Creează un cont pentru a te abona la acest blog și a-i urmări articolele pe pagina Lectură.
-
I avoided running agents with real access for a year.
-
Building multi-channel AI agents means dealing with APIs that silently fail.
-
Set up automated Kamal deployments with 1Password secrets management.
-
Two quick fixes for cryptic APT hash mismatches and missing moby packages when building devcontainers on Debian Trixie.
-
Give your coding agent a browser and a markdown script.
-
Step-by-step guide to rendering OpenAI ChatKit MCP tool results as rich UI widgets in a Ruby on Rails app using server-side hydration and SSE streaming.
-
The difference between good and bad AI coding sessions isn't the model.
-
AI-native apps aren't about having AI features.
-
The MCP spec expects oauth at connect time, before you know what tools you need.
-
What I learned from 12 months of coding with AI agents—and why I built isolated dev environments to make them actually useful.
-
A deep dive into implementing preview environments for pull requests using Kamal deployment, PostgreSQL schema isolation, and GitHub Actions automation.
-
A deep dive into implementing Model Context Protocol (MCP) servers in a Rails application, covering remote HTTP, native Ruby, and Docker subprocess approaches.
-
This week's learning log covers HumanLayer's 12-Factor Agent patterns, layered prompt injection defenses, and the architecture behind production-ready voice interfaces.
-
A story about how I figured out my running shoes with the help of AI after struggling with knee pain and bad advice.
-
I used to write to learn, to reflect.