Does Splitting Work Across AI Tools Really Save Money? Put the Monthly Gap and the Switching Cost in One Table
Is it cheaper to use different AI tools for different tasks? A small Python script that puts per-task cost and switching effort side by side so you can find the break-even point.
Before Turning Undocumented Code Into a Spec, Decide the Reading Order by Fan-In
When you ask an agent to turn undocumented code into a spec, which files do you hand over first? A 36-line Python script ranks files by import count (fan-in) plus route entry points, with measurements from a 77-file Next.js project.
A report of a cache cleanup that wiped a drive: why I now route every delete through a checkpoint
After reading about a cache cleanup request that ended with a developer's drive contents gone, I reopened my own cleanup script. Here is a small Python checkpoint that narrows how far a delete can reach, plus where I draw the line on what to hand to an agent without approval.
A Small Guard Script That Catches an Unattended Agent Rewriting Its Own Settings
After reading a report of an agent widening its own read-only limits by editing settings.json, I wrapped my overnight headless runs in an outside guard. Before/after fingerprints, quarantine and restore, and a hard timeout, with working code.
antigravity-preview-05-2026 shuts down October 5: which setups need more than a string swap
The shutdown date for antigravity-preview-05-2026 is set for October 5, and the official page gives you the date and the successor name, nothing more. If you only read output_text, swapping the string is the whole migration. If you read steps, it is not.
I Asked for the Whole Quote PDF Tool at Once, Then Split It Into Four Requests
How I moved my client quote paperwork from copy-and-edit to a small PDF tool built with Antigravity, why the first single-shot request had to be thrown away, and the four smaller requests that replaced it, with working code.
Fixing uv add Errors with Python ML Packages
Practical fixes for uv add failing with transformers, torch, numpy, and other ML packages — covering Python version mismatches, dependency conflicts, CUDA/CPU torch selection, and build errors.
Keeping the Antigravity Python API Stable in Production — Retries, Timeouts, and Circuit Breakers That Actually Work
A deeply practical guide to keeping Python services built on the Google Gen AI SDK alive under real traffic. We cover retry, timeout, circuit breaker, rate limit, and cost budgeting patterns with runnable code from an Antigravity workflow.
Three Safeguards Every Antigravity Python API Deployment Needs Before Production
Retries, timeouts, and circuit breakers — the three production safeguards you need around your Antigravity Python API calls, with working code for each.
When A2A Tasks Sat Stuck in 'working' — Field Notes on Tracing State Transitions to Detect Stalls
Antigravity's A2A coordination fails less by crashing and more by sitting in 'working' without progress. This walks through recording state transitions as one timeline and naming a stalled task down to which agent and which edge froze, along with what running agents daily has taught me.
Semantic Search Over Your Own Codebase with Gemini Embeddings and sqlite-vec: An Incremental Index Keyed on Git Blob Hashes
A build log for semantic search scoped to your own repository, using Gemini embeddings and sqlite-vec. Covers an incremental pipeline that skips re-embedding unchanged files via git blob hashes, with measured index size and query latency.
Combining All Four Antigravity Surfaces in One Project — Up to Running Your Own SDK Agent
How to split a single project across Antigravity 2.0, CLI, IDE, and SDK, and how to bridge between them — from diverging on design to converging on production, all the way to running a small custom agent with the Python SDK, with implementation included.