{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/4c35a817a91543ea8763e8b55bf1d0ef\" frameborder=\"0\" width=\"1728\" height=\"1296\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1296,"width":1728,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1296,"thumbnail_width":1728,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/4c35a817a91543ea8763e8b55bf1d0ef-38dabc9ea8fd7869.gif","duration":2135.376,"title":"Leveraging AI and MCP for Cost Estimation in FinOps 🚀","description":"In this video, Thiago and I explore the integration of AI agents and the Model Context Protocol (MCP) in the context of FinOps, specifically through a demo scenario involving an IoT platform prototype on AWS. We walk through the process of estimating costs, creating an Infrastructure as Code script, and evaluating actual costs against our estimates as we scale the prototype. Our findings indicate a daily cost of approximately $0.72, which aligns closely with our initial estimates. We also discuss the importance of using the right context and tools for the models to enhance their performance. I encourage viewers to consider how these insights can be applied to their own projects and to share their thoughts on the potential of MCP in their workflows."}