This post covers the core concepts of AI engineering — not machine learning research, but the practical discipline of taking pre-built models and shipping them into real products. By the end, you'll have a working mental model of LLMs, RAG, MCP, agents, fine-tuning, and quantization, and understand how they fit together.
These two disciplines are often conflated, but they're distinct.
Artificial Intelligence has rapidly evolved from a niche research field into one of the most transformative technologies in software engineering. Today, developers across Android, backend, web, DevOps, and cloud engineering are increasingly expected to understand AI systems and how to integrate them into real-world products.
This article walks through the core concepts behind modern AI engineering — including Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), MCP (Model Context Protocol), tools, embeddings, and the architecture of AI-powered systems.
| import logic from 'logicjs'; | |
| var or = logic.or, | |
| and = logic.and, | |
| not = logic.not, | |
| eq = logic.eq, | |
| run = logic.run, | |
| lvar = logic.lvar, | |
| between = logic.between | |
| var g1_rule = ` |
Core Problem: Users need a frictionless way to log daily actions and track their impact without overwhelming complexity.
Invariants for Success:
Must-Have Outcome of the MVP: A single screen that allows users to log actions quickly, view a feed of their logs, and see metrics associated with those actions.
| Keyword | Category | Search Intent | Notes | |
|---|---|---|---|---|
| indie hacker | Indie Development | Community/identity | Very high overlap with IH audience; good for blog/landing pages | |
| indie developer tools | Indie Development | Tool discovery | People actively look for resources to support indie projects | |
| build side project | Indie Development | How-to/educational | Entry point for your funnel | |
| bootstrap startup | Indie Development | Founders searching for growth without VC | Good for blog/landing pages | |
| solo founder guide | Indie Development | Educational | Clear match for your positioning | |
| startup roadmap | Growth & Roadmap | How-to planning | Competes with Notion/roadmap templates | |
| startup checklist | Growth & Roadmap | Tactical | Strong “template” content angle | |
| indie hacker roadmap | Growth & Roadmap | How-to planning | Niche-specific variant you can own | |
| startup daily tasks | Growth & Roadmap | Practical guidance | Perfect fit for “daily missions” angle |
| { pkgs ? import <nixpkgs> {}}: | |
| with pkgs; mkShell { | |
| # Include C++ headers for regular clang calls: | |
| NIX_CFLAGS_COMPILE = lib.optionals stdenv.isDarwin [ | |
| "-I${lib.getDev libcxx}/include/c++/v1" | |
| ]; | |
| nativeBuildInputs = [ | |
| ... |
| ---- MODULE VirtualMachine ---- | |
| VM_Version == "1.0.0" | |
| LOCAL INSTANCE Sequences | |
| LOCAL INSTANCE Integers | |
| LOCAL INSTANCE TLC | |
| CONSTANT PC | |
| CONSTANT SUBJ |
In this document, I propose to separate SLI from SLO as a new data kind in OpenSLO specification. See discussion #29.
A service level indicator (SLI) represents how to gather data from metric sources.
apiVersion: openslo/v0.2.0-beta
| # python3 /tmp/iterategosrc.py /tmp/go/src/ | |
| # check whether go grammar can pass all golang source files. | |
| import os | |
| import sys | |
| import glob | |
| import subprocess | |
| root_dir = sys.argv[1] | |
| total = 0 | |
| failed = 0 | |
| for filename in glob.iglob(root_dir + '**/**.go', recursive=True): |