This blog post explores practical strategies, personal lessons, and real-world experiments in agentic engineering.

The Miners Blog is dedicated to cryptocurrency mining and blockchain technology, offering insights into mining hardware, software, and profitability analysis. Developers and enthusiasts can stay informed about the latest trends and developments in the crypto mining space, learning about mining strategies, hardware configurations, and industry news. Whether it's Bitcoin, Ethereum, or other cryptocurrencies, the Miners Blog provides resources for those interested in mining technologies.

The Miners

A developer shares a practical workflow for reducing frustration with AI coding agents by teaching them to code in a specific style. Rather than correcting the agent repeatedly, the author fed it talk recordings (via Gemini summaries), slide decks, CFP descriptions, and example code repositories to build an architecture.md document reflecting personal coding practices. The process evolved through four stages: attempting video input, gathering multi-source context, providing real code examples, and finally collaborating with the agent to refine and discuss architectural decisions. The key insight is that agents perform better when given concrete examples and documentation upfront, and that frustration usually stems from insufficient instruction rather than agent limitations.

The Agent Isn’t the Problem, You Are My process to remove frustration from agentic engineering

Take 1 – Can the agent learn from a video?

Take 2 – What else can I feed the agent with?