~/aspesi.dev

Kevin Aspesi builds iOS apps, TypeScript agents, and the harnesses that keep them honest.

Software engineer shipping Swift/SwiftUI apps, LangGraph agents, and agentic-dev tooling around Claude Code — worktree-per-agent workflows, self-reviewing PRs, boring test infrastructure. I write up what actually worked, with the failure modes left in.

Recent writing

all posts →

  1. 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.

    #agents#claude-code 11 min

  3. 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.

    #langgraph#typescript 9 min

  5. 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.

    #testing#opinion 7 min

Projects

all projects →
~/projects/on-the-grid

On The Grid

iOS app for discovering and saving places worth going — import a spot from Instagram or TikTok in one tap, then meet people nearby who saved the same places.

ios · swift
~/projects/otto

Otto

A LangGraph.js conversational agent for a car-buying service — it walks a shopper from first message to a qualified sales lead, with live dealer pricing and a CRM handoff.

typescript · langgraph · openai

Now

kevin@dev $ git worktree list ~/projects/on-the-grid main — venue app, iOS + import pipeline~/contrib/paseo pr #2104 — pin workspaces to the top~/config/claude main — review harness: 2 agents + a judge