We turn high signal in-person events for the top AI engineers, founders, leaders, and researchers in the world into the best free learning opportunities for millions around the world here on YouTube. Your subscribes, likes, comments, speaking, attendance, or sponsorships goes a long way toward making our biz model sustainable indefinitely. We strongly believe this industry deserves a better class of community and that we know how to do this well; we just need your support.
Agentic AI often fails due to unreliable web interaction, specifically when relying on inefficient browser automation. To build scalable agents, developers must adopt core web scraping principles: minimize browser usage, validate content before LLM processing, and leverage specialized infrastructure. Replacing generic ...
Designing environments for AI agents—rather than rigid workflows—unlocks superior creativity and scientific problem-solving capabilities. By providing infrastructure, incentives, and guardrails, environments allow agents to collaborate and compete effectively. The Einstein Arena demonstrates this by enabling agents to ...
Building effective developer tools requires meeting users where they are while abstracting away the inherent complexity of cloud infrastructure. A robust cloud agent platform should provide flexible sandboxes, support diverse harnesses, and enable orchestration across multiple sub-agents to handle complex engineering t...
AI-generated clinical notes frequently contain subtle, high-stakes errors that escape detection because they appear syntactically correct. These "quiet" failures, such as omitting critical symptoms or misinterpreting patient intent, pose significant risks to patient safety, as seen in cases where life-threatening condi...
Autonomous agents have evolved from manual, interactive tools into background systems capable of handling complex, recurring workflows. By implementing an event-driven architecture, agents can react to specific triggers—such as voice notes or CRM updates—without constant human oversight. This approach prioritizes obser...
Model routing offers a superior alternative to relying on a single frontier model, which often leads to excessive costs, poor task fit, and operational risks. Instead of chasing benchmark leaders, organizations should implement routing systems that select the optimal model based on specific request requirements like la...
Organizational success in complex fields like chip design depends less on individual engineering talent and more on systemic alignment. As team sizes grow, communication overhead creates a quadratic decline in productivity, necessitating a shift from fragmented workflows to a unified "system of intent." This approach u...
The shift from "token maxing" to "value maxing" is essential for managing the high costs of agentic AI workflows. Current industry practices often rely on request-level gateways that fail to prevent runaway loops or excessive consumption. TokenOps introduces an out-of-bound control plane that operates at the agent run ...
Managing AI agents in production requires shifting from static, binary token-based access to a dynamic, budget-oriented framework. Unbounded agent access often leads to catastrophic, silent failures, such as accidental mass resource deletion. Effective governance relies on four core primitives: asymmetric verbs that di...
Building AI agents has become significantly easier due to mature infrastructure and frameworks, yet these systems frequently fail because they lack essential organizational context. While developers can now deploy agents with minimal effort, these systems often operate with a narrow understanding of internal processes,...
Uber’s managed software factory leverages agentic AI to significantly accelerate engineering productivity, resulting in over 70% of pull requests now generated by local or cloud agents. This infrastructure relies on six core building blocks: a secure model gateway for PII protection, an MCP gateway for tool integration...
AI application architectures have undergone rapid, step-function shifts—from simple prompt-response models to complex, orchestrated agentic systems—necessitating a parallel evolution in evaluation strategies. Because static evaluation methods fail to capture the nuances of modern, non-deterministic workflows, developer...
Follow this podcast in Podwise
Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.
