The 'agents vs. applications' debate is a false dichotomy. Future applications will be sophisticated, orchestrated systems that embed agentic capabilities. They will feature multiple LLMs, deterministic logic, and robust permission models, representing an evolution of software, not a replacement of it.
Many AI developers get distracted by the 'LLM hype,' constantly chasing the best-performing model. The real focus should be on solving a specific customer problem. The LLM is a component, not the product, and deterministic code or simpler tools are often better for certain tasks.
Building a functional AI agent demo is now straightforward. However, the true challenge lies in the final stage: making it secure, reliable, and scalable for enterprise use. This is the 'last mile' where the majority of projects falter due to unforeseen complexity in security, observability, and reliability.
Relying solely on natural language prompts like 'always do this' is unreliable for enterprise AI. LLMs struggle with deterministic logic. Salesforce developed 'AgentForce Script,' a dedicated language to enforce rules and ensure consistent, repeatable performance for critical business workflows, blending it with LLM reasoning.
Instead of starting from scratch on AWS or GCP, founders building niche vertical applications can leverage a PaaS like Salesforce. This provides pre-built enterprise-grade infrastructure, security, and data models, offering a significant head start and allowing small teams to compete with larger ones.
Early in Salesforce's history, Steve Jobs advised Mark Benioff to create an app economy. Benioff acquired the 'App Store' domain but ultimately chose the name 'AppExchange' after focus testing. He later gifted the original domain to Jobs, who used it for the iconic iTunes App Store.