Codex CLI v0.106.0: installs get simpler, threads get realtime, and guardrails get sharper
Edoardo L'Astorina

Codex CLI v0.106.0: installs get simpler, threads get realtime, and guardrails get sharper

Release notes are often short. Diffs are often huge. This is the missing middle: what actually changed in v0.106.0, in plain terms, and who should care. This post is an experiment: we had our planning agent Themistocles read the tag diff and draft a first-pass summary. We edited it for clarity — but we didn’t do a full manual code review ourselves. If you need ground truth, jump to the diff in Sources. If you spot anything off, tell us —...

Read more

I Fell In Love With Vibe Coding. Then I Tried To Ship It
Edoardo L'Astorina

I Fell In Love With Vibe Coding. Then I Tried To Ship It

The first time I vibe coded, it felt like cheating. In the best way. A proof of concept up in minutes? What? I remember thinking: is this the future? And honestly, that part still applies. For prototypes, demos, and experiments, vibe coding is pure momentum. It compresses hours - sometimes days - into a single burst of “let’s see if this idea even works.” But then I did what everyone does after the magic trick works once: I tried to use the...

Read more

Human-in-the-Loop Agents: when to require review, when to automate, how to log decisions
Hannah Lincoln-Abbott

Human-in-the-Loop Agents: when to require review, when to automate, how to log decisions

Agents are moving from “answer questions” to “do work”: filing tickets, changing settings, running scripts, editing content, deploying changes. That shift is less about model quality and more about agency—the ability to take actions in real systems. The catch is simple: the moment an agent can act, you inherit the failure modes of automation and the ambiguity of language. “Human-in-the-loop” isn’t a conservative stance. It’s how you ship...

Read more

AI for UI Tests: generating Playwright/Cypress tests + fixtures, mocks, and data seeding
Hannah Lincoln-Abbott

AI for UI Tests: generating Playwright/Cypress tests + fixtures, mocks, and data seeding

AI can absolutely help you write UI tests faster. The trap is thinking the “writing” part is the hard part. In practice, most UI test suites fail for the same reasons: brittle selectors, non-deterministic data, leaky environment state, and tests that don’t actually prove the user outcome. AI can speed up all of that too—but only if you use it inside a workflow that’s grounded in real fixtures, intentional mocks, and predictable data seeding....

Read more

Designing Loading in Product UIs: Spinners vs Skeletons vs Optimistic UI (When Each Is Right)
Hannah Lincoln-Abbott

Designing Loading in Product UIs: Spinners vs Skeletons vs Optimistic UI (When Each Is Right)

Loading is a UX surface. People don’t rage at “waiting” as much as they rage at uncertainty. If you want your UI to feel calm, fast, and expensive, pick the loading pattern that answers the user’s real question in that moment: Did it register? Is it working? Am I safe to keep going? The 4-variable decision (use this every time) Duration: instant, short, long Predictability: do we know what will show up (shape) and ro...

Read more