About
A short introduction and what I am currently interested in.
I am a software engineer based in Tokyo. I studied physics at graduate school and started my career in systems integration, then moved into iOS engineering — which is where most of the last decade has gone.
From iOS I widened into Flutter, backend work in Kotlin and Ktor, and frontend work in React and GraphQL. That was never a deliberate plan to collect platforms. It is simply what happens when you keep filling in whatever the product is missing.
These days my attention is on cloud infrastructure and AI agents, and specifically on identity: when an agent calls an external API on a user’s behalf, how do you express whose authority it is acting under? I tend to answer that by building the mechanism out myself and then talking about what I found.
Whatever I investigate usually ends up as an article or a slide deck. Without actually running the code it is far too easy to mistake familiarity for understanding, so I try to keep the order fixed: write the sample first, explain it second.
Focus areas
- AI agent identity — When an agent calls an external API on a user’s behalf, whose authority is it acting under? I work through this by actually wiring up three-legged OAuth and token exchange.
- AI agent platforms — Mostly Amazon Bedrock AgentCore: what it takes to run agents in production. Tenant isolation and MCP server topology are the parts I keep coming back to.
- Cloud architecture — AWS first, with Azure, Google Cloud, and Kubernetes alongside it. The interesting question is never whether a new service works, but whether it holds up in operation.
- Mobile apps — Starting from iOS and extending into Flutter and Android. This is the area I have spent the longest on: app architecture, and where to draw the line against the backend.