Notes
Preparing the latest short-form reflections.
Notes
Short observations, experiments, and ideas on AI, product judgment, discovery, careers, and modern tools.
Note
Jun 8, 2026
3 min readDesigning Loops, Not Just Prompts
By Cristiano Pierry
The next AI productivity leap comes from designing agent loops that can plan, verify, revise, and improve without constant human orchestration.
Note
Jun 8, 2026
1 min readThe Strange Missing Link Between Codex and ChatGPT
By Cristiano Pierry
Codex can reach many external tools, but the inability to search ChatGPT history leaves useful research context stranded.
Note
Jun 5, 2026
2 min readWhen Closing the Laptop Stops the Agent
By Cristiano Pierry
Agentic coding needs persistent workspaces that can pause, resume, and carry context beyond the laptop that started the work.
Note
Jun 5, 2026
1 min readWhen Codex Runs Out of Baby Names
By Cristiano Pierry
Codex naming sub-agents with UUIDs is a funny reminder that AI’s future often arrives messy, operational, and practical.
Note
Jun 3, 2026
2 min readBefore You Hit Connect, Add Context
By Cristiano Pierry
Connection requests earn trust when they include context, intention, and a clear reason the relationship could be mutually valuable.
Note
May 31, 2026
2 min readCodex Shouldn’t Have to Steal Focus to Get Work Done
By Cristiano Pierry
Local AI agents need per-thread visual workspaces so parallel tasks can run without competing for the user’s desktop focus.