All Articles
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.
Ask Antigravity CLI Once Whether It Actually Answers, Right Before a Scheduled Run
When Gemini CLI shuts down on June 18 and you move to Antigravity CLI, an expired token or a bad first day can let an unattended job fail silently. Here is a preflight that probes the CLI once, classifies the failure, and decides whether the real job should start at all.
LM Studio Not Starting or Model Won't Load? Fixes for Mac & Windows (2026)
Fix LM Studio startup failures, model loading errors, and unresponsive local API server issues on Mac and Windows with step-by-step solutions and prevention tips.
Fix PyTorch CUDA Errors: torch.cuda.is_available() False & Version Mismatches (2026)
Struggling with PyTorch or CUDA installation errors? This guide covers version mismatches, dependency conflicts, and GPU detection failures with step-by-step solutions.
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.
Making Managed Agent Batches Safe to Re-run: Idempotency and Checkpoints
Running overnight batches on the Antigravity 2.0 Managed Agents API makes recovery from partial failure unavoidable. Starting from a duplicate-post incident, I share the implementation of idempotency keys, a checkpoint store, and resume logic, with real numbers from solo operations.
Feeding axe-core Findings to an Antigravity Agent: An Accessibility Fix Loop in CI
Detect accessibility violations with axe-core, hand them to an Antigravity agent as fixable tasks, and wire detection, triage, fixing, and re-verification into a single CI loop. Includes a diff gate that blocks only new violations and a scoping design that keeps the agent from breaking screen readers.