When the Agent Hands You 1,400 Replacements in One Commit, Ask for Batches Instead
Ask Antigravity to run a large codemod and you can get back one unreviewable commit. Here is a small design — ast-grep rules plus a verified batch driver — that splits a mechanical replacement into the machine's job and the human's check, with working code.
Recovering Missing iOS dSYMs Across Six Apps with Antigravity's Background Agent — A Four-Week Operations Log
After migrating Firebase iOS SDK from CocoaPods to SPM, six wallpaper apps saw their Crashlytics symbolication rate collapse to as low as 4.2%. This is a four-week operations log of letting Antigravity's Background Agent track, upload, and verify 1,847 missing dSYMs across six repositories — including App Store Connect dSYM polling and AdMob revenue reconciliation.
Three Weeks of Running Antigravity Browser Agent and Claude in Chrome Side by Side
Notes from three weeks of running Antigravity's Browser Agent and Claude in Chrome in parallel while tuning AdMob and pre-release checks for my wallpaper apps.
Integrating Antigravity Agents into My Android Release Workflow — 3 Months of Honest Findings
Three months of running Antigravity Agents inside my Android release flow: where crash diagnosis landed, where it missed, how I turned staged-rollout Go/No-Go into a threshold dialog, and the context checklist that decides diagnostic accuracy.
I Let Antigravity Take Over My 10-Year-Old Wallpaper App — What Happened Next Surprised Me
A real case study of handing a wallpaper app's Swift codebase — built since 2014 — to Antigravity's Background Agent. What it got right, what it missed, and what that taught me about AI-assisted refactoring.