Agentic workflows involving tool use or human-in-the-loop steps break the simple request-response model. The system no longer knows when a "conversation" is truly over, creating an unsolved cache invalidation problem. State (like the KV cache) might need to be preserved for seconds, minutes, or hours, disrupting memory management patterns.

To run reliably in the cloud, AI agents cannot be simple synchronous API calls. Their long-running, stateful nature requires an asynchronous architecture. This typically involves a message broker and task queue to farm out agentic loops to ephemeral workers, preventing process failures and enabling scalability.

Traditional software relies on predictable, deterministic functions. AI agents introduce a new paradigm of "stochastic subroutines," where correctness and logic are abdicated. This means developers must design systems that can achieve reliable outcomes despite the non-deterministic paths the AI might take to get there.

Traditional systems can be controlled with simple, deterministic rules. Because modern AI agents are inherently unpredictable, effective governance requires using another layer of AI. A specialized AI must monitor, interpret, and block the actions of other agents in real-time.

An 'AI SRE' will inevitably destroy a production database without the right primitives. The crucial missing piece isn't better AI, but infrastructure that can safely and cheaply clone production environments for the AI to test its changes before applying them.

Unlike traditional SaaS, AI applications have a unique vulnerability: a step-function improvement in an underlying model could render an app's entire workflow obsolete. What seems defensible today could become a native model feature tomorrow (the 'Jasper' risk).

Unlike deterministic software which follows set rules, AI agents are non-deterministic. This allows them to be manipulated or to hallucinate, creating a higher risk profile and requiring a much higher bar for security controls when they access critical systems.

Unlike traditional software, AI products have unpredictable user inputs and LLM outputs (non-determinism). They also require balancing AI autonomy (agency) with user oversight (control). These two factors fundamentally change the product development process, requiring new approaches to design and risk management.

A critical, non-obvious requirement for enterprise adoption of AI agents is the ability to contain their 'blast radius.' Platforms must offer sandboxed environments where agents can work without the risk of making catastrophic errors, such as deleting entire datasets—a problem that has reportedly already caused outages at Amazon.