When Your Agent Commits a .bak File: Why Fix-Tool Artifacts End Up in Git
Backup files like .bak and .orig slip into commits after an agent runs a --fix tool. Here are the reproduction conditions, the real root cause, and three fixes: narrowing the staged scope, wrapping the fixer, and adding a pre-commit extension gate.
When the Android CLI Got 3x Faster and Cut Tokens by ~70%, the Right Move Was More Verification Per Change — Not More Parallelism
Reading that the Android CLI agent runs ~3x faster while using ~70% fewer tokens, my first instinct was to ask how many runs to parallelize. But a faster agent doesn't change how much work ships — it changes where the queue forms. This walks through why, sizes the new bottleneck (review and verification gates) with Little's Law, enforces a WIP cap with a working Python admission controller, and reinvests the freed budget into depth per change — with measured results.
Before a Stray Instruction in a Fetched Page Drives Your Unattended Agent — Tainting Inputs to Downgrade Capabilities
So an unattended agent that reads external pages or PDFs can't be hijacked by an instruction hidden inside them: track the taint of every input and automatically downgrade side-effecting tools. With working Python and real operational numbers.
Stop Hard-Coding Your Agent Concurrency: Let It Tune Itself From What It Observes
When you run several Antigravity 2.0 agents in parallel, a single fixed concurrency number is wrong twice: it stalls at 429s during the day and idles capacity at night. Here is an adaptive design borrowed from TCP congestion control — additive increase, multiplicative decrease — that moves your concurrency from observed signals, with working Python and field notes.
Designing Parallel Agent Changes So You Can Trace Them Later
Antigravity 2.0 became a control tower for many agents. Here is how to build an audit trail that lets you trace who changed what and why, designed from real operational failures.
Scheduling an autonomous agent fleet to run 6 sites solo — a timetable that avoids collisions and spam flags
A real example of the autonomous-agent scheduling I built to run 6 sites and an app business in parallel, solo: off-peak distribution, a daily generation cap, and collision avoidance, drawn from the actual timetable and the reasoning behind it.
Choosing the Right Granularity for an Agent's Tools — Bundle or Split?
Should you split an agent's tools finely or bundle them coarsely? A single decision rule, an intentionally asymmetric two-tier design for destructive actions, and real numbers from running six apps.
Why Antigravity Agent Edits Fail With 'patch does not apply' and How to Fix It
Why Antigravity agent edits stall with 'patch does not apply' or 'hunk failed', and how to fix it. Focused on the race where the file changes after the agent reads it, with the settings that stop it from recurring.
Delegate the Undoable, Guard the Irreversible — Tiering Agent Autonomy by Reversibility
When you hand production work to an Antigravity agent, the thing that bites first isn't intelligence — it's whether the operation can be undone. Here is a design that sorts every operation into three reversibility tiers and routes each to auto-execution, checkpointed execution, or a human gate, with TypeScript implementations and real numbers from running six apps in parallel.
Keeping Secrets Out of Your Antigravity Agent's Output: Layered Defenses for Logs, Diffs, and PR Bodies
The three paths through which background agents leak secrets, and how to defend commit diffs, execution logs, and PR bodies with layered protection, drawn from running six apps and measured false-positive rates.
Rolling Back a Half-Finished Agent: Compensating Transactions for Partial Failure
When you let an Antigravity agent run work that spans several external systems, a failure in the middle leaves the world half-rewritten. Retrying doesn't fix that. Here is how to fold it back safely with compensating transactions (the Saga pattern), with TypeScript and real operational numbers.
Flow Control for Autonomous Agents: Backpressure and Queues That Keep Production Alive
Run several Antigravity agents at once and the problem stops being how smart they are and becomes how little your downstream can absorb. Here is a flow-control design — bounded queue, semaphore, token bucket, backpressure, dead-letter — with TypeScript and real numbers.