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.

Effective enterprise AI needs a contextual layer—an 'InstaBrain'—that codifies tribal knowledge. Critically, this memory must be editable, allowing the system to prune old context and prioritize new directives, just as a human team would shift focus from revenue growth one quarter to margin protection the next.

Effective agent memory is not merely a storage layer. It's an encapsulated system for learning and adaptation that integrates embedding models, re-rankers, databases, and LLMs, all working in concert to hold, move, and store data.

AI agents need a multi-faceted memory architecture inspired by human cognition. This includes episodic (time-stamped events), semantic (world knowledge), procedural (workflows and skills), and working memory (immediate context window).

Instead of treating memory as a component, adopt a "memory-first" approach when designing agent systems. This paradigm shift involves architecting the entire system around the core principles of how information is stored, recalled, and forgotten.

A single AI agent struggles with diverse tasks due to context window limitations, similar to how a human gets overwhelmed. The solution is to create a team of specialized agents, each focused on a specific domain (e.g., work, family, sales) to maintain performance and focus.

Instead of relying solely on massive, expensive, general-purpose LLMs, the trend is toward creating smaller, focused models trained on specific business data. These "niche" models are more cost-effective to run, less likely to hallucinate, and far more effective at performing specific, defined tasks for the enterprise.

The "agentic revolution" will be powered by small, specialized models. Businesses and public sector agencies don't need a cloud-based AI that can do 1,000 tasks; they need an on-premise model fine-tuned for 10-20 specific use cases, driven by cost, privacy, and control requirements.

While the "bitter lesson" suggests powerful general models will dominate, vertical AI solutions can thrive by deeply integrating with a company's specific data, workflows, and project context. The model can't know this proprietary information; value is created by the application that bridges this gap.