DEV Community

Emery Lin profile picture

Emery Lin

Backend developer with a growing interest in applied AI. I write hands-on guides for developers.

Location Hangzhou, China Joined Joined on 
Don't Merge the First Green Check: Hooks, Fixtures, and a Flake Budget

Don't Merge the First Green Check: Hooks, Fixtures, and a Flake Budget

Comments
8 min read
Add a Second CI Lane for Agent-Written Pull Requests

Add a Second CI Lane for Agent-Written Pull Requests

Comments
9 min read
Cite the JUnit XML: A Schema-Bound Failure Classifier for CI

Cite the JUnit XML: A Schema-Bound Failure Classifier for CI

Comments
9 min read
Your CI Check Is Boolean. Your Merge Decision Should Not Be.

Your CI Check Is Boolean. Your Merge Decision Should Not Be.

Comments
8 min read
I Read a 10-Million-Token Free Tier Like a Bank Statement

I Read a 10-Million-Token Free Tier Like a Bank Statement

Comments
5 min read
A Small LLM Service That Costs Nothing to Run: A Case Study

A Small LLM Service That Costs Nothing to Run: A Case Study

Comments
5 min read
It Ran Every Morning and Still Broke: Failure Modes of a Free-Tier AI Job

It Ran Every Morning and Still Broke: Failure Modes of a Free-Tier AI Job

Comments
4 min read
Don't Merge on Green: A Fixture Contract, a Pre-Push Hook, and a Merge Packet

Don't Merge on Green: A Fixture Contract, a Pre-Push Hook, and a Merge Packet

Comments
8 min read
Flaky Tests Are Killing Your Merge Confidence: Build a Flake-Aware CI Gate

Flaky Tests Are Killing Your Merge Confidence: Build a Flake-Aware CI Gate

Comments
4 min read
Use MonkeyCode's Free Tokens to Build a PR Summarizer in CI That Doesn't Spam

Use MonkeyCode's Free Tokens to Build a PR Summarizer in CI That Doesn't Spam

Comments
4 min read
Give Every Dependabot PR a Risk Label Before You Click Review

Give Every Dependabot PR a Risk Label Before You Click Review

Comments
6 min read
Classify CI Failures Before You Read the Logs: A Free-Tier Webhook Setup

Classify CI Failures Before You Read the Logs: A Free-Tier Webhook Setup

Comments
4 min read
Zero-Budget Prompt Labs: What Free Models Actually Afford You (and How to Size One)

Zero-Budget Prompt Labs: What Free Models Actually Afford You (and How to Size One)

Comments
5 min read
Your AI Review Bot Double-Posts. A Webhook Replay Test in CI Fixes It.

Your AI Review Bot Double-Posts. A Webhook Replay Test in CI Fixes It.

Comments
5 min read
A Merge Gate for Prompt Changes: Budgeted CI Evals on a Free Server

A Merge Gate for Prompt Changes: Budgeted CI Evals on a Free Server

Comments
5 min read
An AI Review Gate That Doesn't Flake: Hooks, Fixtures, and a Green-to-Merge Path

An AI Review Gate That Doesn't Flake: Hooks, Fixtures, and a Green-to-Merge Path

Comments
6 min read
A Daily Commit Digest on Free LLM Credits: A Case Study in Low-Stakes Automation

A Daily Commit Digest on Free LLM Credits: A Case Study in Low-Stakes Automation

Comments
5 min read
Cheap Model First, Strong Model on Failure: Building an Auditable Two-Tier LLM Pipeline

Cheap Model First, Strong Model on Failure: Building an Auditable Two-Tier LLM Pipeline

Comments
6 min read
The Release-Day Reality Check: A Small Model Evaluation You Can Rerun

The Release-Day Reality Check: A Small Model Evaluation You Can Rerun

5
Comments 1
5 min read
Your AI Coding Agent Has Tools. Here's a Test Suite for the Sandbox You Hope It Respects

Your AI Coding Agent Has Tools. Here's a Test Suite for the Sandbox You Hope It Respects

Comments
5 min read
loading...