The core needs of AI agents—version control, testing, observability—mirror those of human developers. However, the sheer scale and speed of agentic workflows mean existing tools like Kubernetes are insufficient, requiring a fundamental reimagining of the entire infrastructure stack.

Instead of placing agents inside a pre-set environment, a more powerful approach for reasoning models is to start with just the agent. Then, give it the tools and skills to boot its own development stack as needed, granting it more autonomy and control over its workspace.

Instead of competing with labs on model training, the defensible strategy is to build the ideal environment or 'habitat' for an LLM in a specific vertical. Replit did this for programming by adapting its editor, cloud infrastructure, and deployment tools to serve the AI, not just the human.

Running multiple, complex AI coding agents simultaneously is computationally prohibitive on local machines. Stripe's success relies on their ability to spin up numerous isolated cloud development environments in parallel, a crucial investment for any team serious about agentic engineering.

Warp was initially known as an "AI terminal," a niche market focused on command-line assistance (Docker, Git). The company's growth dramatically accelerated when they pivoted to launching a great coding agent. This addressed the much larger market of core development activity, where most developers spend their time.

Many developers believe tweaking prompts and logic ('harness engineering') is the hardest part of building agents. The real bottleneck, however, is scaling, reliability, and managing production infrastructure—a common miscalculation that managed services aim to solve.

The company leveraged its deep expertise in application integration (its "pre-AI era" business) to build a foundational layer for AI agents, providing the necessary hooks and data pipelines for them to function effectively.

The true capability of AI agents comes not just from the language model, but from having a full computing environment at their disposal. Vercel's internal data agent, D0, succeeds because it can write and run Python code, query Snowflake, and search the web within a sandbox environment.

The manual management of deployment and monitoring will become obsolete. A new, fully AI-managed stack will emerge, allowing founders to simply ask an agent to build and iterate on products. The company's main communication tool may even become the interface for managing these agents.