Skip to main content

03.Build / learn / document

Docs
& notes

Practical notes on product development, engineering, and running a one-person company in collaboration with AI.
Browse the docs

Notes from real projects

Field notes

14articles
01 engineering practice

Tool-call optimization: stop using context as a data transfer layer

General tool-call design patterns for input references, backend working storage, compact results, on-demand reads, and asynchronous continuation, illustrated by a market-analysis implementation.

02 engineering practice

Low tool-call success? Fix these six layers before switching models

A practical Agent optimization review covering tool scope, schemas, repair results, retries, state, and observability before model comparison.

03 engineering practice

A Shorter Prompt Won’t Fix Your Agent: 10 Problems I Hit

A weak Agent is not always a weak model. Real numbers show how context, tools, state, streaming, and useful system records shape the result together.

04 engineering practice

Prompt Cache Reuse Dropped From 99% to Zero—Here’s Why

Two production traces show a simple rule: when the order at the start changes, prompt-cache reuse can fall from 99% to zero even if the content looks almost the same.

05 Getting started

Inside a One-Person AI Company: What I’m Building Right Now

A current record of the products, AI infrastructure, and GeekCode writing I am working on—including what is not finished yet.

06 engineering practice

Should You Test Vibe-Coded Software? Use 4 Risk Layers, Not Coverage

Vibe Coding needs tests, but more is not always better. Start with what a change could break, then choose the smallest useful check for that risk.

07 engineering practice

Why Vibe Coding Gets Unstable—and the Engineering System I Use

AI can write code quickly, but quick is not the same as safe. Define the promise first, write the code second, then check and record what really happened.

08 engineering practice

Slow API? Don’t Add Machines Yet—Find the Bottleneck in 5 Steps

The first job in a slow-endpoint investigation is not “optimization.” It is finding out where the time actually goes.

09 ai perspectives

Your AI Demo Works. Can It Survive Production? 4 Guardrails

A feature that demos well is not necessarily ready to ship. Keep uncertainty at the boundary before asking users to rely on it.

10 independent development

Set Up Your First Environment

A practical environment-setup guide is being prepared for this chapter.

11 independent development

SaaS or Self-Hosted? 4 Costs Indie Developers Often Miss

How independent developers can weigh hosted services against systems they operate themselves.

12 independent development

Why Every Developer Should Ship an Indie Product: 5 Reasons

A comprehensive guide to understanding independent development, its charm, and value

13 Getting started

Getting started

An introduction to GeekCode, what it builds, and how this documentation is organised.

14 ai perspectives

What Is MCP? The Missing Link Between AI, Tools, and Data

An introduction to how the Model Context Protocol connects LLM applications with tools and external information.