Startups can compete with large AI labs by capturing unique user interaction data from specialized workflows. This proprietary "user signal" enables post-training of models for specific tasks, creating a defensible advantage that labs, lacking that specific context, cannot easily replicate.

Companies like Intercom and Cursor are proving that fine-tuning open-weight models on specific, "last-mile" user interaction data creates cheaper, faster, and more accurate models for vertical tasks (like customer service or coding) than general-purpose frontier models from labs like OpenAI.

The notion of building a business as a 'thin wrapper' around a foundational model like GPT is flawed. Truly defensible AI products, like Cursor, build numerous specific, fine-tuned models to deeply understand a user's domain. This creates a data and performance moat that a generic model cannot easily replicate, much like Salesforce was more than just a 'thin wrapper' on a database.

The key for enterprises isn't integrating general AI like ChatGPT but creating "proprietary intelligence." This involves fine-tuning smaller, custom models on their unique internal data and workflows, creating a competitive moat that off-the-shelf solutions cannot replicate.

As AI application layers become easier to clone, the sustainable competitive advantage is moving down the tech stack. Companies with unique, last-mile user interaction data can build proprietary models that are cheaper and better, creating a data flywheel and a moat that is difficult for competitors to replicate.

As AI makes building software features trivial, the sustainable competitive advantage shifts to data. A true data moat uses proprietary customer interaction data to train AI models, creating a feedback loop that continuously improves the product faster than competitors.

Relying solely on expensive frontier models is unsustainable. Vertical AI companies must build a portfolio of smaller, specialized models that match frontier performance on specific tasks but cost 100x less, effectively allocating intelligence where it's needed most.

By training a smaller, specialized model where company data is in the weights, firms avoid the high token costs of repeatedly feeding context to large frontier models. This makes complex, data-intensive workflows significantly cheaper and faster.

Companies create defensibility by generating unique, non-public data through their operations (e.g., legal case outcomes). This proprietary data improves their own models, creating a feedback loop and a compounding advantage that large, generalist labs like OpenAI cannot replicate.