Building Open Infrastructure for the Agentic Era | Bryan McCann, CTO You.com

Building Open Infrastructure for the Agentic Era | Bryan McCann, CTO You.com

🎙 Bryan McCann 👥 5K 📅 October 24, 2025 ⏱ 35 min 👁 76 📄 expert opinion 🧭 2026-08-15
Available in: English (current) Français

Keywords

agentic AIopen infrastructureweb indexsearch APIsMLOps

Summary

In this keynote at MLOps World 2025, Bryan McCann, CTO of You.com, discusses the need for open infrastructure to support AI agents. He argues that the current web infrastructure, designed for human consumers, is inadequate for autonomous agents. McCann highlights the tension between open ecosystems and walled gardens, warning that businesses risk becoming data providers to dominant platforms. He emphasizes the importance of building composable APIs, including web indexes and vertical indexes, to enable agentic AI without vendor lock-in. He shares lessons from his research on transfer learning and contextualized word vectors, stressing the importance of context and evaluation. McCann advises companies to focus on being better at something specific, solving dire needs, and owning the evaluation process. He also notes the trend of search APIs being restricted, pushing companies into ecosystems. The talk concludes with a call for the MLOps community to contribute to building open infrastructure to prevent monopolies and enable sustainable AI development.

156 words

Critical Evaluation

Value of the Information & Strength of the Argument

The talk provides valuable insights into the challenges and opportunities of building AI infrastructure for agents. McCann’s argument is well-structured, drawing on his personal experience and industry observations. He effectively highlights the risks of closed ecosystems and the importance of open alternatives. The argumentation is persuasive, though it relies heavily on anecdotal evidence and personal opinions rather than empirical data. The speaker’s credibility as CTO of You.com adds weight to his claims, but the lack of concrete examples or case studies limits the depth of the argumentation.

Scientific Rigor, Source Quality, Title Accuracy

The talk demonstrates a good level of scientific rigor in terms of referencing his own research and industry trends. However, it lacks formal citations to external sources, relying instead on personal experience and general knowledge. The title accurately reflects the content, focusing on open infrastructure for the agentic era. The speaker mentions specific papers and concepts, but does not provide URLs or detailed references. The overall quality of sources is moderate, with a reliance on expert opinion rather than peer-reviewed literature.

183 words

Title / Content Match

The title accurately reflects the content, which focuses on building open infrastructure for AI agents.

Quality & Reliability

7/10

The talk is an expert opinion from a CTO with significant industry experience, providing insights into AI infrastructure and open ecosystems. It references specific technical concepts and personal experiences, but lacks formal citations or peer-reviewed sources. The claims are plausible and align with industry trends, but the reliability is limited by the absence of verifiable data.

Key Moments

Cited Sources

  • MLOps World — Conference website where the talk was recorded.

Concurring Sources

  • MLOps World — Conference website, consistent with the talk's theme.

Contribution & Novelties

The talk provides a unique perspective on the need for open infrastructure for AI agents, emphasizing the importance of web indexes and composable APIs. It offers practical advice for companies and highlights the risks of closed ecosystems. The speaker’s background in NLP research adds depth to the discussion.

Pour aller plus loin :

94 words

Radar Profile

The radar profile shows high scores in quantity of information and global reliability, indicating a content-rich and credible talk. The technical level is moderate, making it accessible to a broad audience. The quality of information is good, but the lack of formal citations slightly reduces the reliability score.

Reliability 7/10

💬 No comments were provided for analysis.