Presentation: Platform Teams Enabling AI - MCP/Multi-Agentic Tools Across Linkedin

LinkedIn’s Karthik Ramgopal and Prince Valluri discuss leveraging AI as a new execution model for large-scale engineering. They explain how to move beyond fragmented implementations by building platform abstractions for orchestration, structured context, and safe tooling like MCP. They share architectural insights from real-world coding, observation, and UI testing agents built at LinkedIn. By Karthik Ramgopal, Prince Valluri
The proliferation of AI models is pushing enterprises to develop robust platform solutions for managing and orchestrating AI agents at scale, moving beyond fragmented pilot projects to integrated operational systems.
This development indicates that large enterprises are concretely implementing AI into their core engineering processes, highlighting the practical application and scaling challenges of AI, which is critical for future productivity and competitive advantage.
The focus is shifting from individual AI model development to platform-level abstractions that enable multi-agentic systems for complex engineering tasks, indicating a move towards systemic AI integration rather than isolated applications.
- · AI platform providers
- · Large enterprises adopting AI
- · Software engineers proficient in AI orchestration
- · Cloud infrastructure providers
- · Companies with fragmented AI strategies
- · Manual software testing services
- · Legacy enterprise software vendors
- · Teams unable to integrate AI agents
Enterprise engineering workflows will become increasingly automated and efficient through multi-agentic AI systems.
The demand for specialized AI platform engineering talent will surge, creating new career paths and skill gaps.
This platform-centric approach to AI will likely become a new standard for complex enterprise operations, pushing industries towards deeper AI integration and further collapsing white-collar manual tasks.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at InfoQ