Skip to content
Notes

Notes from May 2026

13 notes

Codex Shouldn’t Have to Steal Focus to Get Work Done
Note

May 31, 2026

2 min read

Codex 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.

From Chat History to Execution History
Note

May 29, 2026

1 min read

From Chat History to Execution History

By Cristiano Pierry

Prompt history is becoming the execution record for delegated AI work, capturing intent, decisions, and what agents actually did.

AI Won’t Fix Bad Logic
Note

May 28, 2026

1 min read

AI Won’t Fix Bad Logic

By Cristiano Pierry

AI can generate campaigns and code, but weak product logic still needs humans to teach systems when not to act.

You Are Not Behind
Note

May 25, 2026

1 min read

You Are Not Behind

By Cristiano Pierry

AI’s pace calls for curiosity and steady judgment, not the anxiety of trying to catch every update.

When AI Agents Start Granting Themselves Permission
Note

May 24, 2026

2 min read

When AI Agents Start Granting Themselves Permission

By Cristiano Pierry

A real-world Codex permission prompt bug shows why agentic systems need approval flows that agents cannot complete for themselves.

Working Better with LLMs: 10 Habits for Teams That Build
Note

May 21, 2026

2 min read

Working Better with LLMs: 10 Habits for Teams That Build

By Cristiano Pierry

Ten practical habits for teams using LLMs as working partners to plan, build, review, test, and improve with better judgment.

From Source Code to User Intent: The Next Software Audit Trail
Note

May 20, 2026

3 min read

From Source Code to User Intent: The Next Software Audit Trail

By Cristiano Pierry

As AI coding agents generate more software, prompt history may become a critical audit trail for understanding user intent.

Codex, Product Taste, and the Problem of Too Much UI
Note

May 14, 2026

2 min read

Codex, Product Taste, and the Problem of Too Much UI

By Cristiano Pierry

AI coding tools can make interfaces function, but polished products still depend on taste, hierarchy, and restraint.

Confession from the AI-assisted builder trenches
Note

May 14, 2026

2 min read

Confession from the AI-assisted builder trenches

By Cristiano Pierry

Fast AI prototypes raise the bar for builder taste, product judgment, and knowing whether the result deserves users’ attention.

Don’t Build Your Operating System on a Quota
Note

May 14, 2026

1 min read

Don’t Build Your Operating System on a Quota

By Cristiano Pierry

Reliable AI workflows need an operating layer that does not collapse the moment a quota interrupts daily work.

When Intelligence Becomes Abundant
Note

May 13, 2026

1 min read

When Intelligence Becomes Abundant

By Cristiano Pierry

Near-unlimited access to frontier models changes the way we work when intelligence starts to feel abundant instead of rationed.

When Discovery Moves From Search to Agents
Note

May 9, 2026

2 min read

When Discovery Moves From Search to Agents

By Cristiano Pierry

As agents begin to explore, compare, and filter on our behalf, content discovery shifts away from manual search and toward agent-mediated experiences.

AI Expands Our Range. Expertise Gives Us Depth.
Note

May 7, 2026

2 min read

AI Expands Our Range. Expertise Gives Us Depth.

By Cristiano Pierry

AI gives product teams broader reach across disciplines, but the real leverage comes from pairing that range with deep craft and judgment.