Three Boundaries I Draw Before Handing Work to an Antigravity 2.0 Agent
What to hand a background agent, and what to keep in your own hands. The three boundaries I actually drew while running solo-dev automation in parallel, and how to encode them so the lines hold.
Spending Less on Failure Without Swallowing It: A Retry Budget for Agents Built Around Gemini 3.5 Flash
A design that separates an agent's retries from quietly swallowing errors: classify the failure first, then retry within a budget. Grounded in the speed and price of Gemini 3.5 Flash, with per-task caps, logging, and a weekly tightening routine.
Stopping Parallel Agents from Clobbering the Same File
When you run several agents at once in Antigravity 2.0, two of them can write to the same file and one set of changes silently disappears. Here is how to design write arbitration inside a shared workspace.
After Generating Several Candidates, Which One Do You Adopt? Designing Best-of-N That Arbitrates by Verification
With Gemini 3.5 Flash's speed, generating several implementations of the same task has become practical. The hard part is no longer generation but arbitration. Here is the design and TypeScript implementation of a Best-of-N arbiter that picks the winner using verifiable signals only — not majority vote, not self-reported confidence.
Stop Dialogs From Stacking: One Gate for Paywalls, Review Prompts, and Rewarded Ads
A field record of curing the bug where a paywall, a review prompt, and a rewarded ad all surface at once, fixed with a single priority-based modal gate. I let an Antigravity agent sweep up the scattered show() calls, but kept the display policy in my own hands.
Accounting for Which Agent Spent What: A Cost Attribution Design by Task
Your month-end bill is one number, but running multiple agents on Gemini 3.5 Flash hides which task ate the cost. Separate from a budget guard, I share a cost-attribution accounting design that maps usage to per-task and per-site cost, with a solo-operator implementation and numbers.
Your Antigravity LLM App Drifts on Cost and Quality While the Dashboard Stays Green — Instrumentation Field Notes
Watching only total cost and latency hides the slow drifts that hurt. These are field notes on attributing telemetry by feature, tenant, and prompt version so you catch quality regressions and cost spikes early.
Tracing Parallel Agents After the Fact: Observability with Structured Logs and Spans
Running multiple agents in parallel on the Antigravity 2.0 desktop makes it impossible to tell which one is doing what. I share an observability design that drops tangled print debugging for run_ids and spans you can trace afterward, with a solo-operator implementation and numbers.
When the Antigravity CLI Stalls on a 401 During Unattended Runs
If your scheduled Antigravity CLI job suddenly stops producing output after a single 401 in the logs, here is how to separate an expired token from a silent re-login prompt and rebuild your unattended setup.
Antigravity vs Gemini Code Assist (2026): Which Google AI Coding Tool to Use?
Antigravity and Gemini Code Assist are both Google AI tools for developers, but they serve very different purposes. This guide breaks down the differences by features, cost, and use cases to help you choose — or use both together.
Three Prompts I Tried When Antigravity's Code Felt Correct But Not Mine
When Antigravity's output runs but never quite fits your codebase, the gap is usually missing design context. Three prompting patterns for handing over intent — plus the cases where even that wasn't enough, from real indie development.
Antigravity vs OpenAI Codex: Which AI Coding Agent to Choose in 2026
Antigravity or OpenAI Codex? A hands-on 2026 comparison of architecture, features, pricing, and the clear cases where each wins — plus when it pays to use both.