Fine-tuning creates model-specific optimizations that quickly become obsolete. Blitzy favors developing sophisticated, system-level "memory" that captures enterprise-specific context and preferences. This approach is model-agnostic and more durable as base models improve, unlike fine-tuning which requires constant rework.

Unlike AI startups that fine-tune models immediately, enterprise token usage will primarily come from adapting systems and harnesses around base models. Most enterprises encounter significant operational friction fine-tuning internal data and instead achieve task customization by wrapping off-the-shelf open models in bespoke agent workflows.

Before considering expensive model fine-tuning, implement Retrieval-Augmented Generation (RAG). RAG dynamically retrieves information from a knowledge base to augment the prompt, solving most domain-specific problems efficiently. The recommended hierarchy is: Prompt Optimization -> Context Engineering -> RAG -> Fine-tuning.

View a general-purpose LLM as a highly athletic but untrained high schooler. To make it great at a specific task, you must build a "harness" around it, providing specialized coaching, real-time data feeds, and feedback loops to develop its domain-specific expertise.

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.

"Context Engineering" is the critical practice of managing information fed to an LLM, especially in multi-step agents. This includes techniques like context compaction, using sub-agents, and managing memory. Harrison Chase considers this discipline more crucial than prompt engineering for building sophisticated agents.

The focus in AI has shifted from crafting the perfect prompt (prompt engineering) to providing the right information (context engineering), and now to building the entire operational environment—tooling, systems, and access—that enables a model to perform complex tasks. This new paradigm is called harness engineering.

While many parts of an agent harness can be generic (e.g., prompt caching), domain-specific harnesses gain a competitive edge through custom verification logic. In high-stakes fields like finance or legal, tweaking the error handling between model and execution is a key product differentiator.

As base model capabilities converge, the key differentiator is shifting to the "agent harness"—the infrastructure, tools, and skills built around the model. For vertical AI, this is where domain expertise is injected, creating specialized agents with custom tools that outperform generalist models.