AI agents are now becoming central to marketing workflows. These agents are designed to handle manual, repetitive and time-consuming work, executing tasks inside systems like CRMs, analytics environments and marketing automation tools.
However, agentic AI requires a strong foundation to deliver value. According to Deloitte, nearly 60% of AI leaders and representatives cite their primary challenge in adopting agentic AI as integrating it with legacy systems. Agents need more than just API access; they need structured context, clear guardrails and actionable instructions. Without the proper foundation, agents can create friction rather than value.
A new open standard is emerging to aid the connection of data and AI/LLM tools: MCP, or the Model Context Protocol.
Continue reading this article on digiday.com. Sign up for Digiday newsletters to get the latest on media, marketing and the future of TV.