Julie Zhu observes that many of the fastest-growing companies grow so quickly they don't have time to build robust data logging and observability. They succeed on "good instincts and good vibes," only investing heavily in data infrastructure after growth eventually stalls.
Related Insights
Before investing in complex system instrumentation, use simple surveys to get a quick baseline of developer experience. Ask engineers to name their top three productivity blockers. This provides immediate, high-signal data to prioritize where to focus deeper data collection efforts.
Companies feel immense pressure to integrate AI to stay competitive, leading to massive spending. However, this rush means they lack the infrastructure to measure ROI, creating a paradox of anxious investment without clear proof of value.
Top product teams like those at OpenAI don't just monitor high-level KPIs. They maintain a fanatical obsession with understanding the 'why' behind every micro-trend. When a metric shifts even slightly, they dig relentlessly to uncover the underlying user behavior or market dynamic causing it.
The advantage from data network effects only materializes at immense scale. The difference between a startup with 3 customers and one with 4 is negligible. This means early-stage companies cannot rely on a data moat to win; the moat only becomes visible after a market leader is established.
The biggest scaling mistake is focusing on running up numbers while ignoring the underlying mindset. During its peak growth, Facebook put every new engineer through a six-week bootcamp not for immediate productivity, but to instill the company's culture. This investment in a shared mindset is what enables sustainable scaling, preventing the chaos that comes from rapid headcount growth.
The primary reason multi-million dollar AI initiatives stall or fail is not the sophistication of the models, but the underlying data layer. Traditional data infrastructure creates delays in moving and duplicating information, preventing the real-time, comprehensive data access required for AI to deliver business value. The focus on algorithms misses this foundational roadblock.
Rapidly scaling companies can have fantastic unit economics but face constant insolvency risk. The cash required for advance hiring and inventory means you're perpetually on the edge of collapse, even while growing revenue by triple digits. You are going out of business every day.
Many AI startups prioritize growth, leading to unsustainable gross margins (below 15%) due to high compute costs. This is a ticking time bomb. Eventually, these companies must undertake a costly, time-consuming re-architecture to optimize for cost and build a viable business.
Rapid sales growth creates a powerful "winning" culture that boosts morale and attracts talent. However, as seen with Zenefits, this positive momentum can obscure significant underlying operational or ethical issues. This makes hyper-growth a double-edged sword that leaders must manage carefully.
Reviewing user interaction data is the highest ROI activity for improving an AI product. Instead of relying solely on third-party observability tools, high-performing teams build simple, custom internal applications. These tools are tailored to their specific data and workflow, removing all friction from the process of looking at and annotating traces.
