A model's value is unlocked by its "harness"—the layer of logic, tools, and integrations connecting it to a task. A coding assistant is a harness built around a base model. Focusing on harness design is more critical than the specific model for creating useful, differentiated AI products.

AI models fail in business applications because they lack the specific context of an organization's operations. Siloed data from sales, marketing, and service leads to disconnected and irrelevant AI-driven actions, making agents seem ineffective despite their power. Unified data provides the necessary 'corporate intelligence'.

An AI coding agent's performance is driven more by its "harness"—the system for prompting, tool access, and context management—than the underlying foundation model. This orchestration layer is where products create their unique value and where the most critical engineering work lies.

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.

Performance comes from a "harness" surrounding the AI model, which includes curated data, tools, and rich context. This harness, which can be open and multi-model, is where the hard work lies—prepping the context layer so that a model's plan can execute efficiently.

An AI model alone is like a brain without a body. To become a useful agent, it needs a "harness" or "scaffolding" consisting of four key components: domain-specific knowledge, memory of past interactions, tools to take actions, and guardrails for safety.

The primary barrier for useful AI agents is not the underlying model but the complex task of 'data wiring'—connecting to a user's real-world context like emails, local files, and support tickets. Products that solve this difficult integration challenge, where most agents currently fail, will gain a significant competitive advantage.

AI agents are simply 'context and actions.' To prevent hallucination and failure, they must be grounded in rich context. This is best provided by a knowledge graph built from the unique data and metadata collected across a platform, creating a powerful, defensible moat.

For enterprise applications, the choice of AI model is a minor factor. Salesforce's Gaurav Pathak argues that 95% of the battle is getting the right business data—the context—to the agent. This reframes AI investment from a focus on cutting-edge models to a focus on data infrastructure and management.