus,” Vojtech said. “As I mentioned, our rebranding to Kontent.ai a year ago was not just a coincidence, and we are serious about pioneering fully native AI capabilities as part of the CMS user experience.”
Vojtech also shared that the company is working on further improvements to contextualizing AI-generated content. They're also exploring how to improve navigating, creating, reviewing, and categorizing content.
“I believe AI has the potential to revolutionize content operations by streamlining processes, automating tasks, and enabling users to do more and faster,” he explained. “However, ‘more and faster’ should not be the only goal. Ultimately, it's rather about creating more contextualized, meaningful, and relatable content than just producing more. That's exactly how we envision our customers to benefit from our AI. We're not trying to replace their content contributors. Instead, we're on a mission to help them be more productive and be able to focus on the work they love while utilizing AI to do repetitive tasks for them.
Wrapping things up, I got a bit existential about AI’s impact on people. As Vojtech pointed out, only the future will show whether it’s good for humanity. In the meantime, he said, it’s important to think critically about the ethical implications as AI becomes a normal part of life. This includes data privacy, security, and other factors that must be carefully addressed.
“I am an optimist,” he added, “and I believe that humanity can strike a balance in the development of AI – harnessing its benefits while ensuring it does not pose a threat to our well-being.” 
I hope that optimism is coming from the same crystal ball.

Kontent.ai Pioneers Native AI in Headless CMS: Interview with Vojtech Boril

Kontent.ai logo with headshot of Vojtech Boril

AI continues to drive platform innovation, and builders are being treated to new features daily. While generative technologies like <a href="https://www.cmscritic.com/from-chatbots-to-contentops-how-ai-is-coming-to-your-cms-whether-you-like-it-or-not/">ChatGPT</a> are powering apps with a range of capabilities, having the right infrastructure for product development and deployment is a key requirement. 
To that end, <a href="https://www.cmscritic.com/vercel-launches-new-visual-editing-feature-with-sanity-cms/">Vercel</a> – the frontend cloud for deploying applications quickly and easily – <a href="https://vercel.com/blog/introducing-the-vercel-ai-sdk" target="_blank">just launched</a> a new software development kit for AI apps built with React and Svelte. This includes the Vercal AI SDK for easily streaming API responses from AI models and the Chat &amp; Prompt Playground for exploring models via OpenAI, Hugging Face, and more.
According to the company's website, several AI platforms – including Scale, Jasper, and Jenni – have launched using Vercel and Next.js, its React-based web development framework. Next.js provides the essential tooling and configuration required for React, as well as additional structure and optimizations. 
<h2>Ready for AI with a purpose-built SDK</h2>
The <a href="https://sdk.vercel.ai/" target="_blank">Vercel AI SDK</a> is an <a href="https://github.com/vercel-labs/ai" target="_blank">open-source</a> library with developers in mind. With the SDK, users can build conversational, streaming, and chat user interfaces using JavaScript and TypeScript. According to the company's post, the SDK supports React/Next.js and Svelte/SvelteKit, with support for Nuxt/Vue coming soon. 
Vercel’s AI SDK embraces interoperability and includes first-class support for <a href="https://openai.com/" target="_blank">OpenAI</a>, <a href="https://js.langchain.com/docs/" target="_blank">LangChain</a>, and <a href="https://huggingface.co/" target="_blank">Hugging Face</a> Inference. Regardless of a user's preferred AI model provider, they can leverage the Vercel AI SDK to create cutting-edge streaming UI experiences.
The AI SDK also includes "streaming first" UI helpers that enable real-time dynamic data representation in applications. Vercel also included callbacks for storing completed streaming responses to a database within the same request, allowing more efficient data management when handling text responses. 
From a cloud scalability perspective, the AI SDK is already integrated with Vercel products like Serverless and Edge Functions. This allows users to build AI applications that deploy instantly, stream generated responses, and are cost-effective. 
<h2>A playground for chat</h2>
In late April, Vercel launched an interactive online prompt playground called <a href="http://play.vercel.ai/" target="_blank">play.vercel.ai</a>, allowing developers to compare various language model results in real time. Users can then tweak parameters and quickly generate Next.js, Svelte, and Node.js code.
Last week, Vercel added a new chat interface to this playground, allowing developers to compare chat models simultaneously. The company also added code generation support for the new AI SDK, allowing users to go from playground to chat app in just a few clicks. 
<h2>About Vercel</h2>
Vercel is the cloud platform for frontend developers, providing the speed and reliability innovators need to create at the moment of inspiration. By providing the toolkit frontend teams love, Vercel unlocks developer potential and enables you to go from idea to global application in seconds. Vercel enables customers like Under Armour, Nintendo, The Washington Post, and Zapier to build delightful user experiences on the Web.

Vercel Introduces SDK for Building AI Apps with React and Svelte

It's impossible to deny the impact of AI on the CMS industry. As platforms race to add new features that leverage <a href="https://www.cmscritic.com/from-chatbots-to-contentops-how-ai-is-coming-to-your-cms-whether-you-like-it-or-not/">ChatGPT</a> and other generative technologies, few have incorporated AI beyond some basic integrations. 
But that's starting to change. This week, <a href="https://www.cmscritic.com/kontent-ai-raises-40-million-to-bring-the-power-of-ai-to-content-management/">Kontent.ai</a> – an industry-leading headless CMS – announced a new set of native AI capabilities that will give users complete control to create and manage content across their organization.
According to the company's press release, Kontent.ai will now deliver the first and only context-aware AI that is fully integrated into its CMS product. This provides control from ideation to editing to customer experience in real time, displaying how content will look on websites and applications.
In addition to improving efficiency and productivity, the new AI will provide a layer of content governance – a unique advantage in the CMS landscape of AI capabilities. 
“Native AI skills inside Kontent.ai leverage the power of artificial intelligence while minimizing the risks often associated with it,” said <a href="https://www.linkedin.com/in/petrpalas/">Petr Palas</a>, Founder, Kontent.ai. “Content management challenges will only increase as more content is generated with the adoption of AI. However, we anticipated this and built a solution that works across the organization for the marketer, the developer, and the content creator."
<h2>Delivering real value to content creators with AI</h2>
As demand for content across organizations increases, teams are struggling to manage, maintain, and govern content at scale. Kontent.ai says that building these native AI-powered skills into its headless CMS is an evolution of its platform, designed to meet this challenge in a single solution.
Some benefits of Kontent.ai's native AI skills include:
<ul>
<li>Increased efficiency: Improve all stages of the content management process from creation to review with the power and speed of artificial intelligence.</li>
<li>Faster time to value: Leverage native AI skills immediately without the need for external integrations, plug-ins, or development resources within a headless CMS.</li>
<li>Consistency at scale: Develop core content, versions, style, tone of voice, and more – instantly.</li>
<li>Simplified content governance: Safeguard brand and content guidelines seamlessly using AI.</li>
</ul>
“The vision and innovation of Kontent.ai is what makes them a trusted partner,” reports <a href="https://www.linkedin.com/in/michael-d-orio-22a32517/" target="_blank">Michael D'Orio</a>, VP of Marketing from American Bath Group. “As a long-term customer, who just won the MACH Impact Awards for Best Overall Change Product by the MACH Alliance, we’ve reached new levels of success with Kontent.ai and look forward to the newest solution.”
Learn more about the native AI capabilities of Kontent.ai on the <a href="https://kontent.ai/events-and-webinars/first-look-at-native-ai-capabilities-in-kontent-ai/" target="_blank">upcoming webinar</a> on June 20, 2023.
An <a href="https://kontent.ai/specials/introducing-native-ai-capabilities/" target="_blank">early access program</a> for current customers is also available.
<h2>About Kontent.ai</h2>
Kontent.ai is the headless CMS that gives organizations complete control over content to speed up time to market and engage meaningfully with audiences across channels. In the Kontent.ai platform, governance underpins all operations and workflows. Content creators collaborate in real time, making it easier to land on the best ideas, reduce bottlenecks, and maximize the impact of everything that’s created. Kontent.ai is an API-first cloud-native solution, so developers can use their favorite technologies, languages, and frameworks to deliver seamless experiences that look and feel great on any channel. With offices in New York, London, Amsterdam, Brno, and Sydney, Kontent.ai supports global customers, including Zurich Insurance, Algolia, and Oxford University. Kontent.ai is a Microsoft partner and MACH Alliance member, recognized by both Gartner and Forrester.

Kontent.ai Introduces Industry’s First Headless CMS with Native AI Capabilities

Kontent.ai logo against a tech background

From Chatbots to ContentOps: How AI is Coming to Your CMS (Whether You Like It or Not)

An android with its eyes closed, and a cloud above showing it dreaming of electric sheep.

Explore a wide range of informative articles on Artificial Intelligence, insights, and industry updates. Stay informed and ahead of the curve with our diverse collection of news and posts covering the latest trends and developments in the industry. 