More The AI Native Dev episodes
Published 3 Feb 2026
Duration: 2697
AI skills are standardized software components that enable agents to perform tasks and are becoming a crucial aspect of efficient AI workflow development.
One skill took coding success from 28% to 71%. Another made things worse. Guy Podjarny and Simon Maple tested 1000+ agent skills and reveal which ones...
The podcast examines the evolving role of "skills" in AI agents, describing them as standardized units of context that guide agents in performing specific tasks. These skills are not a new concept, as similar functionalities exist in tools like Cursor and Claude, but recent standardization effortsespecially by Anthropichave increased their visibility and adoption. Skills are typically stored in skill.d files, which include metadata, definitions, and supporting materials, allowing for the gradual introduction of knowledge to prevent overwhelming the AI's context window.
The discussion addresses several challenges in managing these skills, including the tendency to copy and duplicate them instead of treating them as reusable software components. There is a strong emphasis on the importance of lifecycle management, testing, and distribution through package managers to ensure proper maintenance and scalability. Tesla has recently integrated support for skills, offering features like evaluation and package management, which highlights the growing importance of skills in enhancing the reusability of context and improving the efficiency of AI agents. The industry's move toward skill-based context engineering signals a broader trend toward standardization, reusability, and more efficient workflow development across AI platforms.
12 May 2026 "AI Doesn't Stand for Artificial Intelligence" Venkat Subramaniam's Take Will Change How You Think About It
AI in software development requires balancing its speed and automation with human accountability for safety and ethics, emphasizing rigorous quality practices, community-driven adoption, critical thinking, and oversight to ensure AI complements rather than replaces human judgment.
5 May 2026 The Creator of Spring Thinks You Can't Code Serious Software With AI
Integrating AI into enterprises via HTTP calls and existing infrastructure requires balancing language agnosticism, deterministic frameworks like GOAT, Java/Kotlin over Python for reliability, and prioritizing explainability, human oversight, and alignment with business logic over overreliance on AI for simple tasks.
28 Apr 2026 What OpenAI, Stripe & ElevenLabs Devs Do Differently Now | AI Native Dev
The text examines challenges in integrating AI into software workflows, highlights AI-native practices like Stripe's Minions automating code tasks, emphasizes balancing human oversight with automation, and explores future trends in agent-native engineering, specialized models, open-source tools, and ethical considerations in AI-driven development.
21 Apr 2026 Logan Kilpatrick on Who Ships AGI, DeepMind and the Problem With More Software
Software developers must adapt to AI's complexity by bridging tools with real-world applications, mastering context engineering, shifting toward high-level design and system architecture, and navigating fragmented ecosystems as AGI emerges as an integrated system rather than a standalone model.
14 Apr 2026 Everything 100 Episodes Revealed About AI Native Dev
AI in software development shifts from code-centric practices to context- and specification-driven approaches, with humans prioritizing decision-making and oversight while AI handles implementation, but challenges like non-human-readable code, alignment with team practices, and contextual accuracy remain critical.