Tag: developer-tools
-
Keeping tests running in the background while the agent edits
Cursor's agent mode moves fast enough that a broken test can sit unnoticed for several turns. Running the suite in watch mode alongside it turns a silent failure into an immediate one, and changes how much you trust letting the agent keep going.
-
Leaning on Copilot Edits for multi-file, reviewable diffs instead of raw chat
Copilot Chat is fine for a single function. The moment a change touches more than one file, Copilot Edits produces something reviewable, a proper diff against your working tree, instead of five code blocks you have to reassemble yourself.
-
Cheap wins: the keybindings that turn Cursor back into a proper editor
Cursor's default shortcuts collide with a decade of VS Code muscle memory. Here are the remaps that stop the AI from hijacking keys you already own, and the two bindings worth adding.
-
GitHub Copilot: Underrated power of /explain on legacy code no one dares to touch
A field-tested take on the underrated power of /explain on legacy code no one dares to touch with GitHub Copilot: what it rewards, where it breaks, and how to keep the workflow honest.
-
Cursor: Right amount of automation before it becomes magical thinking
A field-tested take on the right amount of automation before it becomes magical thinking with Cursor: what it rewards, where it breaks, and how to keep the workflow honest.
-
GitHub Copilot: Copilot Spaces as shared context libraries for team onboarding
A field-tested take on Copilot Spaces as shared context libraries for team onboarding with GitHub Copilot: what it rewards, where it breaks, and how to keep the workflow honest.
-
Cursor: Resetting indexes when completions start feeling stale
A field-tested take on resetting indexes when completions start feeling stale with Cursor: what it rewards, where it breaks, and how to keep the workflow honest.
-
GitHub Copilot: Constraining the agent with .github/copilot-instructions.md for reproducible behaviour
A field-tested take on constraining the agent with .github/copilot-instructions.md for reproducible behaviour with GitHub Copilot: what it rewards, where it breaks, and how to keep the workflow honest.
-
Cursor: Pairing tab with explicit intent comments to steer predictions
A field-tested take on pairing tab with explicit intent comments to steer predictions with Cursor: what it rewards, where it breaks, and how to keep the workflow honest.
-
I Ran an AI Agent Overnight on My Mac — Here's What It Built
What happens when you run an autonomous coding agent like Claude Code overnight on a Mac — the setup, safety rails, which tasks actually work, the cost and energy use, and how much of the output gets thrown away.
-
GitHub Copilot: Switching models mid-conversation when reasoning quality starts to degrade
A field-tested take on switching models mid-conversation when reasoning quality starts to degrade with GitHub Copilot: what it rewards, where it breaks, and how to keep the workflow honest.
-
Cursor: Composer runs that land a feature in a single reviewable diff
A field-tested take on composer runs that land a feature in a single reviewable diff with Cursor: what it rewards, where it breaks, and how to keep the workflow honest.
