#productivity

10 items tagged #productivity.

BLOG 2026-05-20

The 51% number and what "assisted" hides

GitHub reports that around 51% of code committed in early 2026 was AI-generated or assisted. It is the same kind of number as Airbnb's 60%, and it hides the same things — starting with what the word assisted is doing.

Owner · 6 min #opinion #metrics

GUIDE 2026-05-19

Measuring your own AI-code share honestly

Why 'percent of lines AI wrote' is a vanity metric, what to measure instead, and a lightweight git-based method that counts work which survived contact with review.

Owner · 4 min #productivity #measurement

BLOG 2026-05-19

The 60% claim, deconstructed

Airbnb's CEO said AI writes 60% of the company's new code. The number is real and the conclusion people draw from it is not. This is the gap between the two.

Owner · 6 min #opinion #productivity

CASE STUDY 2026-05-07

Three months of Cursor on a production Rails app: the honest numbers

I tracked task completion times before and after adopting Cursor on a 6-year-old Rails monolith. The results were more nuanced than the marketing suggests.

Owner · 11 min #cursor #rails

GUIDE 2026-05-01

How to write Cursor prompts that actually work

Most Cursor prompts fail not because the model is bad, but because the request is vague. Here's how to give Cursor enough context to stop guessing.

Owner · 7 min #cursor #prompts

BLOG 2026-04-26

Measuring AI coding ROI without fooling yourself

Vendors publish '40% productivity gains'. Internal teams report similar numbers. The reality, when measured carefully, is more modest and more interesting.

Owner · 8 min #measurement #productivity

GUIDE 2026-04-18

Copilot Chat vs inline completions: a workflow split that saves 30 minutes a day

Most Copilot users mix the two surfaces randomly. There's a clear split that produces better output for both, and it's about a five-minute habit shift.

Owner · 6 min #copilot #workflow

BLOG 2026-04-12

The '10x faster with AI' claim, deconstructed

Engineers love to claim AI made them 10x faster. They mean something specific by it, and that specific thing isn't what the claim sounds like.

Owner · 6 min #productivity #claims

BLOG 2026-01-26

The tab completion paradox: simpler features outperform agent loops for daily work

Engineers report Tab autocomplete saves them more time than agent features over a typical day. The marketing emphasizes the wrong thing.

Owner · 4 min #tools #productivity

BLOG 2026-01-24

The hidden cost of bad AI tool defaults

Most engineers use their AI tools at default settings. The defaults are often wrong for the engineer's workflow. The friction adds up.

Owner · 4 min #tools #productivity