Christ First | AE @Airtable | Host - MSP Revenue Secrets

Rhondre Giscombe

I've been studying GTM engineering workflows in my free time.

Across the stack, I'm seeing three layers:

And across the stack it’s Three Layers.

Layer 1: Data
Your CRM. Data warehouse. Product usage data.
The foundation every software company has.
Mostly accessed by Data, Engineering, and some GTMEs.

Layer 2: Intelligence
Where orchestration happens.
Accounts get enriched, scored, routed.
Messaging gets prepped. Emails drafted.
This is where RevOps, Marketing Ops, Sales Ops, and GTMEs live.

Layer 3: Engagement
Where reps actually work.
Most salestech is fighting to own this layer.

I use five tools daily: Airtable, LinkedIn, Outreach, Claude, Salesforce.
Trying to get it down to three. Ideally one.

Here's the thing: the better my intelligence layer works, the less time I waste figuring out who to talk to and what to say.

Intelligence feeds me the signal. I send smarter outreach. That becomes pipeline. That closes.

Am I thinking about this right? What am I missing?

Would love to hear from folks building or operating in this space.

brendan short Brandon Smith Chris Balestras Joe Rhew

Disciple of Christ | GTM @Airtable | Building apps & agents for Operators

I've been trying to understand how Claude Code impacts GTM work. Still early in my research, but one thing keeps standing out.

The compounding intelligence piece.

From what I'm seeing, it's not just about build speed. It's about how context accumulates over time.

Feed it call transcripts and it updates your ICP definition. Feed it more data and it refines what you thought was true. It challenges your assumptions and suggests new angles you might have missed. The system doesn't just store information. It iterates on what you know.

A few other initial observations:

1️⃣ The build speed is real. Clay tables, n8n workflows, JSON configs all ship noticeably faster.

2️⃣ Every Claude Code project pulls context from markdown files. ICP definition, messaging framework, competitor intel. Modularizing your GTM knowledge this way should make outputs more accurate and consistent across projects.

It's designed to compound intelligence, not just automate tasks. The system learns your business over time and gets smarter with every input you feed it.

3️⃣ It's not as "non-technical" as advertised. You still need to understand APIs, JSON structure, and how to set up proper context. There's a learning curve if you haven't touched these concepts before.

Would love feedback if I'm heading in the right direction here.

Matteo Tittarelli ⚡️ Jordan Crawford Jacob Dietle Joe Rhew Taimoor Tariq Javeria Shah

Over the next 4 weeks, I'm building an AI-powered call brief system in Airtable.

Not because I need another project. Because I used to spend 15 minutes before every call scrambling to remember what matters.

Here's what my prep used to look like:

Open the CRM to check deal history. Fire up Perplexity for recent company news. Review Gong history for previous calls. Check product usage data. Skim LinkedIn for the contact's background. Then tie together the core questions I should ask.

Every. Single. Time.

I built a system that does this for me. One hour before any scheduled call, an automation kicks off. It pulls everything I need, synthesizes it with AI, and drops a call brief in Slack with a link to an Airtable interface.

I already use a version of this, but I'm rebuilding it in public so you can see how this actually works in Airtable.

Quick note on scope: This leans into what Airtable does well: centralizing data from different sources. Company news, CRM deal history, Gong call summaries, product usage signals, all synthesized through AI. If you need third-party intent signals (job changes, website visits, LinkedIn engagement), other platforms handle that better.

Before I touch a single automation or field, I need to answer three questions. Skip this, and you'll build something you don't actually use.

⚫️ What's the desired outcome?
✔️ A call brief one hour before every first discovery call. Not raw data. A synthesized view: What's happening at this company? What's our history? How are they using the product? What should I focus on in this conversation?

⚫️ What's required to make this work?
✔️Company news (AI field agents or Perplexity) 
✔️ Deal history (Salesforce) 
✔️ Gong call summaries 
✔️ Product usage data 
✔️ Contact context (LinkedIn) 
✔️ Core discovery questions 
✔️ AI synthesis on what to focus on

⚫️ What does the workflow look like?
✔️ Trigger: Calendar event detected
✔️ Process: Automation pulls data, AI synthesizes the brief
✔️ Output: Slack notification with link to Airtable interface

I open the interface, scan the brief, and show up prepared.

Once I have clarity on those three, then I get into the fun stuff: table structure, automations, integrations, and the interface layer.

Next week: Starting the build. I'll show you the data model and first automation.

Most Airtable users don't know you can enrich LinkedIn profiles natively.

Here's how:

Use Airtable Field Agents to pull LinkedIn profiles as long as you have their Full Name and Company Name.

Back in November, one of my customers was manually finding LinkedIn URLs for 3,000 contacts. Every time a new prospect was logged into their system, they'd pull the profile by hand.

We built with an Airtable Field Agent and ran it across all 3,000 records in 5 minutes.

Coverage landed around 60-70%. Accuracy on matches was about 80%.

Not perfect. But good enough for their use case.

Now every new contact logged into Airtable automatically pulls their LinkedIn profile.

I'll drop the exact prompt in the comments.

Call sentiment alone doesn't tell you if a customer is at risk. 

You need the full picture. 

Airtable integrates with Gong so RevOps teams can cross-reference call transcripts with product usage, CRM health scores, and support ticket trends in one place. 

→ Spot sentiment shifts in calls 
→ Layer in product adoption signals 
→ Surface real risk before it shows up in churn reports 

Complete customer intelligence in one system. 

Check it out today.

I'm going through HubSpot's RevOps Academy in my free time.

As I'm learning more about GTM engineering, I realized I needed deeper RevOps knowledge to understand how revenue operations actually work across the business.

Here's what's landing so far:

1. RevOps makes growth exponential by improving operational efficiency across the business

It's not just sales efficiency. It's marketing, customer success, product, everything that touches revenue.

2. Flywheel model beats funnel model

Customers don't disappear after they buy. They fuel growth if your systems are set up right.

3. Force and friction benefit the organization, even when it doesn't feel like it

The right friction in the right place keeps bad data and bad process from spreading.

4. You need the right number of leads as you scale, not just more
Volume without qualification breaks everything downstream.

5. The buyer's journey: Awareness (problem aware), Consideration (solution aware), Decision (provider aware)

Targeting certification by late Jan / mid Feb.

That said, what else should I be paying attention to? Any core lessons or principles I need to add?

Brandon Smith Jeff Ignacio Haris Odobasic Stefan Mersch 💭 Sebastien van Heyningen

I've been building AI-native apps on Airtable, Lovable, and Replit.

Here are 9 lessons that changed how I approach rapid app development:

1️⃣ Build in layers, not one-shot builds
Nail one component, then move to the next. It's easier to fine-tune and catch issues early.

2️⃣ Clarity of outcome is essential
AI platforms need clear targets. Vague inputs get vague outputs.

3️⃣ Edge cases require knowledge, not just prompts
AI handles standard paths well. Edge cases need platform expertise to close the gap.

4️⃣ Platform flexibility is the real unlock
Airtable lets you reshape your data model mid-build. That flexibility is the foundation of rapid app development.

5️⃣ AI is core to how these platforms work
It's not tacked on, it's foundational to what's possible and how fast you can move.

6️⃣ Advanced functions require platform familiarity
Formulas, automations, and integrations aren't plug-and-play. Expertise accelerates shipping.

7️⃣ Building happens in minutes. Production-grade takes weeks.
The first version is fast. Making it reliable and scalable is where the real work is.

8️⃣ Operators can build without waiting on IT
Quick wins in weeks vs waiting quarters for engineering to pick up your ticket.

9️⃣ The best builds are simple
The apps that stick solve one problem really well.

Rapid app development still requires expertise; it just shifted where it matters. But platforms like Airtable, Lovable, and Replit are unlocking what operators can build on their own.

Build with Airtable today. Link in the comments.

I asked AI to build a competitor to SpaceX.

It came back with a full competitive analysis deck in 20 minutes.

We just launched Superagent, a whole new Airtable product.

I gave it one prompt: "Create a competitive analysis deck of the commercial space market and opportunities for differentiation."

Multiple specialized AI agents deployed. Each tackled a different piece: market analysis, competitive positioning, timeline synthesis, regulatory requirements, technology comparisons.

20 minutes later: rich visuals, interactive charts, full citations. Ready to present.
This isn't another AI summary tool. It's a research and design team working in tandem.

If your team is blocked on competitive analysis or market research that requires real depth, give Superagent a try: bit.ly/3ZC0m40

Most AI roadmaps in 2025 started with the wrong question.

They asked "What can AI do?" instead of "Where are my teams spending time on work that doesn't require a human?"

With AI adoption moving past experimentation in 2026, companies are deploying actual use cases and getting tremendous gains.

So let's look at where AI is getting deployed:

1️⃣ Summarization & Synthesis 
Product teams are condensing product feedback from support tickets, sales calls, and user interviews into actionable themes that inform roadmap prioritization.

2️⃣ Classification & Prioritization 
Product Operations teams are ranking feature requests by revenue association so teams build what impacts the bottom line first.

3️⃣ Personalization at Scale 
Marketing teams at retail companies are generating email copy drafts across multiple campaigns, each one tailored to customer segments and purchase history.

4️⃣ Workflow Automation 
Marketing Operations teams are turning campaign performance data from static reports into automated budget reallocation recommendations for next quarter while there's still time to act on it.

5️⃣ Data Enrichment 
Revenue Operations teams are finding LinkedIn URLs and contact data for prospect lists in minutes instead of hours of manual research.

6️⃣ Generation & Content Creation 
Marketing teams are creating localized campaign content across 12 regions while maintaining brand voice and compliance standards.

If you're building an AI agenda in 2026, start with the workflows you already have. The best AI implementations don't require new systems. They make your existing ones smarter.

Harvard studied 100,000 AI agent users. The pattern is clear: AI that's siloed in chat gets abandoned. AI that's integrated into actual workflows gets stickier.

The reason?

Context engineering.

Most companies buy AI tools that can't touch their CRM, their Google Drive, or their project tracker. Then they wonder why adoption stalls.

Here's the thing: AI's real value isn't answering questions. It's completing tasks. But to complete tasks well, it needs the right information at the right time. When AI is disconnected from your tools, you're getting 10% of its potential. You're stuck with a Q&A bot, not a system that can actually execute.

The breakthrough happens when AI can pull context from across your tools, take action based on that context, and learn as it completes more tasks.

This is why platforms that integrate deeply with Google Drive, email, and project management tools see higher stickiness. Users don't just ask questions. They complete workflows. The AI has context, so it can act. And as it acts more, it gets better.

When evaluating AI tools, ask yourself: Can it access the context it needs? Can it take action, or just suggest it?

Context plus action equals 10x the impact of chat alone.

(Read Will Sullivan’s full breakdown of the Harvard study, link in comments)

Week 1 of building the call brief system. If I mess up the data model now, I'll be fighting this thing for months.

And the whole point of this is to stop scrambling before calls, so I need the data to flow cleanly from the start.

I'm building seven core tables:
1️⃣ Calls (the main hub): Tracks every scheduled call. Links to Call Briefs, Contacts, and Accounts.
2️⃣ Call Briefs (the generated output): Stores the synthesized intelligence for each call. One brief per call. This is what I actually read before the call.
3️⃣ Accounts: Company-level data. Links to Deals, Product Usage, and Company Intelligence.
4️⃣ Contacts: Individual people I'm talking to. Linked to Accounts and Calls.
5️⃣ Deals: CRM history. Deal stage, notes, last activity. Linked to Accounts.
6️⃣ Product Usage: For existing customers. Bases, users, activity trends, automations created. Linked to Accounts.
7️⃣ Company Intelligence: AI-pulled company news, strategic priorities, recent developments. Linked to Accounts.

Each table does one thing. Calls are for tracking the event. Call Briefs store what I actually need to know. Accounts are where all the context lives.

Calls and Call Briefs are linked one to one, so every call gets exactly one brief. There's no duplicates or confusion on which brief belongs to which call.

Linked records mean when I update deal history in Salesforce, it flows through to the brief automatically. When product usage data refreshes, the brief reflects it. I'm not copying and pasting data across tables.

The Accounts table is the hub. Everything connects through it. Company Intelligence, Product Usage, Deals, all linked to Accounts. So when I pull a call brief, it knows which account I'm calling and it pulls everything associated with that account.

I tested this with a fake call record. Linked it to a contact and an account. Added some deal history. Data flows where it should.

Next week: Building the first automation. Can I actually pull company news and deal history on a schedule?

If your tables don't talk to each other cleanly, your automations will break. And you'll be right back to scrambling before every call.

Built this entire base structure with Airtable's Omni in 10 minutes. The hard part isn't building the tables anymore. It's knowing how they should connect.

Most AI projects fail midway through.

Not because the tech doesn't work. Because the scope was never clear.

"Measure twice, cut once" was a principle from traditional trades. Carpenters and tailors used it to avoid irreversible errors and wasted materials.

Today's builders are AI engineers, FDEs, GTM operators, and non-technical people shipping apps and agents.

AI collapsed build time from months to hours. But it also means you can build the wrong thing really fast.

For AI builders, it's "Scope twice, build once."

Before you commit to a critical build, scope what you're actually trying to solve:

⚫️ The Workflow 
Not "automate project management."
But, "Our team spends 2 hours every Monday syncing status across HubSpot, Sheets, and Slack."

⚫️ The Impact
Not "save time."
But, "Cut sync to 15 minutes. Give the team 1 hour 45 minutes back."

⚫️ The Capabilities
What does "done" look like? Data sync? Auto-updates? Notifications?

⚫️ Time to Value 
Days or weeks? If it's 6 months, maybe it's not the right first project.

⚫️ The Initiative it Accelerates
Does this help you hit Q1 revenue targets? Reduce operational costs by 20%? Scale without adding headcount?

Tie it to a real OKR or strategic goal. Otherwise, you're just building because you can.

⚫️ The Phases
V1: Automate the sync. V2: Add notifications. V3: Build the dashboard. 
Don't solve everything at once.

Bad scoping: "Let's build an AI agent for project management."

Good scoping: "Our PM updates 3 systems manually every Monday. That's 2 hours. Automate the sync, give them their Monday back, help us hit our Q1 efficiency goal."

The worst thing teams do? Build fast because they can. Excitement takes over. Then they realize midway they're solving the wrong problem.

Resources wasted. Timelines blown. Sometimes people lose their jobs over a bad scope.

Clarity beats excitement.

Scope it twice. Then build it once.

Most teams are deploying AI without asking the right question.

It’s not “can we automate this?” 
It’s “what are we willing to lose?”

I’ve been building with AI for months now, across customers I consult with at Airtable and my own projects. And I keep seeing the same pattern.

AI is incredible for volume and speed. If you need 500 product descriptions written, or you’re generating e-commerce images at scale, it’s a no-brainer. The output is good enough, and you get it fast.

But the moment you need something that reflects your brand, your specific visual identity, your tone, your creative direction, AI falls short.

I’ve tested this with podcast graphics, brand assets, creative campaigns. The output is generic. It doesn’t carry the theme. It doesn’t have taste.

Here’s the tradeoff most people don’t think through. AI gives you efficiency, but it costs you originality. It gives you speed, but it costs you brand equity.

And that’s fine if you’re optimizing for volume. 
But if what you’re building is brand-critical, you can’t afford that loss.

Before you automate something, ask yourself: 
- What am I optimizing for? 
- Speed or originality? 
- What’s the tradeoff?
- What do I gain, and what do I lose?
- Can I live with that loss?

Zoom in on the task. Zoom out on the impact. 

Then decide what you’re willing to sacrifice.

Not everything should be automated. Some things still need a human in the loop.

Prob one of the best decisions I made in 2025. 

Switched from Apple Podcasts to Snipd. 

I listen to 10-15 hours of podcasts a week across faith, mindset, leadership, AI in business, RevOps/GTME. 

Snipd lets me capture insights as I go. Nothing disappears into the ether. 

Check it out if you aren't using it already.

Over the past year and a half, I’ve had the privilege to work alongside Alex. 

Among other things, three things stand out:

1 - He’s a leader that is in the trenches with you

2 - He’s a leader that challenges growing in your skillset

3 - He’s a leader that cares not just for your performance but, you personally

Joining his team is easily one of the best decisions I’ve made since, moving to ATX.

Apply today 👊🏾

P.S. You’re welcome to hmu too

Commercial Sales Leader @ Airtable | AI + Automation ⚡️

My team is growing! 🚀 I’m looking for a seller with natural curiosity, a strong desire to learn, and the drive to make a real impact. This is a hybrid role for someone who enjoys winning new business and thoughtfully expanding existing accounts over time.

You’ll partner closely with customers as they scale, helping them unlock more value with Airtable through strategic, long-term growth.

Airtable is in a pivotal phase as we build toward IPO, and this role offers real ownership and the chance to help shape what’s next.

📍 Austin (Hybrid)

If this sounds like you (or someone you know), I’d love to connect. Feel free to send me a DM.

Account Executive, Commercial Accounts  

How many internal tools is your team building that you could've bought off the shelf?

And what customer value did you trade for that distraction?

Kyle Norton talked about this on his podcast with Everett from Clay. He broke down a framework on GTM Engineering that clicked for me:

1️⃣ Buy is about 
→ Speed 
→ Broad organizational impact 
→ Resources required to support it

2️⃣ Build is about 
→ Fast execution 
→ Low org impact 
→ Or high enough strategic value to justify dedicated resources

Most things? Buy them. Very few things should you actually build.

If you're a sales tech company building an internal HR tool, you're spending engineering cycles on something Deel or Rippling already solved. That's a distraction, not a strategy.

HubSpot CTO Dharmesh Shah put it clearly: "Spend every calorie possible on creating value for your customers."

Build only when it's so unique to your workflows that it becomes a strategic asset. Something no off-the-shelf tool can do.

Everything else? Buy it and move on.

Stop writing better prompts. Start building better context. 

Most teams think the problem is their prompts. They're tweaking inputs and refining instructions, hoping AI gets smarter. It doesn't work that way. 

AI gets smarter when it has better context to work from. 

The problem is your data lives everywhere. Campaign performance in one tool. Customer intel in another. Product catalog somewhere else. 

When you ask AI to help, it's guessing because it can't see what worked last quarter or connect your product data to your customer data to your performance data. 

Every project starts from scratch and every output feels generic. 

Airtable changes this because it acts as the context layer. When everything lives in one system, AI has the full picture with relational data, linked records, and historical performance tied to real-time inputs. 

I built a demo for a fashion brand that was spending weeks aligning on every creative brief. Past performance was buried, brand guidelines lived in someone's head, and competitor research was scattered across tools. 

We moved everything into Airtable as their single source of truth. 

Now when someone starts a brief, they input the basics and the system pulls the rest: past campaigns, personas, product data, and competitive signals. 
AI drafts using what actually happened before instead of generic best practices.

Performance feeds back after launch, so the next brief is smarter because of it. 

The operators seeing results from AI aren't writing better prompts. They consolidated first and stopped fighting tool sprawl by building on one foundation. 

AI doesn't improve because the model changed. It improves because your context got better, and your context gets better when it lives in one place.

One of the features I've been pushing to every customer I work with.

With the latest improvements Airtable just shipped, there's never been a better time to explore what's possible with custom elements.

Network graphs. 3D models. Custom dashboards. If you can imagine it, you can probably build it.

Check out what builders are creating…

Introducing Built with Omni: a new showcase for builders to share bespoke AI apps 🚀

Get inspired: Browse bespoke elements created by Airtable builders.

Learn: Inspect real code and prompts to uplevel your app building skills.

Contribute your creations: Share your own apps and interfaces for others to learn from.

Plus, we launched a few key improvements to the custom elements experience:
✔️ Code inspection
✔️ Public interface support
✔️ Multi-developer support

Dive into Built with Omni →   https://lnkd.in/gDY2Kdij

WE HELP businesses across various industries automate their workflows and integrate their applications seamlessly, enhancing productivity and efficiency.

How WE DO that:
- Provide a no-code platform that allows users to create custom workflows without programming knowledge.
- Support full-code options for advanced customization and flexibility.
- Offer ready-made integrations for popular apps and services, from Microsoft 365 and Google Workspace to Slack and Discord.
- Include a wide range of AI models ready for instant use, allowing businesses to easily leverage artificial intelligence.
- Enable users to create conditional logic and branching scenarios for complex workflows.
- Ensure smooth and fast onboarding with our expert support team.
- Provide continuous updates and additions of new apps to our integration library.

Working with us, YOU WILL:
- Achieve higher efficiency by automating repetitive tasks and streamlining operations.
- Save time as our platform simplifies the integration and automation process.
- Enhance productivity with our user-friendly interface and robust feature set.
- Gain access to a wide range of pre-built integrations and the flexibility to add custom ones.
- Benefit from our dedicated support and extensive resource library to get the most out of our platform.

Oleg Zankov

AI guardrails don't slow systems down. They speed them up.

The safest AI is also the fastest.

That sounds backwards. Everyone assumes guardrails slow things down.

But Anthropic just proved the opposite.

They added clinical constraints to Claude for healthcare. Cross-referencing against 14 medical databases before every response. The kind of safety layer that should crush performance.

The result?

99% reduction in hallucinations. AND 38% faster processing.

Not despite the constraints. Because of them.

Here's what's happening under the hood.

Unconstrained models waste compute generating plausible nonsense. They spin up entire reasoning chains that go nowhere. They confidently produce garbage.

Constrained models skip that entirely. They check sources first. Generate once. Done.

The data is striking. Standard LLMs hit 87% accuracy on diagnosis support. Claude with guardrails hit 99%. It beat human clinicians on rare disease identification by 15%.

This breaks the mental model most teams are operating with.

You don't choose between safe and capable. Safe IS capable. Constraints aren't a tax on performance. They're a shortcut to it.

Every team debating whether to add safety mechanisms is asking the wrong question.

The question isn't whether you can afford the slowdown.

It's whether you can afford the waste of running without them.

Who else has seen constraints improve performance rather than degrade it?

Co-Founder & Product Owner at Latenode.com & Speaknode.com. Revolutionizing automation with low-code and AI

Meta just paid $2 billion for an AI agent company. Meanwhile, GPU costs jumped 15% last quarter.

One of these numbers will kill most AI startups. The other will save a few.

I've watched this pattern before. Big tech acquires the winners while infrastructure economics quietly crushes everyone else.

The math is getting brutal. AWS moved p5e instances from $34 to nearly $40 per hour. GDDR7 memory went from $70 to $250 for the same 16GB config. Nvidia is cutting gaming GPU production by 40% to feed datacenter demand.

Translation: compute is about to get worse, not better.

But here's what caught my attention. Average AI agent interaction time just hit 40 minutes across 57,000 users. These aren't chatbot queries. These are real workflows. Real work getting done autonomously.

The shift from assistants to agents is now irreversible.

At Latenode, we process millions of workflow executions monthly. The founders winning right now aren't the ones with the best models. They're the ones who figured out infrastructure arbitrage before costs doubled.

The acquisition price tells you where value is moving.

The GPU price tells you who won't survive the journey.

Most founders are still optimizing prompts while their unit economics silently collapse.

What's your infrastructure cost per agent interaction right now — and do you actually know the number?

The best AI model in the world is worthless if you can't plug it in.

The AI companies obsessing over better models are losing.

The winners are signing power contracts.

Here's the shift nobody's talking about:

OpenAI just committed $10 billion to Cerebras. Not for better models. For faster electricity-to-inference pipelines.

Google bought a $4.75 billion energy company. Not an AI startup. A power plant operator.

Meta became one of America's largest nuclear energy buyers. Not for PR. For survival.

The pattern is clear. The constraint moved.

From 2020-2024, GPU access determined who could compete in AI.

In 2025-2026, electricity access determines who can deploy.

Grid interconnection queues now stretch 8-12 years. You can have the world's best model sitting in a data center that can't run at full capacity because the grid won't deliver power.

McKinsey projects inference will consume 50% of all AI compute by 2030. Training is a one-time cost. Inference runs 24/7 forever.

The companies still optimizing for model quality are solving yesterday's problem.

The companies securing 15-year power purchase agreements are solving tomorrow's.

This is the new moat. Not algorithms. Electricity.

Your AI strategy without an energy strategy is a PowerPoint deck.

Who else is seeing this shift?

undefined undefined

Co-Founder & Product Owner at Latenode.com & Debexpert.com. Revolutionizing automation with low-code and AI

I automated myself.
As someone who builds automation platforms, I realized I was the worst at using them for my own work.

Content creation was my bottleneck:
- Inconsistent posting
- Hours lost to research
- Drafts sitting unfinished

So I built an AI agent workflow on Latenode that:
- Researches trending topics in my space
- Pulls specific data, stats, and sources
- Writes drafts in my tone
- Sends me a daily brief for review

Now I focus on what matters - adding real insights, personal stories, and that founder perspective no AI can replicate.

The future of work isn't AI replacing humans.

It's humans + AI doing what neither could alone.

Comment "ghost writer" and i will send full blueprint so you could run it for yourself (i know, it's annoying, but algorithms  like this:)

The AI arms race is already over. Most companies just don't know it yet.

The AI cost crisis everyone is preparing for?

It's already solved.

NVIDIA just announced Rubin. 10x cheaper inference. 4x fewer GPUs to train frontier models.

Microsoft, AWS, and Google are deploying it in 2026.

While companies scramble to raise billions for compute access, the economics underneath them are collapsing.

Anthropic just raised $10B. xAI raised $20B. They're buying infrastructure at peak prices right before the floor drops out.

This is the pattern nobody talks about:

The companies treating compute as a moat are building walls around a commodity.

Jensen Huang said it himself when validating DeepSeek's efficiency approach: "Compute advantages fade. Capital cycles turn. Algorithmic insight compounds."

The winners won't be whoever secures the most GPUs.

They'll be whoever builds the best algorithms on hardware that costs 90% less than today.

Every AI budget approved this quarter assumes costs go up.

They're about to go down. Fast.

The companies that wait 18 months will pay a fraction of what the "first movers" are paying now.

First mover advantage in AI infrastructure is actually first mover disadvantage.

Who else is watching these mega-rounds and thinking the math doesn't add up?

Bigger AI models are not smarter. They're just more expensive ways to be wrong.

The AI industry just mass a $100 billion mistake.

Samsung built a 7 million parameter model that beats OpenAI's 100+ billion parameter giants on complex reasoning.

Read that again.

7 million vs 100 billion.

The tiny model won.

Here's the part that should terrify every AI executive: a two-layer version outperformed a four-layer version. Smaller was literally smarter.

The mechanism is embarrassingly simple. Instead of throwing more parameters at problems, Samsung's model runs 16 recursive refinement cycles. It thinks in loops, not layers.

87.4% accuracy on Sudoku-Extreme. The giants couldn't touch it.

This model runs on a laptop. Not a data center. Not a $100M GPU cluster. A laptop.

The entire industry has been scaling in the wrong direction.

We've been building bigger hammers when we needed sharper scalpels.

Every company racing to train trillion-parameter models is now staring at a simple question: What if intelligence was never about size?

The researchers are calling it a 'Copernican moment.'

I'd call it a $100 billion lesson in first principles thinking.

The winners in AI won't be whoever has the most GPUs. It'll be whoever abandons the scaling religion first.

Who else saw this coming?

Got this email from Azure today.
"Sorry, we can't approve your quota increase due to high demand."

Honestly? My first reaction was panic. We're processing millions of AI agent workflows. Growth is crazy. We need 5000 more CPUs. We need that capacity NOW.

Then I remembered why we went multicloud in the first place.
Added another cloud provider. Took 24 hours. Problem solved.

Here's what hit me:
January 2026 is wild. Everyone's building AI agents. The infrastructure demand is insane. Cloud providers literally can't keep up.

"Infinite scalability" was always marketing speak, but now we're seeing the real limits.

The decision we made 2 years ago to build multicloud - it felt like over-engineering at the time. Extra complexity. More code to maintain.

Today? That decision just saved our ass.

Not sharing this to brag. Sharing because if you're building anything with AI agents right now, you're probably about to hit the same wall.
Plan accordingly.

#AIAgents #CloudComputing #FounderLessons #azure #ai #cloud

Something strange happened this morning.

I woke up to 47 perfectly drafted email responses I never wrote.

Three meeting invites sent to the right people.
Two follow-ups scheduled for next week.
And one very confused feeling...

Here's what I remember:

Last night at 11 PM, I was staring at my inbox. 127 unread emails. Drowning.

So I did something stupid.

I opened Latenode and told an AI agent: "Handle my morning email routine. Figure it out."

Then I went to sleep.

The workflow I built looked simple:
- Gmail → AI brain → Gmail Draft Reply, Calendar → Send

But here's the weird part...

The AI didn't just respond to emails.

It understood context.
It knew which meetings were urgent.
It caught the subtle "let's talk next week" and actually scheduled it.

I didn't program any of that.

This morning, I'm eating caviar for breakfast because I genuinely don't know what to do with all this free time.

My entire morning routine just... disappeared.

No more email triage.
No more "let me get back to you."
No more forgetting to follow up.

Just toast with red caviar, tea, and an existential crisis about what I'm supposed to do from 6-9 AM now.

The automation age isn't coming.

It's here. It's weirdly competent. 

P.S. Yes, that's red caviar. No, you don't need caviar to automate your life - just better tools.

The more you invest in AI transformation, the less likely you are to succeed with AI.

Your company's AI transformation initiative is why your AI isn't working.

MIT just released data on 300 enterprise AI deployments.

95% delivered zero measurable ROI.

But here's what nobody's talking about: the 5% that succeeded did the opposite of what everyone else is doing.

They didn't build. They bought.

They didn't transform. They focused on one problem.

They didn't centralize in AI labs. They let line managers lead.

The research is brutal. Internally-built AI systems succeed one-third as often as purchased solutions. Enterprise-wide initiatives stall because they spread resources too thin to solve anything well. Centralized AI teams can't understand frontline problems deeply enough to fix them.

Meanwhile, 79% of companies claim they've adopted AI agents.

Only 6% have actually deployed them.

The gap isn't technology. It's organizational theater.

Companies are announcing AI transformation while their pilots die in production limbo. They're hiring AI teams while their data infrastructure crumbles. They're chasing enterprise-wide impact while ignoring the single problem they could actually solve.

The winners aren't doing more AI.

They're doing less AI, better.

One problem. One specialized tool. One empowered team.

That's it.

The $38 billion question: Is your AI strategy actually a strategy, or just expensive theater?

#EnterpriseAI #AIStrategy #DigitalTransformation #Leadership

The most advanced AI companies are abandoning large language models.

Your company is spending 20x too much on AI.

Not because you're using the wrong vendor.

Because you're using models that are too big.

NVIDIA just published research that should make every CTO pause their AI budget:

Small Language Models - the ones that fit on a smartphone - now handle 70% of enterprise AI tasks with zero performance loss.

Microsoft's 3.8 billion parameter model outperforms GPT-4 on reasoning and coding.

A 7B model now runs in 2GB of VRAM. Down from 16GB.

92% of GPT-5.2's performance at 15% of the price.

The "bigger is better" era of AI is over.

The companies winning now aren't the ones with the biggest models.

They're the ones who realized that overkill is still waste - even when it's impressive waste.

Every enterprise AI decision made in 2024 and 2025 was based on a false assumption: that capability requires scale.

It doesn't.

The new equation is simple:

Smaller models. Faster deployment. Lower cost. Same results.

If your AI strategy still centers on "how do we access the biggest model" - you're solving last year's problem.

Who else is seeing this shift in their stack?

"Your docs are confusing" — feedback we got too many times.
So we fixed it.

Introducing Latenode's new documentation site:
✓ Clean navigation 
✓ AI Agents section (from basics to multi-agent systems) 
✓ MCP integration guides 
✓ Visual Builder tutorials 
✓ Code examples that actually work

No more hunting through outdated articles.

https://lnkd.in/dM8veKQ2

The best platform means nothing without great docs.

AI agents won't destroy retail margins. They're about to create the most profitable sales channel in history.

Everyone's building defense against AI agents.

They're about to get destroyed by brands playing offense.

Here's what nobody's talking about:

Google just launched the Universal Commerce Protocol with Walmart, Target, Shopify, and Etsy.

It doesn't help AI agents find the cheapest product.

It helps AI agents find the perfect product - and offer exclusive discounts to close the sale.

Think about what that means.

A customer asks Gemini for a "modern, stylish rug for a high-traffic dining room."

The AI doesn't show 47 options sorted by price.

It finds the exact match and triggers a personalized offer from the brand.

AI becomes the ultimate salesperson, not the ultimate price comparator.

Projected market size: $1.7 trillion by 2030.

Walmart already integrated its entire shopping experience into Gemini.

While most brands prepare for margin compression, the smart ones are building AI storefronts.

The companies treating AI as a threat will watch their competitors turn it into their highest-converting channel.

This isn't about surviving AI commerce.

It's about owning it before someone else does.

Who's already building for this?

#AgenticCommerce #RetailStrategy #AICommerce #Ecommerce #GoogleAI

The AI is not the bottleneck. Your organization is.

Your company is not waiting for AI to get better.

It is hiding behind that excuse.

GPT-5.2 now beats human experts on 71% of professional tasks.

It works 11x faster.

It costs 1% of human labor.

And yet only 2% of organizations have deployed AI agents at scale.

The other 98% keep saying the same thing: We need to wait until the technology is ready.

The technology has been ready.

What is not ready is your org chart. Your governance model. Your willingness to let AI make decisions without seventeen layers of approval.

I have watched companies run the same pilot for three years. They keep testing. Keep evaluating. Keep waiting for some magical moment when AI becomes safe enough to trust.

Meanwhile, frontier companies are saving 10+ hours per employee per week. They send 6x more AI queries than median firms. They are redesigning entire workflows while competitors debate whether to expand the pilot.

This is not a technology gap.

It is a courage gap.

The companies falling behind are not the ones with worse AI. They are the ones who keep pretending the AI is the problem.

Every quarter you spend waiting for better AI is a quarter your competitors spend pulling ahead.

The window is closing.

Who else is watching their company hide behind the technology excuse?

The companies that won the GPU arms race are now losing the AI war.

H100 rental prices collapsed 64% in 18 months.

From $8/hour to under $3.

The organizations that locked in multi-year contracts at peak pricing are now trapped. They're paying 2-3x what competitors pay for identical compute.

Here's the brutal irony.

Those expensive long-term commitments created the oversupply that destroyed their value. Companies desperate to monetize unused capacity flooded the market. 300+ new GPU providers entered. Prices cratered.

The scarcity mindset caused the abundance.

I've watched this pattern across dozens of infrastructure decisions. The companies that moved fastest are now stuck with stranded assets. The ones called "slow" or "behind" are now accessing better compute at half the cost with zero commitment.

The real competitive advantage wasn't securing GPUs early.

It was staying flexible while others panicked.

This isn't just about GPUs. It's about how fear-driven infrastructure decisions consistently backfire. The urgency to "not fall behind" creates the exact conditions that punish early movers.

Your AI strategy shouldn't be built on scarcity assumptions in a market racing toward commodity pricing.

Who else is watching their competitors regret their "winning" GPU deals?

Humanoid robots aren't coming. They're already sold out.

Everyone is debating whether humanoid robots will work.

Hyundai already sold out their 2026 production run.

While your leadership team argues about 'the future of automation,' the future quietly got a delivery date.

Here's what just happened:

Hyundai announced 30,000 Atlas humanoid robots per year starting 2028. Google DeepMind's Gemini is the brain. All 2026 units are already committed to their Georgia manufacturing facility.

These robots have 56 degrees of freedom, hands with tactile sensing, and lift 110 lbs instantly. They reason through problems before acting. They explain their decisions in plain language.

This isn't a demo. It's a deployment schedule.

The companies waiting for humanoid robots to 'prove themselves' are waiting for a milestone that passed while they weren't paying attention.

The real question isn't 'will robots replace workers.'

It's 'will your competitors get the robots first.'

Because Hyundai isn't selling a vision anymore. They're allocating capacity.

And capacity has a waitlist.

Is your industry watching this, or still treating it as science fiction?

#HumanoidRobots #ManufacturingAutomation #FutureOfWork #AIRobotics #Industry40

Cloud prices always go down. Except now they do not.

Your cloud cost model is built on a lie.

For 20 years, AWS trained us to believe one thing: prices only go down.

Every cloud migration business case. Every multi-year forecast. Every board deck. All built on the assumption that infrastructure costs decline over time.

On January 4, 2026, AWS quietly raised GPU prices 15%.

No announcement. No customer email. Just a Saturday morning pricing page update.

This is not a temporary blip.

NVIDIA has orders for 2 million H200 chips. They have 700,000 in inventory. Memory manufacturers have already sold out their entire 2026 supply. TSMC packaging capacity is oversubscribed through mid-2026.

The shortage is structural, not cyclical.

Here is what this means for you:

That 30% cost reduction you modeled for 2027? Flip it. IDC predicts large companies will underestimate AI infrastructure costs by 30% through 2027.

The playbook has changed. Once AWS raises prices on one service and the world does not end, the second increase becomes easier. And the third.

Every AI business case you approved last year needs to be stress-tested against rising infrastructure costs, not falling ones.

The companies that win will be the ones who saw this coming.

Who else is reworking their cloud forecasts right now?

Most “AI agents” live in demos.

The useful ones live where your customers already are.

In WhatsApp.

I just created a quick demo showing how to build an AI-powered WhatsApp assistant with Latenode.

Here’s what it does (in plain human terms):
- Listens for incoming WhatsApp messages
- Hands them to an AI Agent using latenode
- Replies back in WhatsApp with a real answer, not a keyword menu
- Remembers the whole conversation, so it doesn’t reset its brain every message

The flow is almost suspiciously simple:

WhatsApp trigger → AI Agent → WhatsApp response

That’s it.

No “enterprise transformation”.
No 6-month implementation saga.
Just an agent that can work for your clients inside the chat they already use every day.

Use cases I’m seeing immediately:
- Lead qualification + FAQ
- Booking / rescheduling
- Order status / support triage
- Sales follow-ups that don’t feel like spam
- Internal ops bots for teams (yes, also in WhatsApp)

If you want the demo link, comment “WhatsApp” and I’ll drop it.

NVIDIA just killed the biggest lie in voice AI.
"You can have natural conversations OR customization. Pick one."

Not anymore.

PersonaPlex is full-duplex. Listens and speaks simultaneously. Like humans.
It says "uh-huh" and "yeah" while you talk. Handles interruptions without breaking. Switches personas with a text prompt.

7B parameters. Single model replacing entire ASR → LLM → TTS pipelines.

This is why I'm obsessed with voice AI right now.

We're building SpeakNode[dot]com — connecting voices like this to CRMs, task trackers, databases through Latenode[dot]com.

Because natural-sounding voice that can't actually do anything?
That's a demo, not a product.

What would you automate first if voice AI actually worked?

Requiring a doctor for every prescription refill isn't a safeguard. It's a liability.

The most dangerous thing in healthcare isn't AI prescribing your medication.

It's a human doctor being too busy to refill it.

Utah just became the first state to let AI legally prescribe medication renewals.

The result? 99.2% match with human physician decisions across 500 cases.

Not 80%. Not 90%. Ninety-nine point two percent.

Here's what everyone misses about the "doctors must be involved" argument:

The bottleneck IS the danger.

Delayed refills. Missed doses. Patients rationing insulin because the renewal sat in a queue.

We built a system where the "safeguard" became the risk.

The AI auto-escalates uncertain cases to human doctors. It carries malpractice insurance at the same standard as physicians.

It's not replacing judgment. It's replacing waiting.

The healthcare industry spent years asking "Is AI safe enough to prescribe?"

Wrong question.

The right question: Is making patients wait for routine renewals safer than a system that matches doctors 99% of the time and flags anything uncertain?

Utah answered it.

The rest of healthcare is still debating a problem that's already been solved.

Who else thinks the "human required" assumption is due for a rewrite?

The safest AI vendor is now your biggest risk.

Staying with OpenAI is now the risky choice.

I know that sounds backwards.

For two years, "just use OpenAI" was the safe default. The boring enterprise answer. The thing you said so nobody questioned your judgment.

That math just broke.

xAI's new Grok Voice API hit the market at half the price with 5x faster response times. Time-to-first-audio of 0.78 seconds versus competitors still measuring in full seconds.

Here's what makes this dangerous for the "safe choice" crowd:

The API is drop-in compatible with OpenAI's spec. Developers are swapping endpoints with minimal code changes. Your competitors aren't rebuilding anything. They're just paying less and shipping faster.

While you're defending your OpenAI budget in quarterly reviews, teams at other companies are pocketing 50% savings and getting responses 5x faster.

The premium you're paying isn't buying better technology anymore.

It's buying the comfort of not having to explain a vendor change.

Market leaders don't stay leaders by charging monopoly prices after faster alternatives emerge. They stay leaders until they don't.

The new risk isn't switching.

It's staying.

Who else is watching their "safe" vendor become the liability?

taplio

The Battle

Rhondre Giscombe

Oleg Zankov

Followers

Posts

Engagements

Likes

Performance ScoreRhondre Giscombe's LinkedIn Performance

Performance ScoreOleg Zankov's LinkedIn Performance

Ready to grow your LinkedIn presence?

taplio

The Battle

Rhondre Giscombe

Oleg Zankov

Followers

Posts

Engagements

Likes

Performance Score.css-goub6s{font-size:var(--chakra-fontSizes-md);font-weight:500;color:var(--chakra-colors-gray-600);display:block;margin-top:var(--chakra-space-1);}Rhondre Giscombe's LinkedIn Performance

Performance ScoreOleg Zankov's LinkedIn Performance

Ready to grow your LinkedIn presence?

Performance ScoreRhondre Giscombe's LinkedIn Performance