Tokenless

Feature

5 Best Practices for Building AI Agent Skills

5 Best Practices for Building AI Agent Skills

This video outlines five essential best practices for developing reliable, secure, and effective AI agent skills. It covers optimizing skill triggering through descriptive metadata, leveraging real-world domain expertise over generic LLM output, managing context windows efficiently by writing lean skills and using progressive disclosure, implementing deterministic logic with scripts for fragile operations, and critically vetting all skills for security vulnerabilities before deployment. These practices are crucial for professionals building robust agentic systems.

Velocity Sickness: What Happens When Your Whole Team Gets 10x Faster — Matt Dailey, Ref.

Velocity Sickness: What Happens When Your Whole Team Gets 10x Faster — Matt Dailey, Ref.

Matt Dailey introduces "velocity sickness" – the stress of increased AI output without impact. He proposes shifting from ephemeral chat-based agent interactions to durable, shared documents as the "decision layer" to separate planning from implementation, enabling teams to own their code and prioritize ideas effectively.

The playbook for building high talent density teams | Adam Ward, Head of Talent at Cursor

The playbook for building high talent density teams | Adam Ward, Head of Talent at Cursor

Adam Ward, Head of Talent at Cursor, dissects the hyper-competitive current hiring market, contrasting the inefficient "funnel of doom" with a strategic, executive-level approach to recruiting top 1% talent. He details a three-step playbook—scoping, mapping, and relentless pursuit—emphasizing personalized engagement, robust work trials, and continuous candidate care. Ward also outlines common founder mistakes in early recruiting hires, the rise of the "forward-deployed engineer," and the critical qualities of effective recruiters, arguing for their strategic importance and high compensation.

Realtime multiplayer, automation, and you! — Idan Gazit, GitHub

Realtime multiplayer, automation, and you! — Idan Gazit, GitHub

Idan Gazit, head of GitHub Next, discusses the future of AI in software development, moving beyond personal productivity to enabling group collaboration and advanced automation. He introduces two prototypes: "Agentic Workflows" for autonomous, secure code upgrades and task execution using natural language, and "ACE," a real-time collaborative development environment designed to integrate AI into team workflows, addressing the 95% of development work beyond mere typing.

Benchmarking Coding Agents on New vs Legacy Codebases — Denys Linkov, Wisedocs

Benchmarking Coding Agents on New vs Legacy Codebases — Denys Linkov, Wisedocs

Denys Linkov details Wisedocs' journey of refactoring a complex, distributed ML pipeline into a monorepo, benchmarking the process against evolving AI coding tools. He honestly audits whether the six-month effort was justified, or if waiting for more advanced AI would have been better, ultimately concluding that the significant social and technical benefits made the refactor a successful strategic move despite current LLM limitations.

Anthropic's CCA Exam as a Field-Guide for Agentic Engineering — Frank Coyle, UC Berkeley

Anthropic's CCA Exam as a Field-Guide for Agentic Engineering — Frank Coyle, UC Berkeley

Frank Coyle demystifies the Claude Certified Architect exam by dissecting key scenarios and highlighting common anti-patterns in Agentic AI design. He provides actionable best practices, emphasizing effective tool use, context management, specialized agent architectures, and cost-saving techniques, all centered on understanding what to avoid to build robust LLM applications.

← PreviousNext →