# D2DO279: Herding the Agentic Geese

Page: https://stenobird.com/podcast/day-two-devops/d2do279-herding-the-agentic-geese
Text version: https://stenobird.com/podcast/day-two-devops/d2do279-herding-the-agentic-geese.md
Podcast: [Day Two DevOps](https://stenobird.com/podcast/day-two-devops)
Published: 2025-08-13T15:47:42+00:00
Episode link: https://packetpushers.net/podcasts/day-two-devops/d2do279-herding-the-agentic-geese/
Audio file: https://feeds.packetpushers.net/link/20975/17119116/D2DO279.mp3
Processing state: processed
JSON: https://stenobird.com/v1/public/podcasts/day-two-devops/episodes/d2do279-herding-the-agentic-geese
Duration seconds: 2433

## Resource

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.

## Highlights
- 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

## Topics

AI Agents, DevOps, Vibe Coding, Software Engineering, AI Observability, Prompt Engineering, Model Context Protocol, Automation

## Chapters
- 1:00 — Defining Staff Engineering: A discussion on the responsibilities of staff-level engineers and their role in leveling up teams.
- 4:05 — The Rise of Vibe Coding: Exploring the trend of using AI to generate software through high-level intent without deep manual coding.
- 10:00 — Prompt Engineering and Context: How to use structured prompts and long-term memory to guide AI agents through complex tasks.
- 13:05 — Instructional Hints and Rules: Using configuration files like 'goose hints' or 'cursor rules' to standardize AI behavior.
- 16:05 — Production Safety and Control: The importance of maintaining human oversight and testing AI-generated changes before deployment.
- 22:00 — AI Observability and Auditing: The need for logging and tracing AI decision-making processes to support post-mortems and troubleshooting.
- 30:55 — The MCP Ecosystem: How Model Context Protocol (MCP) servers allow agents to dynamically interact with external tools like Google Drive.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/day-two-devops/episodes/d2do279-herding-the-agentic-geese/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/day-two-devops/d2do279-herding-the-agentic-geese.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.