Overhyped and Underestimated: Cutting Through the AI Noise with Glen McCracken
Yoni sat down with Glen McCracken, CPTO at Lantum, to talk about separating AI hype from reality, how to create “pull” for AI from the front lines, and why the hardest problems in AI are almost never
I’ve been recording the Building with AI: Promises and Heartbreaks podcast for a while now, talking with people who are actually building things with AI, not just posting hot takes about it.
My recent conversation with Glen McCracken was one of those “I wish more boards could listen to this” episodes. (episode available here)
Glen is the Chief Product and Technology Officer at Lantum, a health-tech scale-up helping the NHS and other providers manage their workforce. He’s been working with what we now call “AI” for nearly 30 years. At one point he was literally working with the creators of R. He’s also one of my favorite contrarian voices on LinkedIn, and the only person I know who can explain AI adoption with a cartoon and a single sentence.
In the episode, Glen described AI as:
“overhyped and underestimated.”
That framing stuck with me. So in this post, I want to unpack a few of the big ideas from our conversation and translate them into concrete actions for data, analytics and AI leaders.
1. The noise machine, FOMO and “overhyped and underestimated”
Glen spends a lot of time calling out the noise machine around AI: vendors exaggerating, analysts inventing new categories, consultants telling you that you are already behind and must “move faster”.
He likes hype up to a point. Hype gets boards asking questions. It gets budgets allocated. It creates curiosity.
The problem starts when the question is:
“How do we shove AI into our organization?”
instead of:
“Where are we in pain, and could AI help us do this better?”
AI on LinkedIn now feels like Instagram for enterprise technology.
On Instagram, everyone is in Bali, eating perfect food, with perfect kids, in perfect light. Meanwhile your real life is: breakfast with your kids, Slack, six Zoom calls, and maybe some cold coffee.
On LinkedIn, every AI demo looks magical. Every company claims “we transformed X in 30 days with agents”. If you’re a leader sitting in the middle of a very real, very messy organization, you start to think:
“Is my AI journey wrong? Is my company behind? Am I missing something?”
Glen’s answer is basically: you are seeing the highlights reel, not the truth. The truth is much closer to what we wrote about in “Sorry for the mess” – everyone’s data is messy, and it’s Okay and Stop saying “Garbage In, Garbage Out”, no one cares.
You don’t see:
The pilots nobody talks about because they quietly died
The security reviews that blocked half the “magical demos”
The teams who don’t have time to adopt the shiny thing because their backlog is already full
The goal is not to opt out of AI because of the hype, and it’s not to chase the hype either. It is to use the hype as air cover while you work on more boring, durable things: foundations, people, data, and actual business problems.
2. Push vs pull: why your best AI projects don’t start in a boardroom
One of Glen’s most useful lenses is how he classifies projects:
“There are push projects and pull projects.”
Push projects: someone senior decides “we need AI”, or “we need an LLM strategy”, and pushes projects down into the organization.
Pull projects: the business feels pain and is actively trying to pull help in. “This takes me 6 hours a week, there has to be a better way.”
Push projects, in Glen’s experience, “are really hard and invariably will fail”.
Pull projects are where the magic happens.
If you listened to our earlier episode with Meenal Iyer and read the write-up (Building an AI-powered Intelligent Enterprise), you’ll recognize the pattern: the best ideas come from the front line, not from the ivory tower.
Glen added another useful concept: moving your organization from “subconsciously incompetent” to “consciously incompetent” about AI.
Right now, in many companies:
People don’t know what is possible with AI
They do know that their work is painful and inefficient
They don’t have the language or examples to connect the two
So his advice is simple:
Raise AI literacy: Give people safe ways to play with tools like ChatGPT, Claude, n8n, Make, etc., in their personal lives and in low-risk work contexts.
Let them feel that “there is a better way to do this”.
When they start coming to you with “Could we use something like this to…?”, that’s your backlog.
This is also where managing upwards comes in.
If your board is pushing you with “we need to do more with AI”, you often need to:
Acknowledge the push
Translate it into a pull strategy
Buy time to do the boring work: literacy, foundations, and discovery
It is more honest to say:
“Yes, we’re on it. Here’s how we’re surfacing bottom-up opportunities and validating them.”
than to spin up three impressive but doomed pilots that will be in the “95% that fail”.
If you want a broader framework for this, The right way to set your data & analytics strategy goes into how to anchor D&A (and now AI) in real business priorities instead of tool shopping.
3. “Taking the robot out of the human”: AI and job fear
We talked about one of the hottest fear zones: SDRs and sales automation.
In one of his examples, Glen mentioned the classic pattern: you bring in AI to automate sourcing and outbound sequencing, and SDRs immediately ask:
“Is this thing going to replace me?”
Glen’s answer comes from years in robotic process automation (RPA). In that world, there is a line he referenced:
“Automation is all about taking the robot out of the human, so it’s taking those highly repetitive activities out of the human.”
You don’t eliminate the role. You change its shape:
The repetitive, rules-based parts (if-then-else) get automated
The exception handling, judgment, and relationship work move up in importance
We see something similar at Solid. We use tools like Amplemarket for outbound. Instead of writing 200 semi-personalized emails, a human defines:
Who we want to talk to
What value prop should resonate
What “story” we want to tell
Then the system generates and executes the outreach, with actual tailoring at scale.
The result:
The machine never gets tired
Humans spend their time on conversations, not copy-paste work
Performance goes up, not down
None of this makes the fear go away automatically. That fear is human. Which means you have to design for it:
Involve people early in defining how AI will change their work
Be explicit that they are still accountable for outcomes
Give them tools that clearly make their day better, not just “more monitored”
When people feel something is being done to them, they resist. When they feel they are co-designing it, they lean in.
4. A real example: turning sales escalations into a “client 360” AI assistant
My favorite part of the conversation was a concrete story from Glen’s previous role leading data, analytics and AI at a large fintech.
The sales team had a familiar problem:
To get a deal approved, they had to prepare a long escalation email for senior management.
That email had to explain: history with the client, product usage, outages, contract evolution, comparable deals, recent interactions, external signals about the customer, and more.
It took hours of manual digging across multiple systems.
Salespeople were very clear on their pain:
“There has to be a better way. We want to spend more time selling and less time doing admin.”
Glen’s team built what was essentially a RAG-powered “client 360” assistant:
It pulled data from CRM, ticketing, usage, billing and external sources
It assembled everything into the exact escalation format leadership expected
It did this in minutes, not hours
A few things stood out:
They ran it in parallel first. Salespeople kept doing escalations the old way while the AI tool generated its own version. That gave the team real-world feedback and “human in the loop” reinforcement.
Adoption became self-reinforcing. The people in the pilot started getting hours back. Others saw that and wanted in. The “coalition of the willing” grew organically.
Quality went up, not just speed. Before, escalation quality varied a lot by region, product and salesperson. Now, everyone was effectively getting the help of “the best escalation writer in the company”.
There was also one unexpected downside:
Senior leaders realized that, previously, they could infer a salesperson’s thinking and skill from how they wrote escalations. Once AI standardized everything, that signal disappeared.
Their solution was clever: since they already had transcripts and emails flowing into the system, they built a lightweight coaching tool. It gave feedback to both the salesperson and their manager on things like:
How discovery calls were run
How objections were handled
Where follow-ups were falling through
Same data, different product, different purpose.
There is a pattern here that echoes a lot of what we’ve written before, especially in Beyond Efficiency: How AI is Redefining Data Analytics:
Start from a painful, specific workflow
Build something that obviously helps the humans
Expect second-order effects, and be ready to build on the new foundations you just created
And, crucially, Glen kept repeating: the salesperson is still responsible.
You do not want to hear: “Well, the AI wrote it, so if it’s wrong, that’s not on me.”
5. Stop waiting for perfect data
If you work in data, you’ve probably heard (or said):
“We can’t do AI until our data is clean.”
Glen has lived through the opposite.
In that same fintech, they were stitching together systems from more than 40 acquisitions. Different CRMs, billing tools, ticketing, you name it. The temptation was:
“Let’s fix the data first. Then we’ll build the cool stuff.”
Instead, they:
Built useful Power BI reports and AI tools earlier
Accepted that some data would be wrong
Made it trivial for business users to flag issues
The result: they effectively crowdsourced data QA.
The people who knew the data best – the ones using it every day – now had a reason and a channel to say:
“This says they’ve been a client for three years. It’s at least seven.”
That feedback then improved the underlying pipelines for everyone.
Glen’s main regret: they should have started earlier.
This lines up almost perfectly with what we argued in “Sorry for the mess” – everyone’s data is messy, and it’s Okay and Stop saying “Garbage In, Garbage Out”, no one cares:
No one has a perfectly clean house
You cannot and will not fully “tidy up” before you invite AI in
The right question is: “How do we build AI that can live in the mess and help us clean where it matters most?”
That requires humility from the data team:
You test and monitor as much as you can
You do your own anomaly detection and sanity checks
But you are honest that the map is not the terrain, and you treat your users as partners, not just consumers
6. Do you really need a “VP of AI”?
Later in the conversation, I asked Glen to bust an AI myth in one sentence.
He went straight for this one:
“AI is really easy to implement. Like it really is… the myth I would bust would be that AI is hard. It’s not hard.”
If a vendor tells you “AI is hard”, his suggestion is simple:
Find one who genuinely thinks it is easy – because they’ve actually done it before.
His view on org design matches that.
He likes Charles Handy’s old idea of federated organizations and applies it to AI:
You can create a separate AI office, a VP of AI, an “AI center of excellence”
Or you can embed AI responsibility into every function, the way we did with email and the internet (Reut talked about this too)
Marketing owns AI for marketing, Sales for sales, Finance for finance, with support from central data/AI teams
You didn’t appoint a Chief Email Officer when email showed up. You taught everyone how to use it.
That doesn’t mean there is never a case for a central AI team. Sometimes you really do need tight governance, shared infrastructure and consistent standards. At Solid, our platform team exists for a reason.
But if all AI energy is concentrated in a single “tower”, you get:
Slow feedback loops
Misaligned incentives
Leaders who aren’t building AI skills in their own orgs
If, instead, AI is part of how every CxO does their job, you get:
Better problem selection
More realistic expectations
Less magical thinking, more delivery
7. Practical takeaways for AI and D&A leaders
If you are a CDAO, CPO, CTO or Head of Data reading this while your LinkedIn feed screams “You’re already behind on AI”, here is how I’d summarize Glen’s playbook.
1. Start from pain, not from models.
Build your roadmap from pull: real, repeated pain that business teams are begging you to fix. “We spend 10 hours a week on X” is a better starting point than “We should have an agent strategy.”
2. Use hype as cover, not as a spec.
The noise machine buys you air cover to invest in literacy, foundations and boring plumbing. It doesn’t define your success metrics.
3. Invest in literacy and experimentation.
Your goal is to move people to “consciously incompetent” about AI. They should know enough to say, “I think we could automate this,” even if they don’t know how.
4. Design for augmentation, not replacement.
Repeat Glen’s line to your teams: automation is about “taking the robot out of the human”. Roles will change. They should also become more interesting.
5. Get something useful in front of people before the data is perfect.
Let your users help you discover where the real data problems are. Just don’t treat them as unpaid QA – respect their time and close the loop when they flag issues.
6. Keep humans accountable.
No “the AI did it” excuses. If your name is on the presentation, email or escalation, you own it. AI is a tool, not a shield.
7. Make AI everyone’s job.
Support from central teams is important. But the real responsibility sits with the people who own outcomes in Sales, Marketing, Product, Finance and Operations.
If you want to hear Glen in his own words – including his story about working with the creators of R back in the 90s, why he loves Otter, and why he thinks we’ll still be fighting about hype five years from now – you can listen to the full episode of Building with AI: Promises and Heartbreaks with him.
And if you’re trying to make sense of where AI actually fits in your own data and analytics journey, we’re always happy to talk about how Solid can help.
Great article Yoni!