Tatsuya Shimomoto - DEV Community

Tatsuya Shimomoto

Oct 3

Turning Claude Code into a Writing Harness with Claude Mods and an Output Style

#claudecode #contextengineering #plugins #writing

9 min read

Tatsuya Shimomoto

Sep 29

"Is There Any Point to This?" Removing the Jev Plugins I Added to Claude Code After One Week

#jev #claudecode #aiagents #agenticcoding

1

10 min read

Tatsuya Shimomoto

Sep 27

Before Adding a Jev-Type Judgment Model, Read Your Generation Model's Probabilities

#ollama #localllm #gemma #jev

20 min read

Tatsuya Shimomoto

Sep 23

Moving My Research Pipeline's Judgment Calls from an LLM to Jev, a Judgment-Only Model

#jev #pydanticai #aiagents #llm

11 min read

Tatsuya Shimomoto

Sep 22

What Does It Take to Reproduce Jev's Decisions Locally?

#localllm #aiagents #llm #benchmarking

11 min read

Tatsuya Shimomoto

Sep 21

I Added Jev's Skill Router to Claude Code and Turned Back Just Before Rewriting the Skill Listing

#claudecode #aiagents #agenticcoding #llm

10 min read

Tatsuya Shimomoto

Sep 21

How Close to Opus Does Jev, a Model That Writes No Text, Get at Skill Selection in 0.3 Seconds?

#aiagents #llm #localllm #benchmarking

10 min read

Tatsuya Shimomoto

Sep 16

I Made the Top Model My Session Default, and One Heavy Implementation Plus Its Review Burned Through Fable's Usage Limit

#claudecode #aiagents #agenticcoding #anthropic

10 min read

Tatsuya Shimomoto

Sep 12

Why an 11-Second Burst Never Showed Up in the Log That Gets Read Every Week

#claudecode #aiagents #observability #logging

11 min read

Tatsuya Shimomoto

Sep 12

People Inside the Business Don't Call It a 'Domain'

#discuss #ddd #aiagents #career

18 min read

Tatsuya Shimomoto

Sep 5

I Deleted the LLM-Facing Architecture Docs I Had Committed 159 Times in 3 Months: Structure Goes to LSP, Reasons to ADRs, Diagrams to Humans

#claudecode #aiagents #documentation #architecture

11 min read

Tatsuya Shimomoto

Sep 2

I Asked AI to Diagnose My Knowledge Blind Spots — 15 Days of Deadlock Moved in 85 Minutes

#systemsthinking #claudecode #knowledgemanagement #metacognition

7 min read

Tatsuya Shimomoto

Aug 30

My Dead-Code Scan Returned Zero, Then I Deleted 2,063 Lines: Detectors Measure References, Not Consumption

#claudecode #aiagents #staticanalysis #technicaldebt

14 min read

Tatsuya Shimomoto

Aug 28

After Cutting My AI Reviews, I Put a Complexity Ceiling in Ruff

#claudecode #aiagents #staticanalysis #codereview

2

17 min read

Tatsuya Shimomoto

Aug 27

I Cut My AI Review Chain From 6 Stages to 1: Breaking the Loop That Never Hits Zero Findings

#claudecode #aiagents #codereview #agenticcoding

10 min read

Tatsuya Shimomoto

Aug 27

My KPIs Improved. I Deleted My Homegrown LLM Judge Anyway

#claudecode #llm #evaluation #agents

2

13 min read

Tatsuya Shimomoto

Aug 21

Two Drafts Passed Every Eval and Both Were Hollow. Attach the Raw Transcript to the Ledger You Hand Your AI

#claudecode #ai #contextengineering #agents

11 min read

Tatsuya Shimomoto

Aug 20

I Handed 41 Tasks to an AI Loop. The Bottleneck Was Judgment, Not Code

#claudecode #aiagents #automation #agenticcoding

8 min read

Tatsuya Shimomoto

Aug 16

AI Review Kept Creating Work: Why I Deleted 4,541 Lines

#claudecode #aiagents #codereview #agenticcoding

1

12 min read

Tatsuya Shimomoto

Aug 14

Can Six-Month-Old AI Code Survive Today's Review? A 25-Bug Triage

#claudecode #codex #codereview #testing

1

11 min read

Tatsuya Shimomoto

Aug 5

Claude Code's Memory Has No Vectors — Try ADRs Before Memory RAG

#discuss #rag #claudecode #contextengineering

12 min read

Tatsuya Shimomoto

Aug 2

Give Claude Code a Second Harness

#claudecode #anthropic #contextengineering #aiagents

8 min read

Tatsuya Shimomoto

Jul 30

Banned from Wikidata Overnight — I Believed Every Edit Was Compliant, but All 109 Items Were Deleted as Promotion

#wikidata #postmortem #geo #claudecode

13 min read

Tatsuya Shimomoto

Jul 29

What Humans Should Approve Is Intent, Not the Diff — A Decision Table for Agent Approval Gates

#claudecode #aiagents #devops #ai

3

18 min read

Tatsuya Shimomoto

Jul 28

Opus 5 Changed How Rules Should Be Written — Audit Yours

#claudecode #contextengineering #promptengineering #anthropic

1

12 min read

Tatsuya Shimomoto

Jul 27

claude-security Beta: Cost, Output, Accuracy — 189 Agents, 2 Hours, Measured

#claudecode #anthropic #security #ai

1

11 min read

Tatsuya Shimomoto

Jul 20

herdr, a tmux for AI Agents — Until the Editor Disappeared

#claudecode #terminal #productivity #ai

18 min read

Tatsuya Shimomoto

Jul 16

What Do My AI Agent's Logs Look Like in OpenTelemetry?

#opentelemetry #observability #jaeger #llm

15 min read

Tatsuya Shimomoto

Jul 15

Fault Injection TDD Found 3 Silent Failures in My LLM Agent

#testing #llm #pytest #agents

12 min read

Tatsuya Shimomoto

Jul 14

LLM-as-Judge Shouldn't Aggregate Scores: Binary Checks as Evidence, One Holistic Verdict

#llm #promptengineering #evaluation #claudecode

12 min read

Tatsuya Shimomoto

Jul 13

Building an Autonomous Agent on an M1 Mac, by Choice

#discuss #ollama #llm #agents

1

6 min read

Tatsuya Shimomoto

Jul 12

Why Did My Agent Decide That? 3 Observability Patterns

#observability #agents #claudecode #skills

13 min read

Tatsuya Shimomoto

Jul 8

Claude Code from iPhone: Plugging 3 Holes in Remote Control

#claudecode #tmux #mobile #github

14 min read

Tatsuya Shimomoto

Jul 7

Linters Can't Measure a Non-Code Asset's Value — I Built an LLM Stocktake for It

#claudecode #ai #devtools #githubactions

9 min read

Tatsuya Shimomoto

Jul 5

I Built a Skill for Easy Codex Reviews from Claude Code

#codereview #codex #claudecode #skills

7 min read

Tatsuya Shimomoto

May 2

Between the Workflow and ReAct Quadrants: How Phase Decides Skill Design

#discuss #ai #programming

1

10 min read

Tatsuya Shimomoto

Apr 30

Is ReAct Needed in Production? — Separating Design and Operation Phases

#discuss #ai #llm #architecture

10 min read

Tatsuya Shimomoto

Apr 29

(3) The LLM Workflow Quadrant Is Missing from Our Vocabulary

#discuss #ai #llm #architecture

11 min read

Tatsuya Shimomoto

Apr 29

Where ReAct Agents Are Actually Needed in Business

#discuss #ai #programming

14 min read

Tatsuya Shimomoto

Apr 18

Organic Growth and Content Integrity in an AI Writing Team

#discuss #ai #claudecode #writing

1

6 min read

Tatsuya Shimomoto

Apr 16

Building Zed as an Observation Window for Claude Code — Japanese Typography with IBM Plex

#zed #ai #font #typography

10 min read

Tatsuya Shimomoto

Apr 13

AI Agent Black Boxes Have Two Layers — Technical Limits and Business Incentives

#discuss #ai #governance

8 min read

Tatsuya Shimomoto

Apr 12

Can You Trace the Cause After an Incident?

#discuss #ai #programming #devops

9 min read

Tatsuya Shimomoto

Apr 6

A Sign on a Climbable Wall: Why AI Agents Need Accountability, Not Just Guardrails

#ai #agents #governance #security

5 min read

Tatsuya Shimomoto

Apr 5

How Ethics Emerged from Episode Logs — 17 Days of Contemplative Agent Design

#ai #python #ethics #programming

7 min read

Tatsuya Shimomoto

Mar 30

Freedom and Constraints of Autonomous Agents — Self-Modification, Trust Boundaries, and Emergent Gameplay

#ai #security #python #design

6 min read

Tatsuya Shimomoto

Mar 30

Porting Game Dev Memory Management to AI Agent Memory Distillation

#ai #python #memory #gamedev

6 min read

Tatsuya Shimomoto

Mar 24

Where to Put a Coding Agent's Knowledge — and How to Make It Stick

#ai #claudecode #agents #devtools

18 min read

Tatsuya Shimomoto

Mar 22

My Agent's Memory Broke — A Day Wrestling a 9B Model

#ai #python

11 min read

Tatsuya Shimomoto

Mar 21

Not Reasoning, Not Tools — What If the Essence of AI Agents Is Memory?

#discuss #ai #agents

8

7

14 min read

Tatsuya Shimomoto

Mar 19

What Actually Happens When You Write an Article with AI — 20 Dialogues, 2 Hours, a Completely Different Core

#ai #writing #productivity

2

8 min read

Tatsuya Shimomoto

Mar 19

Do Autonomous Agents Really Need an Orchestration Layer?

#discuss #ai #programming

1

9 min read

Tatsuya Shimomoto

Mar 16

Every LLM App Is Just a Markdown-and-Code Sandwich

#ai #python #programming

1

7 min read

Tatsuya Shimomoto

Mar 15

Natural Language as Architecture — Controlling an Autonomous Agent with Prompts, Memory, and Fail-Safe Design

#ai #python #security

2

3

8 min read

Tatsuya Shimomoto

Mar 11

The Install and Hope Problem with MCP Tools

#claudecode #mcp #ai #devtools

1

2

5 min read

Tatsuya Shimomoto

Mar 9

Prompt-Based Alignment Has a Ceiling — 3-Model Prisoner's Dilemma Evidence

#ai #alignment #benchmark

1

10 min read

Tatsuya Shimomoto

Mar 9

click() Betrayed Me 3 Times — Playwright Magento Battle-Tested Patterns

#playwright #python #magento #automation

1

6 min read

Tatsuya Shimomoto

Mar 8

I Built an AI Agent from Scratch Because Frameworks Are the Vulnerability

#ai #python #security

3

16 min read

Tatsuya Shimomoto

Mar 7

I Made a Paper I Don't Understand Run in the Browser — Active Inference Claude Code

#claudecode #numpy #streamlit #python

1

10 min read

Tatsuya Shimomoto

Mar 6

Obsidian's Official CLI Is Here — No More Hacking Your Vault from the Back Door

#obsidian #cli #ai #productivity

5

1

9 min read

2 Week Community Wellness Streak

1 Week Community Wellness Streak

Writing Debut

Want to connect with Tatsuya Shimomoto?