To scale a testing program effectively, empower distributed marketing teams to run their own experiments. Providing easy-to-use tools within a familiar platform (like Sitecore XM Cloud) democratizes the process, leveraging local and industry-specific knowledge while avoiding the bottleneck of a central CRO team.

The evolution of a protocol like MCP depends on a tight feedback loop with real-world implementations. Open source clients such as Goose serve as a "reference implementation" to test and demonstrate the value of new, abstract specs like MCPUI (for user interfaces), making the protocol's benefits concrete.

MCP shouldn't be thought of as just another developer API like REST. Its true purpose is to enable seamless, consumer-focused pluggability. In a successful future, a user's mom wouldn't know what MCP is; her AI application would just connect to the right services automatically to get tasks done.

OpenAI integrated the Model-Centric Protocol (MCP) into its agentic APIs instead of building its own. The decision was driven by Anthropic treating MCP as a truly open standard, complete with a cross-company steering committee, which fostered trust and made adoption easy and pragmatic.

The MCP protocol's primitives are not directly influenced by current model limitations. Instead, it was designed with the expectation that models would improve exponentially. For example, "progressive discovery" was built-in, anticipating that models could be trained to fetch context on-demand, solving future context bloat problems.

While traditionally creating cultural friction, separate innovation teams are now more viable thanks to AI. The ability to go from idea to prototype extremely fast and leanly allows a small team to explore the "next frontier" without derailing the core product org, provided clear handoff rules exist.

PostHog manages its 16+ product suite by assigning small, autonomous teams of roughly three engineers to each product. This "compound startup" approach allows them to go wide, competing with multiple point solutions while remaining flat and avoiding bureaucracy. The small team structure fosters ownership and rapid development.

MCP acts as a universal translator, allowing different AI models and platforms to share context and data. This prevents "AI amnesia" where customer interactions start from scratch, creating a continuous, intelligent experience by giving AI a persistent, shared memory.

A key competitive advantage wasn't just the user network, but the sophisticated internal tools built for the operations team. Investing early in a flexible, 'drag-and-drop' system for creating complex AI training tasks allowed them to pivot quickly and meet diverse client needs, a capability competitors lacked.