Connect with us

AI Research

Salesforce, Workday Face Their Biggest Challenger Yet

Published

on


Imagine an HR manager looking for the PTO record of an employee. Instead of logging onto the HR dashboard and pulling up the worker’s profile, the manager asks an artificial intelligence (AI) chatbot to get and email the data.

If this is the future of work, would enterprises still need to use the software as a service (SaaS) HR provider?

This is the question surrounding the SaaS industry in the age of AI. SaaS has defined enterprise software for nearly two decades. It was an upgrade to buying boxed software and running it on in-house computers. Instead, many companies pay a monthly fee per worker for the service.

The SaaS revolution made companies such as ADP, Salesforce, Workday and Slack into multibillion-dollar businesses.

But now another revolution is here. AI could bypass the services provided by SaaS companies. Users might no longer have to use a SaaS dashboard like ADP’s to get the information they need.

Still, the answer is not that simple.

“AI bots won’t replace SaaS entirely, but they will disrupt it in meaningful ways,” Martin Balaam, CEO and co-founder of SaaS platform Pimberly, told PYMNTS. “In some cases, they could even eliminate the need for certain SaaS platforms, particularly larger, slower-moving providers weighed down by technical debt and outdated UIs,” or user interfaces.

Balaam pointed out that businesses pay to use a SaaS tool’s dashboard to work with their data. But with AI, users don’t need a dashboard. They just have to ask the AI to show trends, find patterns and even pull in external data sources that the SaaS tool could not do.

Businesses also pay to have the SaaS tool integrate and orchestrate across the company’s data. AI can also do it. Third, SaaS makes it easier for non-technical users to use the software through drag-and-drop workflows. With AI users, can just describe what they want to do.

“The takeaway: SaaS should evolve with AI, not against it,” Balaam said.

SaaS should be designed so it can work with AI and being flexible so the customer can use whichever AI model works best for them. This flexibility will help SaaS companies endure, Balaam said. The bottom line is that SaaS isn’t dead but the way it provides value is changing.

Zohar Bronfman, CEO of predictive SaaS provider Pecan AI, agreed. “SaaS is not going anywhere, but it is evolving,” he told PYMNTS. “Enterprises will continue to need vertical software designed for their unique data structures, yet the real shift is toward much smarter SaaS that is dynamic, adaptive, and requires minimal customization.”

That means specialized SaaS systems for certain industries have deep, domain-specific knowledge baked in, such as compliance rules, data formats and workflows that the AI assistant might not fully replicate. Like Balaam, Bronfman believes that SaaS itself is changing to become more dynamic and adaptive, becoming even easier to use.

Salesforce was one of the first major SaaS players to go all in on artificial intelligence, launching its Einstein platform in 2016 to embed predictive intelligence directly into its CRM. It doubled down in recent years, weaving generative AI into Slack, Tableau and Service Cloud. Workday, ServiceNow, ADP, Slack and other SaaS providers also are putting AI into their products.

See also: Klarna CEO: SaaS Companies to Consolidate as Customers Seek ‘Hub of Knowledge’

Now for Agents as a Service

But Rahul Sharma, CEO at HSBlox, thinks traditional SaaS can be replaced, by agents as a service (AaaS). He told PYMNTS that agents can outperform SaaS systems, which basically let companies create, read, update and delete records through a user-friendly interface.

“AI agents will be able to understand what users want or need, anticipate their requests, and eliminate the need for the current model of SaaS applications,” Sharma said.

Sharma gave this example to illustrate how SaaS is different from AaaS:

Task: Claims processing
SaaS: Identifies issues resulting in denial of claims, but still requires action from healthcare workers to trigger different resolution workflows
Agentic AI: Automatic validation of claims, identification of any missing information, triggers any workflows that require resolution, and reduces denials. AaaS uses LLMs for clinical documents interpretation and extraction and matching for coding accuracy.

However, agentic AI still needs to earn the trust of enterprises. According to a July 2025 PYMNTS Intelligence report, 85% of chief financial officers (CFOs) surveyed have no plans to deploy agentic AI. And even among the 15% who do, 89% remain in the evaluation phase without a concrete roadmap.

Whether or not AI agents are ready for prime time, Jarie Bolander, general manager and executive partner at Decision Counsel, believes SaaS is on its way out. “Traditional SaaS is dead,” Bolander said. “Single endpoint solutions are rapidly going away. When you can build pretty much anything you want with AI, then what matters is the outcomes that companies can provide.”

Seymour Duncker, AI and ML executive strategist at Decision Counsel,  added that with SaaS, users still do all the work. With agentic AI, the agent does the work for the user. “Everything will be outcomes or transactions-based. … So yes, traditional SaaS is dead.”

Not all agree. Some see AI as the natural advancement of SaaS. “AI is not the new SaaS. It’s the next generation of it,” Greg Bibeau, CEO of Terminal B, told PYMNTS.

“SaaS revolutionized how businesses consumed technology by making it scalable, available, and subscription-based,” Bibeau said. “AI is now doing for SaaS what SaaS previously did for on-premises software — redefining the value proposition.”

Whether SaaS is “dead” or simply evolving, there is at least one consensus: The subscription model that once defined the software industry is giving way to an outcomes model, where users expect AI to not just provide tools but deliver results.

“The next generation of SaaS will be judged not by how many features it offers, but by how much real work it takes off the customer’s plate,” Mike Cieri, general manager of software solutions at BILL, told PYMNTS. “That means fewer clicks, less effort, and more results.”

Read more:

Capchase and WeTransact Team to Bolster SaaS Cash Flow

Collaborative Finance: How SaaS and Embedded Payments Are Changing the Game

Lemon Launches Flexible Financing Solutions for SaaS Vendors



Source link

AI Research

ChatGPT, the most existential artificial intelligence (AI), was created by a company called OpenAI. ..

Published

on


The world of Teen Maeil Economy with your children is now

[Getty Images Bank]

ChatGPT, the most existential artificial intelligence (AI), was created by a company called OpenAI. Currently, more than 100 million users around the world average about 3 billion questions a day on ChatGPT.

Recently, the GPT-4o model of OpenAI (where ‘o’ stands for ‘omni’) was upgraded to GPT-5. Sam Altman, CEO of OpenAI, also expressed strong confidence by introducing GPT-5, describing it as the “smartest model” and “doctoral level.”

But the market’s response was a little different. The newly released GPT-5 was considered to be an emotionless robot by users, while making errors even with basic questions. In fact, even though he is an agent, his speech and expression have become stiffer than before.

I compared the answers to the sentence, ‘I got scolded by my mom today.’

GPT-4o said, “What happened? It hurts me a little to say that I got scolded by my mom… Can you tell me why you got in trouble? Let’s talk together. It may not necessarily be your fault to get in trouble. I’m here, so it’s okay to talk slowly.”

On the other hand, GPT-5 said, “Oops… What happened? Why did you get in trouble? It’s okay if you tell me,” he responded briefly and succinctly.

[Yonhap News]
[Yonhap News]

Thanks to GPT-4o’s kind and warm way of speaking, there have been many users who have used AI not just as a tool but as if they are friends. However, the newly updated GPT-5 is widely considered to be formal and emotionless in its tone compared to the previous version. Many people tested it and found that the majority of the responses were that the previous version, GPT-4o, was much more expressive and gave careful answers.

Various overseas tech websites have also raised fire by pouring out articles on why the GPT-4o version is better than the GPT-5. Controversy also continued on the ChatGTP bulletin board of the American community Reddit, and some users even disparaged GPT-5 with expressions such as “disaster” and “unfortunate.”

In the end, OpenAI decided to support the option to use GPT-4o again for paid users by referring to user opinions. CEO Altman later said the GPT-5 launch had “more twists and turns than expected” and that he had improved the GPT-5 warmer and kinder.

Regardless of the GPT-5’s speech and performance issues, some criticize the fact that OpenAI deleted the model used by paid users without guidance. The function you paid for disappeared overnight, which means that you have betrayed your trust with consumers.

Meanwhile, there are also people who are concerned about emotionally relying on AI. Experts caution that excessive reliance on AI can lead to problems such as confusion and delusion.

[Yonhap News]
[Yonhap News]

Some users said that the GPT-4o’s kindness was rather uncomfortable because it seemed to be flattering to the user, and that the dry and short tone of the GPT-5 was more suitable for work. It is also an example of which way AI speaks better depends on the expectations and purpose of the user.

The attitude of facing AI that is getting smarter varies from person to person. Some people think that AI only needs to be good at what they are told to do. Another person wants to hear warm words from AI, and they want that kind of AI. This is why in a world where AI is becoming increasingly active, we need to think together about how it is healthiest to relate to AI. Reporter Bae Yoon-kyung. Researcher Chung Ju-hee.

This is an article in the youth economic newspaper ‘Teen Maeil Economy’. If you apply for a subscription to the Maeil Business Newspaper (02-2000-2000), you can get the Teen Maeil Business for free.



Source link

Continue Reading

AI Research

Canada’s first lunar rover looks to future space exploration

Published

on


Ali Abbas AhmadiBBC News, Toronto

Canadian Space Agency A computer generated image of the lunar vehicle on the surface of the MoonCanadian Space Agency

A computer generated image of what the lunar vehicle could look like on the Moon

In a shopping plaza an hour outside Toronto, flanked by a day spa and a shawarma joint, sits a two-storey building with blue tinted windows reflecting the summer sun.

It is the modest headquarters of Canadensys Aerospace, where Canada is charting its first trip to the Moon.

Canadensys is developing the first-ever Canadian-built rover for exploring the Earth’s only natural satellite, in what will be the first Canadian-led planetary exploration endeavour.

Models, maps and posters of outer space line the office walls, while engineers wearing anti-static coats work on unfamiliar-looking machines.

Sending this rover to the Moon is part of the company’s “broader strategy of really moving humanity off the Earth”, Dr Christian Sallaberger, Canadensys’ president and CEO, told the BBC.

Learning about the Moon – which is seen to have the potential to become a base for further space exploration – is the “logical first step”, he said.

“People get all excited about science fiction films when they come out. You know, Star Wars or Star Trek. This is the real thing.”

Two prototypes of the Moon rover, one white one in the foreground and the grey one on the table, with the Canadian flag in the background

Prototypes of the lunar rover, both designed and built by Canadensys

The Canadian vehicle is part of Nasa’s Artemis programme, which aims to establish a sustainable human presence on the Moon.

As part of that overarching goal, this rover aims to find water and measure radiation levels on the lunar surface in preparation for future manned missions, and survive multiple lunar nights (equivalent to about 14 days on Earth).

The rover will also demonstrate Canadian technology, building on Canada’s history in space.

Canada was the third country to launch a satellite, designed the Canadarm robotic arms for the Space Shuttle and the International Space Station, and is known for astronauts such as Chris Hadfield and Jeremy Hansen – the latter of whom will orbit the Moon on the Artemis II mission next year.

The 35kg rover is scheduled to be launched as part of a Nasa initiative in 2029 at the earliest. It will land on the Moon’s south polar region – one of the most inhospitable places on the lunar surface.

The vehicle does not have a name yet. The Canadian Space Agency held an online competition to select one, and is expected to announce the winner in the future.

Canadensys President Christian Sallaberger standing in one of the company's labs, with a Canadian flag visible on the back wall

Canadensys President Christian Sallaberger said he is excited to be playing a role in humanity’s quest to explore space

Canadensys is currently working on several prototypes of the rover. The final vehicle, Mr Sallaberger said, would be assembled shortly before launch.

Each component is tested to ensure it can survive the Moon’s harsh conditions.

Temperature is one of the main obstacles. Lunar nights can plummet to -200C (-328F) and rise to a scorching daytime of 100C (212F).

“It’s one of the biggest engineering challenges we have because it’s not so much even surviving the cold temperature, but swinging between very cold and very hot,” he said.

Designing the wheels is another challenge, as the Moon’s surface is covered with a sticky layer of fragmented rock and dust called regolith.

“Earth dirt, if you look at it microscopically, has been weathered off. It’s more or less in a round shape; but on the Moon the lunar dirt soil is all jagged,” Mr Sallaberger said.

“It’s like Velcro dirt,” he said, noting it “just gums up mechanisms”.

Engineers Misha Hartmann and Adam Abdulahad work on a prototype of the rover at the Canadensys headquarters. Both wear white lab coats and are working on the vehicle, which is siting on a table, and has metal wheels and visible wires.

Engineers Misha Hartmann (L) and Adam Abdulahad work on a prototype of the rover at the Canadensys headquarters

The search for water on the lunar surface is especially exciting, considering the Moon was generally thought to be bone dry following the Apollo missions in the 1960s and 70s, the US human spaceflight programme led by Nasa.

That perception changed in 2008, Dr Gordon Osinski, the mission’s chief scientist, told the BBC, when researchers re-analysed some Apollo mission samples and found particles of water.

Around the same time, space crafts observing the Moon detected its presence from orbit.

It has yet to be verified on the ground and many questions remain, the professor at Western University in London, Ontario, said.

“Is it like a patch of ice the size of this table? The size of a hockey rink? Most people think, like in the Arctic, it’s probably more like grains of ice mixed in with the soil,” he said.

Water on the Moon could have huge implications for more sustainable exploration. He noted one of the heaviest things they need to transport is often water, so having a potential supply there would open doors.

Water molecules can also be broken down to obtain hydrogen, which is used in rocket fuel. Mr Osinski described a future where the Moon could become a sort of petrol station for spacecrafts.

“It gets more in the realms of sci- fi,” he said.

Dr Gordon Osinski seated at a wooden desk in his office in Western University, wearing an Artemis programme t shirt with a rock from the Moon on the desk in front of him

Dr Osinski, an expert in lunar geology and has experience training astronauts in Canada’s Arctic, showed off a lunar rock during the BBC interview

Canada has wanted to build a lunar surface vehicle for decades, with talk of a Canadian-made spacecraft even in the early 2000s – but it was not until 2019 that concrete plans were announced.

Canadensys was awarded the C$4.7m ($3.4m; £2.5m) contract three years later.

Founded in 2013, Canadensys has worked on a variety of aerospace projects for organisations like Nasa and the Canadian Space Agency, as well as commercial clients.

More than 20 instruments built by the company have been used in a host of missions on the Moon.

But there are challenges ahead – as even landing on the Moon is no easy feat.

In March, a spacecraft by commercial US firm Intuitive Machines toppled over onto its side during landing, ending the mission prematurely.

Three months later, Japanese company iSpace’s Resilience lost touch with Earth during its landing, and eventually failed.

“That’s the nature of the business we’re in,” Mr Sallaberger said. “Things do go wrong, and we try to do the best we can to mitigate that.”

Intuitive Machines/The Planetary Society An instrument designed by Canadensys, on the Intuitive Machines' lander in space. Earth is seen below it against a black sky. Intuitive Machines/The Planetary Society

A picture of the Earth taken by a Canadensys-built camera was selected as the Best Space Exploration Image of 2024 by the Planetary Society

Space exploration has been a collaborative field over the years, with countries – even rivals, such as the United States and Russia – working together on the International Space Station.

But that might be changing, Mr Osinski said. As the prospect of a permanent presence on the Moon becomes more realistic, wider geopolitical questions have begun to swirl around the ownership of the satellite.

“There’s more talk around who owns the Moon and space resources,” Mr Osinski said.

In 2021, the US passed a law to protect the Apollo Moon landing site “because they had a concern that China could just go and grab the US flag, or take a piece of an Apollo lander”, he said.

But he had some encouraging words about the Artemis missions, which are “even way more international than the space station”.

The Artemis Accords, which is a set of ideals to promote sustainable and peaceful exploration of outer space, has been signed by more than 50 countries – including ones like Uruguay, Estonia and Rwanda, which are not traditionally seen as key space race nations.

Space is also becoming more accessible. Private companies like SpaceX and Blue Origin have taken an increasingly important role and are able to take anyone with the money and barely any training – like Amazon founder Jeff Bezos and pop star Katy Perry – into space for a few minutes.

But the Moon is the Holy Grail, as it opens up all sorts of possibilities.

Mr Sallaberger said that Canadensys is involved in longer-term projects, such as lunar greenhouses for food production.

Those still remain many years in the future, but the rover is a starting point.

“If you design something that can survive on the lunar surface long-term, you’re pretty bulletproof anywhere else in the solar system.”



Source link

Continue Reading

AI Research

Researchers make AI-powered tool to detect plant diseases

Published

on


A team of researchers at Maharshi Dayanand University (MDU), Rohtak, has developed an artificial intelligence (AI)-based tool capable of detecting diseases and nutrient deficiencies in bitter gourd leaves, potentially transforming the way farmers monitor crop health.

The study, recently published in the peer-reviewed journal ‘Current Plant Biology’ (Elsevier), highlights how AI-driven innovations can play a crucial role in real-time crop monitoring and precision farming.

The newly developed web-based application, named ‘AgriCure’, is powered by a layered augmentation-enhanced deep learning model. It allows farmers to diagnose crop health by simply uploading or capturing a photograph of a leaf using a smartphone.

“Unlike traditional methods, which are time-consuming and often require expert intervention, AgriCure instantly analyses the image to determine whether the plant is suffering from a disease or nutrient deficiency, and then offers corrective suggestions,” explained the researchers.

The collaborative research project was led by Dr Kamaldeep Joshi, Dr Rainu Nandal and Dr Yogesh Kumar, along with students Sumit Kumar and Varun Kumar from MDU’s University Institute of Engineering and Technology (UIET). It also involved Prof Narendra Tuteja from the International Centre for Genetic Engineering and Biotechnology (ICGEB), New Delhi and Prof Ritu Gill and Prof Sarvajeet Singh Gill from MDU’s Centre for Biotechnology.

MDU Vice-Chancellor, Prof Rajbir Singh, congratulated the research team on their achievement.

According to the researchers, AgriCure can detect major diseases such as downy mildew, leaf spot, and jassid infestation, as well as key nutrient deficiencies like nitrogen, potassium and magnesium.

“This represents a step towards sustainable agriculture, where AI empowers farmers with real-time decision-making tools,” said corresponding authors Prof Ritu Gill and Prof Sarvajeet Singh Gill. They added that the web-based platform can be integrated with mobile devices for direct use in the field.

The team believes that the technology’s core framework can be extended to other crops such as cereals, legumes, and fruits, creating opportunities for wider applications across Indian agriculture.

Looking ahead, they plan to integrate AgriCure with drones and Internet of Things (IoT) devices for large-scale monitoring, and to develop lighter versions of the model for full offline use on mobile phones.





Source link

Continue Reading

Trending