{"podcast":{"title":"Day Two DevOps","slug":"day-two-devops","podcast_index_feed_id":341814,"rss_url":"https://feeds.packetpushers.net/day2cloud/","website_url":"https://packetpushers.net/","image_url":"https://static.feedpress.com/logo/day2cloud-669fc5e024d4b.jpg","author":"Packet Pushers","episode_count":250,"summary":"Join hosts Ned Bellavance and Ethan Banks as they dive deep into the challenges of cloud operations from the perspective of seasoned practitioners. You'll hear from expert guests—technical leaders, trainers, and consultants with years of hands-on experience—discussing the nuances of modern cloud environments. From AWS to Azure, networking to security, automation to DevOps, each weekly episode equips you with the insights to confidently address tech and business challenges such as resilience, cost management, and performance. Whether you want to hone your skills today or prepare for what’s coming next, Day Two Cloud cuts through the vendor fog to guide you through a shifting IT landscape.","last_synced_at":null,"page_url":"https://stenobird.com/podcast/day-two-devops"},"episode":{"title":"D2DO279: Herding the Agentic Geese","slug":"d2do279-herding-the-agentic-geese","published_at":"2025-08-13T15:47:42+00:00","page_url":"https://stenobird.com/podcast/day-two-devops/d2do279-herding-the-agentic-geese","show_page_url":"https://stenobird.com/podcast/day-two-devops","url":"https://packetpushers.net/podcasts/day-two-devops/d2do279-herding-the-agentic-geese/","audio_url":"https://feeds.packetpushers.net/link/20975/17119116/D2DO279.mp3","summary":"Developers from Block discuss the development of Goose, an agentic AI agent, and the rise of 'vibe coding.' The conversation explores the tension between rapid AI-driven development and the necessity of engineering rigor, observability, and human oversight.","meta_description":"Explore the future of agentic AI with the creators of Goose. Learn about vibe coding, AI observability, and maintaining control in an automated world.","key_points":["Main idea: 'Vibe coding' allows rapid prototyping through natural language, but lacks the structural integrity required for production environments","Practical takeaway: Use 'hints' files or system prompts to enforce constraints, such as requiring the AI to ask for direction when uncertainty exceeds a specific threshold","Failure mode: Relying on unverified AI outputs can lead to 'hallucinated' infrastructure or code, as seen in recent high-profile journalistic errors","Practical takeaway: Implement AI observability tools like LangFuse to audit the decision-making process and trace why an agent chose specific implementations","Main idea: Effective AI interaction is a learned skill centered on providing context and structured instructions rather than just simple prompting"],"chapters":[{"start_ms":60000,"title":"Defining Staff Engineering","summary":"A discussion on the responsibilities of staff-level engineers and their role in leveling up teams."},{"start_ms":245000,"title":"The Rise of Vibe Coding","summary":"Exploring the trend of using AI to generate software through high-level intent without deep manual coding."},{"start_ms":600000,"title":"Prompt Engineering and Context","summary":"How to use structured prompts and long-term memory to guide AI agents through complex tasks."},{"start_ms":785000,"title":"Instructional Hints and Rules","summary":"Using configuration files like 'goose hints' or 'cursor rules' to standardize AI behavior."},{"start_ms":965000,"title":"Production Safety and Control","summary":"The importance of maintaining human oversight and testing AI-generated changes before deployment."},{"start_ms":1320000,"title":"AI Observability and Auditing","summary":"The need for logging and tracing AI decision-making processes to support post-mortems and troubleshooting."},{"start_ms":1855000,"title":"The MCP Ecosystem","summary":"How Model Context Protocol (MCP) servers allow agents to dynamically interact with external tools like Google Drive."}],"topics":["AI Agents","DevOps","Vibe Coding","Software Engineering","AI Observability","Prompt Engineering","Model Context Protocol","Automation"],"duration_seconds":2433,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/day-two-devops/episodes/d2do279-herding-the-agentic-geese/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/day-two-devops/d2do279-herding-the-agentic-geese.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}