Agentic media buying cannot scale without the right foundation, as the current process relies on emails, spreadsheets, PDFs, and phone calls, causing fragmentation and delays. The bottleneck is coordination, not talent, with no standardized way to discover inventory or evaluate audiences, making each connection a bespoke integration. Agentic workflows using LLMs and protocols like MCP can automate the loop of reading briefs, researching publishers, and negotiating price. However, automation alone is insufficient; IAB Tech Lab's Agentic Advertising Management Protocols (AAMP) standards establish a shared vocabulary for inventory and audiences (AdCOM), a common transaction protocol (OpenDirect, OpenRTB deals), and a registry model for discovery and trust, enabling any compliant buyer agent to transact with any compliant seller agent. Databricks provides the foundation for where agents run, including their state, models, identity, and governance. An example of agentic media buying and selling was built fully on Databricks, where autonomous buyers and sellers discover each other, agree on price, and close deals, using the official open source IAB Tech Lab Software Development Kit (SDK) to avoid lock-in at the protocol layer.