Regression-Testing Antigravity Agent Output in CI
Agent output drifts between identical runs and turns CI red for no real reason. Here is how I stabilized snapshot regression testing for Antigravity agents using a normalization layer and pytest golden files, drawn from running it in my own indie developer CI.
When Managed Agents Run in the Cloud, How Do You Hand Them Credentials?
The Antigravity 2.0 Managed Agents API runs agents in the cloud, away from your machine. Convenient, but the credential handling that was trivial on your own laptop suddenly gets hard. Here is a design for not handing over long-lived tokens, but issuing them per run and expiring them quickly.
After Gemini 3.5 Flash Became the Default, Route Flash and Pro Per Task
Now that Antigravity's default Flash is Gemini 3.5 Flash, leaving everything on Flash wastes accuracy and forcing everything onto Pro wastes time. Here is a two-axis decision table for splitting work between Flash and Pro, plus the routing setup to wire it into your agents.
Pairing a Local LLM With Antigravity to Keep Sensitive Code Off the Cloud
Should you really let a cloud agent read code that holds your billing keys and revenue logic? For indie developers that worry is concrete. Here I pair Ollama and Gemma as a local LLM with Antigravity, routing sensitive parts to local and general parts to the cloud, with the decision rules and measurements.
Trusting Temporal Workflows in Production — Field Notes on Idempotency, Retry Triage, and Saga Compensation
Practical notes from running Temporal as a production backend: how to make activities idempotent for real, where to draw the line between retryable and fatal errors, how to keep Saga compensation from firing twice, and how to make it all observable—built with Antigravity in the loop.
Making My Managed Agents Batch Survive a Crash Without Redoing Everything
Running a 200-item batch on the Managed Agents API kept torching tokens, because every mid-run failure restarted from item one. Here is the checkpoint-and-idempotency design I added so the batch resumes from where it died.
Routing thinking_level by Task in Gemini 3.5 Flash — Re-measuring My Token Spend
After Gemini 3.5 Flash became Antigravity's default, my thinking tokens crept up quietly. Here's how I measured thinking_level per task type and landed on a setup that cuts spend without losing accuracy.
Keep Side Questions Out of Your Main Thread with Antigravity's /btw
How Antigravity 2.1.4's /btw slash command routes side questions to a disposable subagent so your main agent's context stays clean through long tasks.
When the Edge Cache Pinned Next.js Error Pages: A cache-worker Guard Design
Users reported intermittent 'failed to load' errors I could never reproduce. The cause: SSR exceptions shipped as HTTP 200 and pinned by the edge cache. Here is how I narrowed it down with an Antigravity agent and added a cache-worker guard to stop it.
Before You Trust 'It's Fixed' — Make the Agent Confirm Your Live URL Actually Renders
The agent reported it had fixed the bug and deployed successfully, yet the production page was blank. To prevent the empty-body-with-200 trap, here is how to add a completion gate that makes Antigravity 2.0's Browser Sub-Agent open the live URL and confirm the main content selector is actually filled.
Budgeting Quota So Parallel Agents in Antigravity 2.0 Don't Run Dry
Run several agents at once in Antigravity 2.0 and your quota can be gone by mid-afternoon, right when you need it for the real work. Here is how I measure per-agent consumption, find the Pro-vs-Ultra break-even, and budget so I never hit the ceiling.
A Week of Coding Hands-Free with Antigravity 2.0's Live Voice Transcription
Antigravity 2.0 added Gemini Audio-based live transcription right inside the editor. After a week of using it in real work, here's an honest take on how it differs from external dictation tools, how it handles technical terms, and where it actually earns its place.