M&A Deal Flow

Subject: This Week's AI M&A: Follow the Data, Ignore the Hype

Ins7ghts Readers,

Forget the breathless headlines about "AI dominance." This week's funding activity reveals a far more nuanced, and frankly, predictable power play. The real story isn't about who's building the best model, but who's building the infrastructure to support those models.

The Obvious (and Overhyped):

Yes, Anthropic and OpenAI are still vacuuming up capital. We see articles about Anthropic potentially securing a $25B round, and OpenAI chasing $50B from the Middle East. This is table stakes. They're in a race to build, train, and deploy ever-larger models. But here's the thing: throwing money at compute isn't a long-term strategy. It's a land grab.

The Signal in the Noise:

The real action is in the data infrastructure layer. Look at ClickHouse. They just raised a $400M Series D. Why? Because everyone is drowning in data and needs fast analytics. The ability to ingest, process, and query massive datasets in real-time is becoming the bottleneck. Companies like ClickHouse are the picks and shovels of the AI gold rush.

Then there's OpenEvidence, a medical AI startup valued at $12 billion. They secured $250M in funding. This is interesting because it highlights the growing importance of AI in specialized domains like healthcare, where regulatory hurdles and data privacy concerns are paramount.

The Hot Take:

The current AI funding frenzy is unsustainable. We're heading for a reckoning. The companies that will survive and thrive aren't necessarily the ones with the biggest models, but the ones with the most efficient and cost-effective infrastructure. The focus will shift from model building to model deployment and operationalization.

The M&A Landscape - What to Watch:

| Category | Companies to Watch | Why

Subject: This Week's AI M&A: Follow the Data, Ignore the Hype (cont.)

Ins7ghts Readers,

Forget the breathless headlines about "AI dominance." This week's funding activity reveals a far more nuanced, and frankly, more interesting picture.

You asked about the largest acquisition. On paper, it's impressive: Databricks acquiring Tabular for a cool $1.1 Billion. Everyone's talking about the price tag, but they're missing the point. This isn't about "buying AI," it's about owning the modern data stack.

Think about it. Databricks already had a strong position with Delta Lake. Tabular brings Apache Iceberg, arguably Delta Lake's biggest competitor, into the fold. This isn't just consolidation; it's a strategic land grab.

Hot Take: Databricks isn't just buying tech; they're buying optionality. By controlling both major open table formats, they effectively dictate the rules of the game for data lakehouses. This is a power play, plain and simple. Expect to see them push a unified "Delta Lake + Iceberg" story, subtly steering users towards their preferred implementation.

The real winners here? Netflix, for open-sourcing Iceberg in the first place, and the early engineers at Tabular who are now sitting on a mountain of Databricks stock.

What does this mean for you?

• Don't blindly commit to a single table format. Understand the strengths and weaknesses of both Delta Lake and Iceberg.
• Negotiate hard with Databricks. Their increased market power means they'll be less flexible on pricing.
• Invest in skills around Apache Iceberg. Even if you're a Delta Lake shop, understanding Iceberg will make you a more valuable data professional.

This isn't the end of the data lakehouse wars, but it's a significant escalation. Keep your eyes on how Databricks integrates Tabular, and be ready to adapt your strategy accordingly.

– Yves

Subject: This Week's AI M&A: Follow the Data, Ignore the Hype (cont.)

Ins7ghts Readers,

Forget the breathless headlines about "AI dominance." This week's funding activity reveals a far more nuanced,

...and frankly, more interesting picture. You asked about valuations. Here's the inconvenient truth: it's not just about the AI, it's about the infrastructure and the compliance surrounding it.

Everyone's chasing the shiny object of generative AI, but the real money is flowing into the picks and shovels – the tools that make AI usable, secure, and, crucially, legal.

Look at the trend drivers this week:

See a pattern? "AI Regulation" is the top trend, dwarfing even "Agentic AI." This isn't about building the next GPT; it's about navigating the minefield of AI ethics and legislation.

Hot Take: The companies that will truly win in the next 12-18 months aren't the ones with the flashiest models, but the ones that can demonstrably prove their AI is compliant, unbiased, and secure. Think about it: every enterprise deploying AI at scale needs this.

This is why I'm watching companies like Databricks and Snowflake so closely. They're not just data warehouses; they're becoming the central nervous system for AI governance. They're positioning themselves to be the gatekeepers of responsible AI, and that's where the real long-term value lies.

Specific Advice:

• If you're investing: Look beyond the hype. Focus on companies building tools for AI governance, data privacy, and regulatory compliance. Due Diligence must include how AI models are being used and what risks are associated.
• If you're building: Don't just focus on model accuracy. Prioritize explainability, bias detection, and security. Build compliance into your product from the ground up.
• If you're deploying: Demand transparency from your AI vendors. Ask tough questions about their data sources, training methods, and bias mitigation strategies. Don't just accept "trust us."

The AI gold rush is on, but the smart money is being made selling the shovels – and the compliance certifications.

Yves Mulkers