Despite industry talk, there is currently no software that can orchestrate and manage various third-party AI agents from different vendors. Teams must manage each agent in its own siloed interface, creating significant operational overhead.

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.

Despite the hype, LinkedIn found that third-party AI tools for coding and design don't work out-of-the-box on their complex, legacy stack. Success requires deep customization, re-architecting internal platforms for AI reasoning, and working in "alpha mode" with vendors to adapt their tools.

Many current agentic AI products are built by connecting AI to technologies, like databases, that were never designed for it. Mykhailo Marynenko calls this 'gluing shit and sticks together' and argues it's a fundamentally flawed approach. Truly innovative AI products require rebuilding the underlying infrastructure from first principles.

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.

A major trend in AI development is the shift away from optimizing for individual model releases. Instead, developers can integrate higher-level, pre-packaged agents like Codex. This allows teams to build on a stable agentic layer without needing to constantly adapt to underlying model changes, API updates, and sandboxing requirements.

An AI-native application is not a traditional app with an AI feature; it's architected around AI from the start. This requires developers to master a new stack including language models, vector databases, and agentic workflows, moving beyond just REST APIs and traditional databases.

Early agent development used simple frameworks ("scaffolds") to structure model interactions. As LLMs grew more capable, the industry moved to "harnesses"—more opinionated, "batteries-included" systems that provide default tools (like planning and file systems) and handle complex tasks like context compaction automatically.

Using a composable, 'plug and play' architecture allows teams to build specialized AI agents faster and with less overhead than integrating a monolithic third-party tool. This approach enables the creation of lightweight, tailored solutions for niche use cases without the complexity of external API integrations, containing the entire workflow within one platform.