Writing on iOS, agents, and dev tooling.https://aspesi.dev/https://aspesi.dev/writing/teaching-claude-code-to-review-its-own-prs/https://aspesi.dev/writing/teaching-claude-code-to-review-its-own-prs/A judge agent, two independent reviewers, and a rule file per repo. What a self-review pipeline catches, what it confidently invents, and the prompt changes that closed the gap.Sun, 28 Jun 2026 00:00:00 GMThttps://aspesi.dev/writing/a-worktree-per-agent-workflow/https://aspesi.dev/writing/a-worktree-per-agent-workflow/Give every agent its own git worktree and most coordination problems dissolve. Setup scripts, port allocation, and the cleanup step everyone forgets.Fri, 12 Jun 2026 00:00:00 GMThttps://aspesi.dev/writing/langgraph-checkpoints-as-a-debugging-superpower/https://aspesi.dev/writing/langgraph-checkpoints-as-a-debugging-superpower/Checkpoints aren't just resumability — they're a time machine. Replaying a misbehaving agent from any node, diffing state between runs, and the checkpointer I ended up writing.Sat, 30 May 2026 00:00:00 GMThttps://aspesi.dev/writing/swiftui-observation-framework-one-year-in/https://aspesi.dev/writing/swiftui-observation-framework-one-year-in/What @Observable fixed, the re-render traps that survived the migration, and the measurement setup I use before trusting any performance claim.Thu, 14 May 2026 00:00:00 GMThttps://aspesi.dev/writing/the-case-for-boring-test-infrastructure/https://aspesi.dev/writing/the-case-for-boring-test-infrastructure/Clever test frameworks rot faster than the code they test. Why I keep choosing flat fixtures, real assertions, and one slow end-to-end suite over anything exciting.Wed, 29 Apr 2026 00:00:00 GMThttps://aspesi.dev/writing/writing-an-mcp-server-a-model-will-use-correctly/https://aspesi.dev/writing/writing-an-mcp-server-a-model-will-use-correctly/Tool descriptions are prompts, and most MCP servers write them like API reference docs. Naming, argument shape, and error strings that steer a model back on task instead of into a retry loop.Thu, 02 Apr 2026 00:00:00 GMThttps://aspesi.dev/writing/evals-for-agents-that-edit-code/https://aspesi.dev/writing/evals-for-agents-that-edit-code/Diffing against a golden patch is the wrong metric — a real edit has many correct shapes. The rubric I settled on, why I run every suite twice, and how much variance to tolerate before calling it a regression.Wed, 18 Mar 2026 00:00:00 GMThttps://aspesi.dev/writing/the-actor-boundary-is-a-design-decision/https://aspesi.dev/writing/the-actor-boundary-is-a-design-decision/Strict concurrency doesn't just want annotations — it wants you to decide what your app's isolation model actually is. Three refactors where the red diagnostics were right and my architecture was wrong.Sat, 21 Feb 2026 00:00:00 GMThttps://aspesi.dev/writing/satisfies-and-the-shape-of-your-config/https://aspesi.dev/writing/satisfies-and-the-shape-of-your-config/A type assertion is the point where TypeScript stops helping you. How `satisfies` plus a couple of narrow generics let a config object check itself — and the two places I still cast and say so in a comment.Tue, 27 Jan 2026 00:00:00 GMThttps://aspesi.dev/writing/snapshot-tests-i-dont-regret/https://aspesi.dev/writing/snapshot-tests-i-dont-regret/Most SwiftUI snapshot suites become a wall of noise nobody reads. Pinning the device matrix, testing states instead of screens, and deleting every test that only ever failed on a system font update.Tue, 09 Dec 2025 00:00:00 GMThttps://aspesi.dev/writing/git-rerere/https://aspesi.dev/writing/git-rerere/One config flag turns a long-lived branch from a rebase tax into a non-event. What rerere records, the one case where its memory betrays you, and how it changed how long I let a branch live.Tue, 11 Nov 2025 00:00:00 GMThttps://aspesi.dev/writing/structured-output-beat-every-prompt-trick/https://aspesi.dev/writing/structured-output-beat-every-prompt-trick/Months of prompt tuning to stabilize one agent's output, undone in an afternoon by a Zod schema. Where schema-constrained generation is a free win, and where it quietly costs you reasoning quality.Mon, 06 Oct 2025 00:00:00 GMThttps://aspesi.dev/writing/claude-md-is-a-product-surface/https://aspesi.dev/writing/claude-md-is-a-product-surface/Written like documentation, an agent instruction file gets long and ignored. Written like an API — few rules, each testable, each naming the failure it prevents — it starts doing work.Tue, 19 Aug 2025 00:00:00 GMThttps://aspesi.dev/writing/shipping-a-swiftui-app-with-no-view-model-layer/https://aspesi.dev/writing/shipping-a-swiftui-app-with-no-view-model-layer/I cut MVVM out of a real app to find out what would break. Mostly nothing — but the two places it genuinely hurt are worth knowing before you copy the experiment.Tue, 24 Jun 2025 00:00:00 GMT