When Nobody Reads Your AI Code Reviewer Anymore — Field Notes on Measuring Actioned-Rate
Our production AI code-review agent quietly went hollow over six months. When the team started silently resolving every comment, we instrumented actioned-rate and false-positive rate to bring it back. These are the field notes.
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.
Letting a Background Agent Work Overnight Without Regretting It by Morning — Guardrails for Unattended Runs
When you hand overnight refactoring to Antigravity's Background Agent, the morning brings as much anxiety as convenience. From three angles — blast radius, completion criteria, and detecting silent regressions — here are the guardrails that let me run unattended jobs with confidence.
When Your Antigravity Agent Eval Gate Keeps Flickering — Build Notes on Pass/Fail That Survives Non-Determinism
Same code, yet the eval passes in the morning and fails by noon. The first thing that breaks when you put agent evaluation into CI on Antigravity is the stability of the verdict. Here's how I separate noise from real regression and lock down pass/fail in code.
When an AI Agent's git push Reports Success but Nothing Reaches the Remote
Why agent-automated git pushes fail silently (a missing identity plus a no-op push), with three fixes: explicit config, SHA verification, and the GitHub REST API.
When Antigravity's AI rewrites your package.json dependencies and breaks the build
You asked Antigravity for a small visual change, and somehow twenty-three dependency lines in package.json got rewritten — carets stripped, pins bumped to latest, the build dead on arrival. Here is what triggers it, how to roll back cleanly, and three guardrails to keep it from recurring.
When Antigravity's AI Imports a Package That Doesn't Exist
Antigravity's AI sometimes writes imports for packages that exist nowhere on npm. Here's how to spot phantom imports in five minutes, why the model invents them, and the AGENTS.md rules I use to keep my repo clean.
Building a Stripe Dunning Recovery Pipeline with Antigravity AI Agents — Stop Failed Payments from Becoming Churn
Wire Antigravity AI agents into Stripe Smart Retries to recover failed payments before they turn into churn. Webhooks, idempotency, AI-tailored email copy, Slack escalation, and winback offers — all in one production-ready pattern.
Building a Coding Agent System with Gemma 4 × Antigravity — A Complete Implementation Guide for Code Review, Test Generation, and Refactoring
A hands-on guide to building a 3-agent collaborative system using Gemma 4 and Antigravity AgentKit 2.0, covering code review, automated test generation, and refactoring suggestions. Includes production-quality code and pitfall solutions.
Antigravity × Durable Execution: Designing Fault-Tolerant Long-Running AI Tasks
An implementation guide for putting Antigravity agents to work on long-running jobs using Durable Execution — covering checkpointing, idempotency, and automatic retries, plus three real incidents from a 50M-download indie app and seven production pitfalls the official docs never spell out.
Turn Draw.io Diagrams into AI Prompts — Visual Agent Design with Antigravity
Learn how to use Draw.io flowcharts and sequence diagrams as executable AI agent prompts. This guide covers XML metadata techniques for visual prompt design.
Antigravity Prompt Engineering Guide — Crafting Instructions That Maximize AI Agent Accuracy
Master prompt engineering techniques for Antigravity's AI agents. Learn how to write structured instructions that dramatically improve code generation, refactoring, and debugging accuracy.