Dakota Liu - DEV Community

Dakota Liu

Sep 22

Cap the Tool Response. Never Feed Raw Bytes to the Model.

#ai #python #testing #api

8 min read

Dakota Liu

Sep 21

Cap the Diff. Freeze the Lockfile. Score From a Sidecar the Agent Cannot Touch.

#ai #testing #git #python

8 min read

Dakota Liu

Sep 20

Replay the Patch on a Worktree the Agent Never Mounted

#git #testing #ai #python

7 min read

Dakota Liu

Sep 19

Throw Away the Agent Recap. Merge Only a Hashable Proof Bundle.

#ai #testing #git #python

8 min read

Dakota Liu

Sep 18

Require a Job Receipt. Apply Nothing the Schema Cannot Parse.

#ai #tutorial #python #git

8 min read

Dakota Liu

Sep 17

Name Every File the Agent May Touch. Fail the Job If git Disagrees.

#ai #testing #git #python

7 min read

Dakota Liu

Sep 16

Start From a Red Test. Keep the Model Off Your Shell.

#python #ai #testing #git

7 min read

Dakota Liu

Sep 14

From Zero to a Gated Agent Loop: Six Bootstrap Stages, a Smoke Test, and a Token Ledger

#ai #agents #tutorial #devtools

6 min read

Dakota Liu

Sep 13

Cap the Agent at Eight Turns. Apply Nothing Until git apply --check Passes

#ai #git #python #productivity

8 min read

Dakota Liu

Sep 12

Pack a Redacted Job. Never Upload the Working Tree to a Remote Agent.

#ai #security #agents #python

8 min read

Dakota Liu

Sep 11

Scratch-Box the Agent Loop. Promote the Diff Only When the Hash Matches.

#ai #agents #testing #python

9 min read

Dakota Liu

Sep 9

Pin Agent Tools to a Checked-In Schema Before the First Call

#ai #agents #python #tutorial

8 min read

Dakota Liu

Sep 8

Give the Model One JSON Job. Run Everything Else Yourself.

#ai #testing #python #agents

7 min read

Dakota Liu

Sep 6

Build an Assumption Ledger Before You Trust Agent-Written Config

#ai #agents #tutorial #devops

8 min read

Dakota Liu

Sep 5

Fail Closed on AI-Suggested Installs: A From-Zero Registry Gate

#python #ai #security #devops

9 min read

Dakota Liu

Sep 4

Catch Invented CLI Flags Before Your Agent Touches the Shell

#python #ai #testing #productivity

8 min read

Dakota Liu

Sep 4

Free LLM Access Is a Constraint. Score Your Workload, Then Decide.

#ai #llm #python #productivity

5 min read

Dakota Liu

Sep 4

I Put My Free LLM Quota on a Cron Job: A 60-Line Daily Digest Bot

#python #automation #llm

5 min read

Dakota Liu

Sep 3

Prove Every README Command Before You Let a Model Rewrite It

#python #documentation #tutorial #ai

8 min read

Dakota Liu

Sep 2

Turn Your TODO Comments into an Actionable Debt Report (Free AI, Free Server)

#ai #python #productivity #tutorial

5 min read

Dakota Liu

Sep 1

Automate Release Notes with a Free AI Model (Step-by-Step Guide)

#ai #serverless #github #tutorial

6 min read

Dakota Liu

Aug 31

A $0 AI Summary API: Free Tokens, Free Server, and a Working Walkthrough

#ai #tutorial #opensource #webdev

4 min read

Dakota Liu

Aug 30

I Gave My Git Repo a Free AI Commit-Message Writer (No Credit Card Required)

#ai #git #productivity #tutorial

4 min read

Dakota Liu

Aug 29

AI Wrote the Fix. Who Tests the Fixer? A 50-Line Regression Gate

#ai #testing #opensource #tutorial

4 min read

Dakota Liu

Aug 28

Build an AI Code Reviewer That Fits in a Free Tier (Step-by-Step, Harness First)

#ai #tutorial #python #webdev

5 min read

Dakota Liu

Aug 26

From Empty Directory to Deployed AI Bot: A Free-Infrastructure Walkthrough

#ai #tutorial #webdev #productivity

5 min read

Dakota Liu

Aug 25

Nightly Drift Checks: Catch a Free Model's Behavior Change Before Your Users Do

#llm #python #testing #ai

6 min read

Dakota Liu

Aug 25

Free LLM Tier or Self-Hosted? A 5-Question Framework (and a Probe Script)

#ai #llm #opensource #productivity

5 min read

Dakota Liu

Aug 22

Context Budgeting: Keep Your AI Assistant Sharp Past the First 20 Minutes

#ai #llm #python #productivity

5 min read

Dakota Liu

Aug 21

Stretch a Free LLM Quota With a 40-Line Semantic Cache

#ai #python #llm #opensource

5 min read

Dakota Liu

Aug 17

Launch-Week LLM? Run a Free-Server Probe Before You Switch

#ai #llm #programming #testing

4 min read

Dakota Liu

Aug 14

MiniMax H3 and the Free-Tier Trap: Run a 12-Prompt Gate Before You Switch

#ai #llm #benchmarks #opensource

4 min read

Dakota Liu

Aug 10

Stop Picking LLMs by Vibes: A Reproducible Evaluation Harness You Can Run for Free

#ai #llm #testing #productivity

5 min read

Writing Debut