asagiman

Founder & CEO of Netsujo. Building trustworthy AI agent systems, with a focus on task boundaries, verification, and production reliability. Creator of Agent Role Contracts (ARC).

Kyoto, Japan Joined on Oct 19, 2026 https://github.com/suirindo/agent-role-contracts

asagiman

Oct 27

A sentinel test for AI coding-agent confinement

#testing #agents

3 min read

Want to connect with asagiman?

Create an account to connect with asagiman. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

asagiman

Oct 27

An AI agent can be approved and still leave you with an unknown result

#ai #agents #testing #opensource

5 min read

asagiman

Oct 26

Before an AI agent acts: scope, execution and evidence answer different questions

#ai

3 min read

asagiman

Oct 26

What should stop an AI coding agent before it acts?

#discuss #ai #security #testing

2 min read

asagiman

Oct 21

Before Your AI Agent Writes a File, Check Its Task Scope

#agents #ai #opensource #security

2 min read

asagiman

Oct 19

How to catch out-of-scope coding-agent tasks before execution

#agents #opensource #javascript #testing

4 min read

DEV Community

asagiman

Badges

1 Week Community Wellness Streak

Writing Debut

Skills/Languages

Currently learning

Currently hacking on

Available for

A sentinel test for AI coding-agent confinement

Want to connect with asagiman?

An AI agent can be approved and still leave you with an unknown result

Before an AI agent acts: scope, execution and evidence answer different questions

What should stop an AI coding agent before it acts?

Before Your AI Agent Writes a File, Check Its Task Scope

How to catch out-of-scope coding-agent tasks before execution