uehara

404 bio not found

Joined on May 30, 2018

uehara

Sep 5

Hand one person's good way to the whole team — team development in a new era

#ai #claudecode #plugin #codequality

8 min read

Want to connect with uehara?

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

Create Account

Already have an account? Sign in

uehara

Sep 3

Run your AI subscription 24 hours a day — use the quota you already pay for

#ai #claudecode #llm #startup

9 min read

uehara

Sep 1

Running the whole company on AI: the big picture

#ai #claudecode #productivity #startup

9 min read

uehara

Aug 30

Bringing shared foundations into one place — merging five shared repositories into one

#monorepo #typescript #npm #architecture

7 min read

uehara

Aug 27

Four Failures I Kept Repeating on AWS Amplify — Full env Replacement, Green Build but 500 at Runtime, Silent Outages, Domain Migration

#aws #amplify #cicd #devops

7 min read

uehara

Aug 26

When anyone can build with a prompt, what counts as productivity? — We're moving our whole company to AI and keeping humans on judgment

#ai #productivity #management #career

5 min read

uehara

Aug 25

The 18 products EarthLink Network builds in-house

#ai #saas #productivity #startup

8 min read

uehara

Aug 24

An AI's “Done” Can't Be Trusted — Quality Gates That Stop False Completion With Evidence

#ai #claudecode #testing #codequality

6 min read

uehara

Aug 20

I cut small AWS charges by picturing them at 100x scale

#aws #cost #dynamodb #amplify

8 min read

uehara

Aug 19

I looked at the GitHub Actions bill and built a CI + security base at home

#ci #githubactions #selfhosted #devops

9 min read

uehara

Aug 17

When a Provider Retires Your LLM Model: Two Products, the Root Cause, and Preventing Recurrence

#ai #llm #machinelearning #reliability

6 min read

uehara

Aug 15

Cloud bills kept climbing from 24/7 AI development — I moved the decisions and the implementation to my own local LLMs and cut the cost

#ai #llm #localllm #costoptimization

10 min read

uehara

Aug 10

Moving Half of Our AI Development to Local LLMs — by Splitting Work by Role, Not by Picking the Biggest Model

#ai #llm #machinelearning #localllm

3 min read

DEV Community

uehara

1 Week Community Wellness Streak

Writing Debut

Eight Year Club

Seven Year Club

Six Year Club

Five Year Club

Four Year Club

Three Year Club

Two Year Club

One Year Club

Organizations

EarthLink Network

Hand one person's good way to the whole team — team development in a new era

Want to connect with uehara?

Run your AI subscription 24 hours a day — use the quota you already pay for

Running the whole company on AI: the big picture

Bringing shared foundations into one place — merging five shared repositories into one

Four Failures I Kept Repeating on AWS Amplify — Full env Replacement, Green Build but 500 at Runtime, Silent Outages, Domain Migration

When anyone can build with a prompt, what counts as productivity? — We're moving our whole company to AI and keeping humans on judgment

The 18 products EarthLink Network builds in-house

An AI's “Done” Can't Be Trusted — Quality Gates That Stop False Completion With Evidence

I cut small AWS charges by picturing them at 100x scale

I looked at the GitHub Actions bill and built a CI + security base at home

When a Provider Retires Your LLM Model: Two Products, the Root Cause, and Preventing Recurrence

Cloud bills kept climbing from 24/7 AI development — I moved the decisions and the implementation to my own local LLMs and cut the cost

Moving Half of Our AI Development to Local LLMs — by Splitting Work by Role, Not by Picking the Biggest Model