An Agent's ORM Code Made p95 Five Times Slower — Measuring Query Counts and Blocking Them in CI
N+1 queries slip past code review because the code looks correct. Here is a CI gate that measures query counts and judges them by their slope against input size, with working code and real numbers.
You Can Measure a Request Before You Send It — Sizing Agent Tasks by Working Backward from Rework Rate
When an Antigravity agent returns code that misses the mark, the cause is rarely the wording of the prompt. It is the size of the task. Here is a Python scorer that grades a request before you send it, plus what happened when I scored 80 past requests against their actual rework outcomes.
Tracing Why an Agent Wrote That Line Six Months Ago — Commit Granularity and Provenance Trailers
When an agent packs 14 files and 800 lines into a single commit, git blame tells you nothing six months later. Here is how I split commits at intent boundaries, recorded provenance as machine-readable Git trailers, and built a one-command path from a blamed line back to the design decision behind it.
When Your Agent's Files Vanish Into .gitignore — A Pre-Commit Detection Gate
When an agent writes files that match .gitignore, the diff review looks perfect but nothing lands in the commit. Here is a gate script that catches ignored build output before you push, plus the tuning it needs.
Deciding When to Stop a Staged Rollout, Before You Have To — Agents Watch, I Halt
Field notes on building a Google Play staged-rollout watcher with Antigravity. Crash rate as a ratio to baseline, delayed ANR evaluation, and an explicit insufficient_data verdict — with the halt action kept in human hands.
Background Refresh May Never Run — Measuring Execution Opportunity and Redesigning Around Freshness
Scheduling a BGTaskScheduler or WorkManager job is a request, not a guarantee. Here is how I instrumented execution opportunity, defined freshness as an SLO with p50 and p90 targets, and rebuilt the update path into three layers that hold up when background work never runs.
Before an Agent's .proto Edit Silently Breaks Binary Compatibility: Gating Wire Compat with buf breaking
When an agent edits your .proto files, the text can look perfect while wire compatibility quietly breaks. Here is how to stop field-number reuse and unsafe type changes with a working gate built from buf breaking and reserved.
Antigravity DevContainer: A Complete Setup Guide for Reproducible AI Development
An end-to-end guide to running Antigravity inside a DevContainer — Docker setup, Ollama integration, secrets, volume persistence, team distribution, and CI parity.
Calling Local LLMs from Antigravity — Ollama and LM Studio Integration in Practice
Treating Antigravity as a cloud-LLM-only tool? Pairing it with Ollama or LM Studio opens up real options for confidential projects and cost-sensitive workloads. Here's the practical configuration and operational knowledge.
Localizing Antigravity 2.0 to Japanese — The Three-Layer Setup for Menus, Commands, and AI Responses
Installing the Japanese Language Pack in Antigravity 2.0 only translates part of the UI. To get a clean Japanese experience — menus, command palette, AI responses — you need to configure three independent layers. Here is the exact setup I run as an indie developer at Dolice, plus which parts I deliberately leave in English.
When Antigravity Reads Cloud-Synced Files as Empty: The Online-Only Placeholder Trap
A file is right there in Finder, yet the Antigravity agent insists it is empty or missing. The culprit is an online-only placeholder created by cloud sync. Here is how to spot it, hydrate the data, and design a workspace that avoids the problem.
Measuring the Rework Rate of What You Delegate to Agents: Drawing Delegation Boundaries with Numbers, Not Instinct
How much should you hand to an agent? I drew that line by instinct for a long time. Here is a practical way to compute a per-category rework rate from your git history and redraw the delegation boundary with numbers, with working code.