know.2nth.ai Software
Software · Domain Hub

The software branch.

The idea the whole tree rests on: AI is just software, and an LLM is just a brain. A brain with no hands, no memory, and no tools does nothing. Software, tools, and version control are what turn a model into work. This branch owns the craft — Git, GitHub and code repositories, CI/CD, packages, languages. Where Technology covers the platforms you run on, Software covers how you build, version, review, and ship the code itself.

13
Live leaves
Git
The ledger
14th
Branch of the tree
01 · The thesis

AI is just software. LLMs are just brains.

Strip away the mystique and an LLM is a stateless function: text in, text out. It has no memory between calls, can't take an action, and can't check whether it was right. Everything useful an "AI" does — remembering, calling tools, reading a codebase, opening a pull request, staying correct — is software wrapped around the model. The agents domain says it plainly: agents are software, not prompt soup. This branch is where that bar gets defined: version control, repositories, review, and CI as the discipline that makes both human and agent work compound instead of drift.

02 · Skill nodes

What's in this branch

Thirteen leaves, from the thesis through to how agents operate and plan inside a repo. Each is written for two readers: the human learning the craft, and the agent that has to operate inside it.

Live · thesis

AI is just software software/ai-is-software

The manifesto. What an LLM actually is (a stateless next-token function), why a brain needs a harness, and why "buying AI" really means buying software discipline. The frame every other node hangs off.

LLM = brain Harness Tools + context Compounding
Live

Version control software/version-control

Git as the ledger. Commits, branches, merges, and history as institutional memory — the substrate that makes software reproducible, reviewable, and auditable, for humans and agents alike.

Git Commits Branches History
Live

GitHub & code repositories software/github

The repository as system of record. GitHub, GitLab, Bitbucket, Codeberg; pull requests, code review, issues, Actions/CI, releases — and why repos are the layer agents read, write, and ship through.

GitHub Pull requests Actions / CI Agent PRs
Live

Repositories & monorepos software/repositories

How code is organised — monorepo vs polyrepo, README and docs-as-code, branching strategies, and the repo as a knowledge-management surface, not just a code dump.

Monorepo Docs-as-code Structure
Live

CI/CD & automation software/ci-cd

Pipelines, tests as gates, and deploy-on-merge. The automation that turns "it works on my machine" into "main is always shippable" — including this site, which auto-deploys from main.

Pipelines Tests as gates Deploy-on-merge
Live

Packages & dependencies software/packages

Registries (npm, PyPI, crates, Maven), semantic versioning, lockfiles, and supply-chain risk — the dependency graph every modern build (and every agent install) sits on top of.

npm / PyPI SemVer Supply chain
Live

Programming languages software/languages

How to choose one, and why it matters less than the discipline around it. Typed vs dynamic, ecosystem and runtime fit, and the languages agents write most reliably.

Typed vs dynamic Ecosystem fit Agent-friendly
Live

Go (Golang) software/go

Google's compiled, statically-typed language built for simplicity and scale. Goroutines, single static binaries, fast compiles — the language of cloud-native (Docker, Kubernetes, Terraform), and one agents write reliably.

Goroutines Static binary Cloud-native
Live

Rust software/rust

C/C++ performance with memory safety and no garbage collector — proven at compile time by the borrow checker. Cargo tooling, WASM and embedded reach, and the honest learning curve. The Go vs Rust split, in full.

No GC Memory-safe Systems · WASM
Live

Software for agents software/software-for-agents

The repo as agent context, SKILL.md in version control, agent-authored pull requests, and CI as the agent's safety net. Where this branch meets the Agents domain head-on.

Repo-as-context Agent PRs CI safety net
Live

Planning with agents software/planning-with-agents

The backlog is the prompt. Spec-driven development, the backlog as agent-readable data, cadence below the sprint, and what to measure when velocity breaks. The process-level continuation of software-for-agents.

Spec-driven Backlog as data Operator model
Live

Orchestrating agents software/orchestrating-agents

From pairing to orchestrating a small fleet. The three execution modes (interactive planning, isolated worktrees, headless batch), orchestrator-vs-peer patterns and their token cost, the three forge-automation layers and their permission traps, and an adoption sequence. Foundation before fleet.

Execution modes Worktrees Forge automation
Live

Waterfall software/waterfall

The model its author told you not to use. Royce's 1970 paper drew the linear model as the thing to avoid; the industry mandated it anyway. The history straight — the misread paper, the DoD codification, the Standish numbers and their dispute — and the honest half: where phase-gated development still fits.

Royce 1970 Phase-gated History
03 · Related domains

Where the software branch connects

Software is the craft underneath every other branch. It pulls hardest on Agents (agents are software) and Technology (the platforms that software runs on), and it shows up wherever a domain treats its rules as code in version control — Finance, Business, Design.