Implementation Notes: Running AdMob Mediation A/B Tests with Antigravity Parallel Agents
Notes from automating AdMob mediation A/B testing using Antigravity parallel agents across an indie wallpaper-app portfolio with 50M cumulative downloads. Covers joint eCPM + ARPU optimization, the 7-day rotation pipeline, and the rollout design that does not break production.
One Month Splitting Antigravity's Inline Edit and Agent Mode Across Four Wallpaper Apps
A month of notes from running Antigravity's Inline Edit and Agent Mode across four production wallpaper apps — with real counts, the decision rule I wrote into AGENTS.md, a one-pass dSYM fix, and how credit cost factors in.
Cost Attribution for Antigravity Agents — A Showback Architecture That Maps Execution Cost Back to Tenants Across Multi-Product Operations
A multi-tenant Showback architecture for Antigravity agents running across multiple products, with the schema, propagation patterns, and seven months of production numbers from running 4 sites and 6 apps in parallel.
Running iOS Push Notification A/B Tests Weekly With Antigravity Agent — A Self-Improving Loop For Copy, Timing, And Segments
Drawing on 12 years of indie iOS app development across wallpaper and wellness apps with over 50 million cumulative downloads, this article walks through a weekly Push Notification A/B testing loop powered by Antigravity Agent. It covers the FCM bridge, BigQuery measurement, segment design, and a real D7 retention recovery story.
When Japanese Prompts Drag Down Antigravity Quality — A Multilingual Operator's Hybrid Workaround
Switching Antigravity's UI to Japanese is one thing; getting Antigravity to produce quality output from Japanese prompts is another. As an indie developer running multilingual apps and Japanese-language blogs in parallel, I break down measured quality drops with Japanese prompts, a hybrid English-Japanese strategy, a lightweight translation layer, and the reality of running Gemma 4 locally for Japanese.
Why Antigravity's Agent Keeps Referencing the Previous Repo After You Switch Projects — Diagnosis and Fix
When Antigravity carries leftover state from your previous project into a new one, the agent confidently edits files that don't belong to the current repo. Here's how to diagnose and prevent that context bleed.
VS Code 1.121 and the Agent Host Protocol — Reading the Moment When Editor Boundaries Started Moving Outward
VS Code 1.121 introduced Remote agents and the Agent Host Protocol (AHP), expanded the Claude Agent's Auto mode and BYOK options, and made Markdown Mermaid support standard. Read from an Antigravity user's perspective, this release looks like the moment the editor began stepping outside itself.
Catching "Running but Doing Nothing" Antigravity Subagents — A 3-Layer Observability Pattern Across Six Production Apps
Running Antigravity subagents across six production apps surfaced more than ten silent failures every month — exits clean, logs green, but nothing actually happened. Here is the Heartbeat / Output Trace / Decision Log pattern I now use to catch them inside 60 seconds, with code, GCP costs, and four months of running numbers.
Designing Antigravity Agents That Survive Multi-Hour Batches — A 4-Layer Durability Pattern From the Trenches
Long-running Antigravity batch agents will fail somewhere. After running them against the operations of an indie app business, I distilled four durability layers — checkpoint granularity, persistence choice, idempotent restore, and context summarization — into a single, opinionated design memo with working code and real cost numbers.
Six Weeks of Letting an Antigravity Background Agent Watch the Drift Between AdMob and Remote Config
A six-week field report on handing weekly AdMob and Firebase Remote Config diffs to an Antigravity Background Agent, with the drift cases it actually caught and the operational boundaries I ended up drawing.
Apple Search Ads × Antigravity Agent: Autonomous Keyword Bid Tuning Notes from an Indie iOS Studio
How I delegated Apple Search Ads keyword bidding to Antigravity sub-agents for an indie wallpaper app portfolio. JWT auth, ROAS / CPI bid policy, and a Crashlytics-driven safety net.
Which Local-LLM Path to Keep with Antigravity: Ollama, LM Studio, or Raw Gemma 4 (Indie Judgment Notes)
After running three local-LLM paths from Antigravity in parallel, here is what I kept and what I cut, written from a one-Mac-mini indie operation.