Knowledge Base

Concepts

The vocabulary of C², defined. Each term links into the method where it’s used in full.

Core ideas

P = aic²: Productivity = AI × Context². Your output is the AI crew multiplied by the Context and Code you build around it.
The two Cs: Context and Code — the two systems C² optimises, and the two letters in C². They multiply; if either is zero, productivity collapses.
Contextbase: What guides: briefs, patterns, gotchas, decisions. Written as you work, committed to git, read by the AI before it acts. It compounds.
Codebase: What runs: the software itself. Richer context makes sharper code; cleaner code surfaces sharper context.
Pilot / Crew: The human is the pilot — sets course, reviews, owns the quality bar. The AI is the crew — writes code, runs tests, manages files.
Harness engineering: The layer C² operates at — the gather → act → verify loop — which contains both prompt and context engineering.

The Cascade: The six-tier chain every piece of work flows through: Platform PRD → Feature PRD → Prompt Brief → Task → Session Brief → Release Note.
Prompt Brief: The atomic build unit — where the pilot hands off to the crew. Interactive (pilot present) or Autonomous (pilot absent).
Quality gate: The six-item check — goal, scope exclusions, testable AC, non-goals, testing approach, definition of done — every brief passes before execution.

The Router (router.md): The file your agent reads first — the living index of the contextbase. Named for your agent. Links rather than embeds.
Knowledge index: The index of 03-knowledge the Router points to. The AI reads the index, not every file.
Learn loop: Capture discoveries fast during a session, then periodically consolidate them into 03-knowledge and the Router.
Compaction: Keeping the working context lean. C² does it three ways: the Session Brief, the Router, and the Learn loop.

Lead agent: Executes — reads context, writes code, manages git, writes briefs. One leads per codebase surface.
Bench agent: Reviews, never executes. Independent second opinion on PRDs, security, architecture. Budget-capped.
Specialist agent: A scoped subagent for repeatable tasks — QA review, release notes, security review.

WIP cap: Max five in-progress PRDs. Anything above goes to backlog — forces completion before starting.
Brief-before-active: A PRD can't go in-progress without at least one Prompt Brief. If you can't write a brief, it's a thinking document.
Monthly PRD review: A 30-minute monthly pass: walk every in-progress PRD; force-move stale ones to backlog.