The top 1% of AI companies making significant revenue don't rely on popular frameworks like Langchain. They gain more control and performance by using small, direct LLM calls for specific application parts. This avoids the black-box abstractions of frameworks, which are more common among the other 99% of builders.
Related Insights
Recognizing there is no single "best" LLM, AlphaSense built a system to test and deploy various models for different tasks. This allows them to optimize for performance and even stylistic preferences, using different models for their buy-side finance clients versus their corporate users.
In the fast-evolving AI space, Vercel's AISDK deliberately remained low-level. CTO Malte Ubl explains that because "we know absolutely nothing" about future AI app patterns, providing a flexible, minimal toolkit was superior to competitors' rigid, high-level frameworks that made incorrect assumptions about user needs.
Simply offering the latest model is no longer a competitive advantage. True value is created in the system built around the model—the system prompts, tools, and overall scaffolding. This 'harness' is what optimizes a model's performance for specific tasks and delivers a superior user experience.
Don't just sprinkle AI features onto your existing product ('AI at the edge'). Transformative companies rethink workflows and shrink their old codebase, making the LLM a core part of the solution. This is about re-architecting the solution from the ground up, not just enhancing it.
For specialized, high-stakes tasks like insurance underwriting, enterprises will favor smaller, on-prem models fine-tuned on proprietary data. These models can be faster, more accurate, and more secure than general-purpose frontier models, creating a lasting market for custom AI solutions.
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.
High productivity isn't about using AI for everything. It's a disciplined workflow: breaking a task into sub-problems, using an LLM for high-leverage parts like scaffolding and tests, and reserving human focus for the core implementation. This avoids the sunk cost of forcing AI on unsuitable tasks.
AI platforms using the same base model (e.g., Claude) can produce vastly different results. The key differentiator is the proprietary 'agent' layer built on top, which gives the model specific tools to interact with code (read, write, edit files). A superior agent leads to superior performance.
Unlike sticky cloud infrastructure (AWS, GCP), LLMs are easily interchangeable via APIs, leading to customer "promiscuity." This commoditizes the model layer and forces providers like OpenAI to build defensible moats at the application layer (e.g., ChatGPT) where they can own the end user.
Instead of offering a model selector, creating a proprietary, branded model allows a company to chain different specialized models for various sub-tasks (e.g., search, generation). This not only improves overall performance but also provides business independence from the pricing and launch cycles of a single frontier model lab.