The transformative power of AI agents is unlocked by professionals with deep domain knowledge who can craft highly specific, iterative prompts and integrate the agent into a valid workflow. The technology itself does not compensate for a lack of expertise or flawed underlying processes.

The primary barrier for enterprise AI is the 'context gap.' Models trained on public data have no understanding of your specific business—its metrics, language, or history. The key is building infrastructure to feed this proprietary context to the AI, not waiting for smarter models.

Maxima's founder, a former accountant, believes AI tools fail when built by the practitioners themselves. He argues the domain expert's role is to define problems and architect the solution, while top AI engineers handle construction, like a Formula One driver designing a car they don't build.

Building an AI application is becoming trivial and fast ("under 10 minutes"). The true differentiator and the most difficult part is embedding deep domain knowledge into the prompts. The AI needs to be taught *what* to look for, which requires human expertise in that specific field.

The effectiveness of an AI system isn't solely dependent on the model's sophistication. It's a collaboration between high-quality training data, the model itself, and the contextual understanding of how to apply both to solve a real-world problem. Neglecting data or context leads to poor outcomes.

Product managers may lack the expertise to create comprehensive evals from scratch. A better approach is to generate initial outputs with a base model, have subject matter experts review them, and use their direct feedback to define what constitutes a failure. It's easier for experts to spot mistakes than to predict them.

Assigning error analysis to engineers or external teams is a huge pitfall. The process of reviewing traces and identifying failures is where product taste, domain expertise, and unique user understanding are embedded into the AI. It is a core product management function, not a technical task to be delegated.

As AI capabilities become commoditized, the key to superior output is the user's domain expertise. An expert with precise vocabulary can guide an AI to produce better results in one attempt than a novice can in many, because they can articulate the desired outcome more effectively.

Since current AI is imperfect, building for novices is risky because they get stuck when the tool fails. The strategic sweet spot is building for experts who can use AI as a powerful but flawed assistant, correcting its mistakes and leveraging its strengths to achieve their goals.