slowlp
BLOG

A working
notebook

Experience, know-how, and thoughts from solo dev with AI.

TAGS
78 posts
Story 2026.07.19 NEW

I almost gave up, then reopened myWiki from the requirements with Grok

Facing the mountain left by unmanned work, I chose repair over rebuild

Series 10 min
#indie-dev#ai-collaboration#personal-wiki
Lesson 2026.07.19 NEW

I asked to fix the title and the body vanished

Why a wiki you cannot hand-edit needs rewrite validation and undo

Series 9 min
#personal-wiki#ai-collaboration#agent-design
Story 2026.07.19 NEW

I tried to run it like second and cost broke me

Why I dropped full-analysis summarize, and merge only asks title and summary before stitching bodies

Series 10 min
#personal-wiki#ai-collaboration#indie-dev
Story 2026.07.19 NEW

The body was sitting in the database

Why I ran one unmanned full loop, then dropped Postgres body columns for a two-layer md layout

Series 8 min
#personal-wiki#indie-dev#documentation
Lesson 2026.07.19 NEW

Index and keywords came out worse than I expected

Splitting vertical classification from cross filters, then capping counts all the way into merge

Series 12 min
#personal-wiki#documentation#ai-collaboration
Lesson 2026.07.19 NEW

Chat felt slow because of wait time, not unit cost

We cut full document-map injection and set 4k/10k caps, but short answers, search, and synthesis are still unfinished

Series 9 min
#personal-wiki#ai-collaboration#context-management
Lesson 2026.07.12

I only saw the mountain of fixes after shipping unmanned

myWiki finished via dispatch after requirements and screens — cost of skipping mid-flight review

Long read 5 min
#indie-dev#ai-collaboration#agent-design
Story 2026.07.12

Why only now for us

First day on Grok after Claude quota friction — speed and back-and-forth without waiting

Long read 4 min
#ai-collaboration#indie-dev#agent-design
Method 2026.07.12

Why I pin a model on each todo

How dispatch injects model tags into subagents, and why longer todos are design not clutter

Long read 5 min
#agent-design#context-management#ai-collaboration
Method 2026.07.12

Subagents start blank

When a todo line and detail block are the whole interface — including a 140-turn failure

Long read 5 min
#agent-design#context-management#ai-collaboration
Method 2026.07.07

The Actual Point of Using AI - Loop Engineering

Long read 8 min
#agent-design#ai-collaboration
Tip 2026.07.07

Where Agent Development Starts - Prompt Engineering

Short 6 min
#ai-collaboration#agent-design
Method 2026.07.07

Making It So You Don't Have to Say It - Harness Engineering

Short 5 min
#agent-design#context-management
Story 2026.07.05

Just Start Already

Short 6 min
#natural-language-dev#ai-collaboration
Lesson 2026.06.26

Two Token-Saving Tricks I Found the Hard Way

Set a lower default and lock each skill's model: two fixes that cut my cron token usage.

Long read 12 min
#claude-code#agent-design#ai-collaboration
Lesson 2026.06.11

A Skill Is Just a Well-Made Prompt

Constraining behavior, reuse, auto-invocation, easy authoring — the four properties of Claude Code skills

Long read 9 min
#agent-design#natural-language-dev
Lesson 2026.06.11

The Code I Wrote by Hand Was Already in Claude Code

As prompt engineering gets built into the tools, what a builder should hold onto is an understanding of how LLMs behave

Short 9 min
#ai-collaboration#agent-design
Method 2026.06.11

Every Session, the LLM Meets You for the First Time - Context Engineering

Context engineering and CLAUDE.md — how to ship project context to an LLM that has no memory

Long read 11 min
#documentation#context-management
Method 2026.06.11

You Don't Need to Code to Build an App

What non-developers actually need to get right, from a 10-year developer who builds with natural language

Series 9 min
#natural-language-dev#agent-design
Method 2026.07.06

AI Writes All My Code — So Why Do I Still Blog?

The real reason I blog was never the content. It was the review.

Long read 9 min
#content-pipeline#ai-collaboration#indie-dev
Lesson 2026.07.04

I Automated a Spot That Shouldn't Have Been Automated

Safe automation is knowing what to leave to humans

Long read 10 min
#agent-design#ai-collaboration
Lesson 2026.07.03

I Ditched the Claude Deploy Skill for GitHub Actions — and My Token Usage Hit Zero

How a self-hosted runner rabbit hole led to appleboy/ssh-action for home server deploys

Short 5 min
#deploy-automation#home-server
Method 2026.06.11

How to Write Instructions for an AI Agent

Why "do B2" fails: handing your agent the full context with the build-plan format

Video soon 8 min
#agent-design#indie-dev
Method 2026.06.11

From Idea to Build Plan: Automating 8 Design Docs with AI

Revealing the docs-spec workflow validated through myWiki's design process

Video soon 9 min
#agent-design#documentation#indie-dev
Tip 2026.07.02

Why You Can't Close Your MacBook While Running an Agent — How I Started Using Amphetamine

Short 2 min
#ai-collaboration
Method 2026.07.01

Why You Don't Have to Read Every Raw File to Get an Answer — 4 Levels of Wiki Index Priority

Long read 11 min
#personal-wiki#ai-collaboration
Lesson 2026.06.30

[Blog 3] Jumping from Seed Straight to Draft Kept Missing the Point

Why a two-stage seed→draft pipeline drifts off-target, and how a brief checkpoint fixed it

Long read 7 min
#content-pipeline#agent-design
Story 2026.06.27

The Well Wasn't Dry

How I built blog-mine when daily blogging left my queue empty

Long read 9 min
#content-pipeline#personal-wiki
Method 2026.06.27

Every Skill Pipeline Converged to the Same Shape

I built separate pipelines for blogging, apps, and tasks. They all ended up identical.

Long read 9 min
#agent-design#ai-collaboration
Method 2026.06.27

Why I Dropped Codex and Wired Claude CLI Into Hermes

Getting daily AI news via cron without spending a single credit

Long read 9 min
#home-server#deploy-automation#ai-collaboration
Lesson 2026.06.25

Why digest Wasn't Growing My Wiki

How 1,861 raw files went unfound by digest, and how a second-layer index cache fixed it.

Long read 6 min
#personal-wiki#ai-collaboration
Method 2026.06.23

Skills Grow As You Use Them

A real record of building the triage skill through conversation

Series 9 min
#agent-design#ai-collaboration
Method 2026.06.22

Put Logic on the Model and Duplication Disappears

Avoid copy-pasting update rules to three places: gather them into a single model method.

Series 12 min
#backend-design#orm
Method 2026.06.22

Routers Do HTTP, Logic Lives in Services: Separating Layers

Why I split router, service, and repository responsibilities one line each

Series 9 min
#backend-design#layered-architecture
Method 2026.06.22

Common Modules and Base Classes to End Code Duplication

Around the third domain, lift the repeating code up into common

Series 8 min
#backend-design#code-duplication
Method 2026.06.22

Your Folder Structure Is Your Design

Why I organize by domain instead of function, and what changes when you do

Series 8 min
#backend-design#project-structure
Method 2026.06.22

Data Access Through Repositories Only

Lock your queries inside repositories and there's only one place left to change

Series 9 min
#backend-design#data-access
Story 2026.06.22

Everyone Was New to ORMs, So I Wrote the Guide

A 17-section development guide written to stop copy-paste duplication

Series 8 min
#backend-design#indie-dev
Method 2026.06.22

Validate at Every Boundary: Schemas and Layered Defense

Don't ship your models as-is; validate at each layer with a different responsibility

Series 9 min
#backend-design#data-validation
Method 2026.06.22

Only Catch the Exceptions You Can Handle

Catch only what you can recover from, and let unrecoverable exceptions rise to the caller.

Series 7 min
#backend-design#exception-handling
Story 2026.06.22

I Automated Todoist with MCP, Starting with Sorting

From triage to execution: how I automated Todoist by connecting it to Claude Code via MCP

Long read 11 min
#agent-design#api-integration
Tip 2026.06.22

The First To-Do App That Had Everything I Wanted

Why I chose Todoist: global quick add, free tier, and an MCP that makes it programmable

Long read 7 min
#api-integration#ai-collaboration
Method 2026.06.19

The Justice League Once Lived in My Stock App

BaseSqlModel, BaseRepository, a 15-chapter guide, and making the AI stick to one pattern.

Series 8 min
#ai-collaboration#indie-dev
Lesson 2026.06.19

The AI Was Fine. I Just Didn't Know the Tools.

Five automation mistakes in my stock app and what finally changed how I work.

Series 12 min
#ai-collaboration#indie-dev
Story 2026.06.16

Storing Is Only Half the Job: I Built a Search Skill Too

If the wiki has the answer, shouldn't it be able to find it when asked?

Long read 9 min
#personal-wiki#ai-collaboration
Method 2026.06.11

The Hard Part Wasn't Collecting, It Was Digesting

How I set up Claude Code to run the second wiki: digest rules, pin, pipeline, and hooks.

Long read 7 min
#personal-wiki#agent-design#content-pipeline
Story 2026.06.11

If It Doesn't Pile Up Automatically, You Won't Collect It

CLI only worked at my desk, and remote kept trying to edit my wiki, so I moved to Hermes

Long read 9 min
#personal-wiki#indie-dev
Lesson 2026.06.18

[Blog 2] AI Hallucinated From Examples I Intentionally Made

I removed the markers, and AI filled them with things that looked like my own story.

Long read 6 min
#ai-collaboration#agent-design#indie-dev
Method 2026.06.18

[Blog 1] Markdown Only, No Database: A Blog AI Manages End-to-End

The technical architecture of slowloop lab: Astro, text files, and a second brain wiki

Long read 7 min
#indie-dev#ai-collaboration#content-pipeline
Method 2026.06.18

[Blog 5] What It Means for AI to Manage Your Whole Blog

With just text files, AI can read and rewrite your entire blog without a database

Long read 8 min
#ai-collaboration#content-pipeline#indie-dev
Method 2026.06.18

[Blog 4] How Conversation Becomes a Post: One Sentence to Published

AI-prompted posts always sound generic. I built a skill pipeline to fix that.

Long read 9 min
#content-pipeline#ai-collaboration#agent-design
Story 2026.06.17

The Person Building Alone with AI Agents

Without a second brain, I don't think I'd have gotten this far

Long read 7 min
#indie-dev#ai-collaboration
Story 2026.06.11

How I Built My Mom's Online Art Museum in 6 Hours

Planning on the commute, AI that started without asking, and how we got it shipped.

Video soon 9 min
#indie-dev#ai-collaboration#home-server
Lesson 2026.06.11

I Read the Terms of Service After Building the Whole Thing

A stock portfolio app dev story: KIS API regulation traps and a last-minute pivot

Long read 9 min
#api-integration#indie-dev#home-server
Story 2026.06.16

Before Building the App, I Tried CLI and Obsidian First

I fed 130 scattered chat histories into a CLI to validate the hypothesis in a single day.

Long read 10 min
#personal-wiki#ai-collaboration
Story 2026.06.16

I Read a Stock Book and Decided to Build an App Instead

Zero stock knowledge, built it anyway. Back after a year, and done in two weeks.

Long read 6 min
#indie-dev#ai-collaboration
Story 2026.06.16

Turning an Idle PC into a Zero-Cost Server

Hosting costs hurt, I turned on a home server, and hit SSL certs and domain config walls.

Long read 5 min
#home-server
Story 2026.06.16

A Token-Burning Experiment Became the Foundation of Atlas

AI generates, humans evaluate: what the template experiment left behind.

Long read 5 min
#ai-collaboration#agent-design
Lesson 2026.06.16

AI Stamped Out Templates, But I Couldn't Judge Them

Auto-generation worked. Self-verification didn't: the gap that blocks autonomous loops.

Long read 5 min
#agent-design#ai-collaboration
Story 2026.06.16

Tokens Were Going to Waste, So I Made a Screen Every Week

The starting point of a design experiment born from leftover tokens

Long read 4 min
#ai-collaboration
Method 2026.06.16

I Couldn't Pick the Design, So I Let Users Vote

Outsourcing the design call through voting, then piping that signal back into generation.

Long read 4 min
#ai-collaboration
Lesson 2026.06.16

Neither of Us Speaks English, But the Museum Is Multilingual

Running a multilingual site without a translator: filling the DB with an LLM pipeline

Long read 6 min
#indie-dev#ai-collaboration
Lesson 2026.06.16

I Didn't Build It All at Once

Why I split requirements, mockups, and code into separate phases, and what that saved.

Long read 5 min
#indie-dev#ai-collaboration
Story 2026.06.16

Five Years Later, I Built My Mom's Art Museum Right

The failed shop that taught me the difference between selling and showing

Long read 5 min
#indie-dev#branding
Method 2026.06.11

Why I Break Every Big Task into Phases

How I structure every large task with AI: phases, gates, and why both matter.

Video soon 11 min
#agent-design#indie-dev
Method 2026.06.11

Why You Should Not Integrate Your Tools

Context evaporates at every handoff. The answer wasn't tool integration, it was a spine.

Video soon 9 min
#context-management#agent-design
Story 2026.06.11

It Didn't Exist, So I Started Building It Myself

Dozens of PKM apps, nothing fit, so after an OAuth headache I decided to build my own.

Long read 5 min
#personal-wiki#indie-dev
Story 2026.06.11

I Built a Second Brain So My AI Chats Wouldn't Disappear

What a month of AI chats left behind, and why I split raw files from wiki pages.

Long read 8 min
#personal-wiki#context-management
Method 2026.06.11

AI Wrote It, But It's My Story

How raw conversations stored in a wiki become blog posts

Long read 13 min
#personal-wiki#content-pipeline
Story 2026.06.11

My Planning AI and Coding AI Were Working in Silos

The problem of context breaking between agents, and how I solved it with a second brain

Long read 6 min
#context-management#personal-wiki
Method 2026.06.11

4 Control Levers When Your Agent Won't Listen

Why it's not the model's fault, and what each of the 4 control levers actually does

Video soon 11 min
#agent-design#documentation
Tip 2026.06.11

I Quit Documentation Three Times. Then /docs-init Fixed It.

Complex structure kills documentation. The survivors: just index.md and log.md

Long read 9 min
#documentation#agent-design
Method 2026.06.11

Why "Build Me an App" Is Actually the Slow Way

One session = one item, dependency-aware splitting is the mechanism that creates speed

Long read 11 min
#agent-design#indie-dev
Lesson 2026.06.11

Decide First, Then Code: docs-spec Forces Specs Up Front

Even solo developers can avoid the "I have to rip this out" moment

Long read 9 min
#agent-design#indie-dev
Lesson 2026.06.11

3 Painful Lessons Deploying a Stock App at Home

iptime CAA block, DB port conflict, stale checkout: things you only learn the hard way.

Long read 10 min
#home-server#deploy-automation#api-integration
Method 2026.06.11

Running Multiple Apps on One Home Server

How I run a stock app, art gallery, and bot on the same server, full setup shared.

Series 8 min
#home-server#deploy-automation
Story 2026.06.11

Building a Loop Where Discord Messages Land in Your Wiki

How ideas thrown from your phone pile up in a wiki, built with a single ops repo.

Long read 10 min
#personal-wiki#deploy-automation
Method 2026.06.11

How I Run hermes and Claude Code Together

hermes for chat, Claude Code for code and wiki: the split I found running both at home.

Short 6 min
#context-management#agent-design