All Articles
How Far Can On-Device Inference Stay Free? Measuring the Line Between Foundation Models and Gemini
WWDC 2026 widened Apple Foundation Models' free tier, making on-device inference easier to reach for. But 'free, so everything on-device' hits cases where quality falls short. Here is how to decide the range you hold on-device and the range you pass to cloud Gemini by measurement, not guesswork.
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.
Turning 'the Antigravity CLI feels faster' into a number with hyperfine
The Go-based Antigravity CLI feels snappier to start. Here is how to turn that impression into a reproducible number with hyperfine: warm vs cold runs, cumulative cost in automation, and a CI gate that catches regressions.
A Compatibility Shim That Bridges Old Scripts to agy Before Gemini CLI Shuts Down
Ahead of the June 18 Gemini CLI shutdown, instead of rewriting every gemini call scattered across cron and CI at once, a thin compatibility shim can bridge them to the Antigravity CLI (agy). Here is the approach with working shell scripts.
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.
After Migrating to Antigravity CLI: Deciding How Much to Delegate to Scheduled Runs
When the June 18 Gemini CLI sunset pushes you onto Antigravity CLI, you gain background scheduled runs. Convenient, but delegate everything and you won't notice when it breaks. Here is how I separate what to schedule from what to keep manual, with the actual routing rules.
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.