Everyone’s talking about AI agents and natural language interfaces. The hype is loud, and the pressure to keep up is real.
For supply chain leaders, the promise of AI isn’t just about innovation. It’s about navigating a relentless storm of disruption and avoiding costly missteps.
Volatile demand, unreliable lead times, aging systems — these aren’t abstract challenges. They’re daily operational risks.
When the foundation isn’t ready, chasing the next big thing in AI can do more harm than good. Real transformation in supply chain decision-making starts with something far less flashy: structure.
That’s why a practical, three-layer AI strategy deserves more attention. It’s a smarter path that meets supply chains where they are, not where the hype cycle wants them to be.
Let’s be honest: if your data is chaotic, incomplete, or scattered across a dozen spreadsheets, no algorithm in the world can fix it.
This first layer is about getting your data house in order. Structured or unstructured, it has to be clean, consistent, and accessible.
That means resolving legacy-system headaches, cleaning up duplicative data, and standardizing formats so downstream AI tools don’t fail due to bad inputs.
It’s the least glamorous step, but it’s the one that determines whether your AI will produce anything useful down the line.
Once you’ve locked down trustworthy data, it’s time to add context. Think of this layer as applying machine learning and predictive models to uncover patterns, trends, and probabilities.
This is where demand forecasting, lead-time estimation, and predictive maintenance start to flourish.
Instead of raw numbers, you now have data enriched with insights, the kind of context that helps planners, buyers, and analysts make smarter decisions.
It’s the muscle of your stack, turning that data foundation into something more than an archive of what happened yesterday.
Finally, you get to the piece everyone wants to talk about: agents, copilots, and conversational interfaces that feel futuristic.
But these tools can only deliver value if they stand on solid layers one and two.
If you rush to launch a chatbot on top of bad data and missing context, it’ll be like hiring an eager intern with no training. It might sound impressive, but it won’t help your team make better calls.
When you build an interactive layer on a trustworthy, well-contextualized data foundation, you enable planners and operators to work hand in hand with AI.
That’s when the magic happens.
Humans stay in control while offloading the repetitive grunt work to their AI helpers.
It’s tempting to jump straight to agentic AI, especially with the hype swirling around these tools. But if you ignore the layers underneath, you risk rolling out AI that fails spectacularly — or worse, quietly undermines confidence in your systems.
A three-layer approach helps supply chain teams scale responsibly, build trust, and prioritize business impact.
It’s not about slowing down; it’s about setting yourself up to move faster, with fewer costly mistakes.
Curious how this framework looks in action?
Watch our on-demand webinar with Norfolk Iron & Metal for a deeper dive into layered AI strategies for supply chains.
The post The three-layer AI strategy for supply chains appeared first on DataRobot.
While the battle of the AI titans raged on in Q2, 2025, ChatGPT – in many respects – ended up ‘owning’ the quarter.
New figures from Similarweb, for example, revealed that ChatGPT currently controls 80% of the AI market – and attracts more AI users than its next nine competitors combined.
Meanwhile, ChatGPT also offered a flurry of upgrades during the quarter, including:
–The ability to connect ChatGPT directly to your data library via OneDrive, SharePoint and other popular database platforms
–A memory boost that enables ChatGPT to remember every one of your interactions — so it can grow continually more adept at serving your AI needs
–A jump in overall smarts, which officially made ChatGPT smarter than 98% of all humans
Even so, a Gallup poll found that despite all the powerhouse AI currently available from ChatGPT and its competitors, only 8% of human workers use AI on a daily basis.
Plus, inexperienced users of AI continued to end-up with egg-on-their-face, including the Chicago Sun-Times, which published a ‘summer fun’ guide riddled with AI-hallucinated facts.
Here’s a complete rundown of the Top Ten Stories that helped shape AI in Q2, 2025:
*ChatGPT Controls 80% of the AI Market: Despite their best efforts, competitors to ChatGPT are unable to approach the chatbot’s influence worldwide.
Observes writer Jose Antonio Lanz: “ChatGPT attracts more traffic than the next nine AI tools combined, with 5.5 billion visits crushing Gemini and Claude.
“ChatGPT has become the default AI assistant for hundreds of millions of users worldwide.”
*AI Users: ‘AI Has Tripled My Productivity:’ A new survey of U.S. workers finds they’re reducing the time it takes to complete some tasks by as much as two-thirds.
Moreover, 40% of U.S. workers reported they were using AI in some way in April 2025 –- as compared to 30% of workers just four months prior.
Even so, more gains would be possible if more of these early adopters would leverage relatively sophisticated applications of AI, such as AI-powered, deep research, AI agents and similar advanced AI systems, according to Ethan Mollick, a business technology professor at the University of Pennsylvania.
*ChatGPT Now Connects to Your Data Library on OneDrive or SharePoint: Writers and researchers with a wealth of data stored on MS OneDrive or SharePoint have a new, competitive advantage: They can now seamlessly integrate those databases with ChatGPT Deep Research.
The new feature, still in beta testing, enables users to prompt ChatGPT’s Deep Research tool to search those databases – which is especially handy if you know that the data you’re looking for is there, but you don’t know precisely where.
Other database platforms that also integrate with ChatGPT – at least in this beta application – are Dropbox and GitHub.
ChatGPT Plus, Pro and Team subscribers already have access to this extremely powerful new capability.
Access for ChatGPT Education and Enterprise subscribers is promised soon.
*ChatGPT: Matching the Right AI Engine for Your Task: ChatGPT runs on a number of different AI engines these days – each optimized for specific tasks.
Here’s the breakdown:
–Everyday writing: ChatGPT-4o is the go-to alternative for everyday writing tasks. It’s heavily tried, true and tested.
–Advanced Creative Writing: ChatGPT-4.5 is billed as an advanced creative writing tool – especially for users looking for AI with advanced emotional intelligence. The only downside: If you’re on ChatGPT Plus, you can only send 20 messages to ChatGPT-4.5 each month.
*New ChatGPT AI Engine Smarter than 98% of Humans: Stick a fork in it: Apparently, the battle of wits between humans and AI is so yesterday — and we flesh-bags have lost.
New test results from Mensa — the global group of the rumoredly smartest people in the world — show that one of ChatGPT’s newest AI engines, o3, has an IQ of 136.
Observes writer Liam Wright: “The score, calculated from a seven-run rolling average, places the model above approximately 98% of the human population.”
Currently, ChatGPT runs on a number of specialized AI engines — including ChatGPT-4o, which is rated best overall for writing.
ChatGPT-o3 was designed to excel in reasoning, math and other hard sciences applications.
*ChatGPT Gets a Memory Boost: ChatGPT’s memory — which helps many writers by getting to know how and why they’re using ChatGPT — just got a boost.
Writer Cecily Mauran reports that “ChatGPT can now reference all of your past chats to provide more personalized responses.
“In addition to the saved memories that were there before, it can now reference your past chats to deliver responses that feel noticeably more relevant and useful.”
*Gallup: Only 8% of U.S. Workers Use AI Daily: In a stunning finding, a Gallup poll reveals that only 8% of U.S. workers use AI on a daily basis.
This in the face of other, markedly different study findings that indicate interest in AI is skyrocketing — including a DemandSage report finding that ChatGPT alone enjoyed 4.5 billion visits in March 2025.
Even more perplexing: Widespread AI adoption at the workplace is currently most prevalent in jobs that are heavily dependent on creativity and in-depth analysis, such as marketing, financial and similar reporting, law and IT.
That could mean that after accounting for the heavy use of AI in all those creativity/analysis heavy jobs, as little as 2% of rank-and-file white collar workers are actually using AI on the job every day.
The bottom line: Apparently, based on this June 2025 poll, U.S. business still has not picked-up on the message that using AI for something as simple as email — in terms of cost savings alone — is a no-brainer.
*Washington Post: Got an Opinion? Let Our AI Write It for You: Sages on bar stools across the globe, rejoice: The Washington Post is working on new AI that will forge your words of wisdom into op-ed gems.
Dubbed ‘Ember,’ the tool promises to automate several functions provided by human editors, including helping amateur writers develop an early thesis, supporting points and a memorable ending to their unique perspectives.
Observes writer Emma Roth: “The move is reportedly part of a broader initiative to open the paper to outside opinion pieces.”
*Now Made by AI: 30,000 Hyper-Local Newsletters: Thousands of town and neighborhood newsletters once curated by human beings are now being processed by AI, according to newsletter giant Patch.
Essentially, Patch discovered the hyper-local newsletters simply could not be sustained using human curation.
Observes Simone Wilson, former product manager, Patch, explaining the need for the switch: “There were certain communities where we couldn’t sell an ad to save our lives.”
*Oops: Chicago Sun-Times Publishes AI-Generated Gibberish: In yet another egg-on-my-face AI moment, a Chicago newspaper published an AI guide to summer fun that features made-up books and experts.
According to writer Mia Sato, the AI-generated, hallucinatory guide was created by Hearst Media and then published by the Chicago Sun-Times without so much as a quick glance to verify accuracy.
‘Facts-take-a-holiday’ moments in the guide include the non-existent book, “Nightshade Market,” the nonexistent food expert, Dr. Catherine Frost and the non-existent professor of leisure studies, Dr. Jennifer Campos.
Share a Link: Please consider sharing a link to https://RobotWritersAI.com from your blog, social media post, publication or emails. More links leading to RobotWritersAI.com helps everyone interested in AI-generated writing.
–Joe Dysart is editor of RobotWritersAI.com and a tech journalist with 20+ years experience. His work has appeared in 150+ publications, including The New York Times and the Financial Times of London.
The post Top Ten Stories in AI Writing, Q2 2025 appeared first on Robot Writers AI.