Start here · Lesson 1 of 6
What is YAGNI and how does it work?
Published June 9, 2026 · Updated August 14, 2026
YAGNI is the coding agent that knows your company: a drop-in CLI and desktop harness your engineers run, backed by agent Teams that carry ongoing engineering scopes like PR review and production watch. It learns how your team builds software, keeps a shared decision ledger, and nothing consequential ships without a person's approval.
What does “coding agents that know your company” mean?
Most coding agents know the repo in front of them and nothing else. YAGNI’s agents are grounded in the company around the code: the ticket that asked for the change, the Slack thread where scope shifted on Tuesday, the customer behind the bug report, the decision your team already made about queues. The answers are cited, so you can check the work instead of trusting it.
That grounding compounds. Every run writes to a shared decision ledger: what was chosen, what was rejected, and why. Your agents read it before they plan, so they stop re-deciding what your team already settled. Thirty days in, YAGNI knows how your team builds software, and everything it learned is yours.
What is YAGNI Code?
The harness itself: a CLI and desktop app your engineers run, drop-in with the skills, plugins, and MCPs they already use. Its signature move is the /go run, which takes a task from repo map to opened PR through checkpoints that are yours. The YAGNI Code lesson covers the run, the routing, and the install.
What is a Team?
The unit that owns an outcome. A Team carries a scope, its Responsibilities, the Number it answers for, and the Playbook it has learned, while the agent workers engaged on it carry the execution. From day one an engineering Team can run PR review through the lenses your team sets, watch production, triage incidents, answer “why is this built that way” questions, run the rhythms, and turn context into well-formed tickets.
What stays in your hands?
Judgment. A /go run pauses at the plan until you approve it. Consequential work arrives as a staged Decision in the Feed: the proposal, the evidence, the Team’s confidence, waiting on you. Autonomy is earned on the record and promoted by a person, never a switch the system flips itself. And the floor is permanent: irreversible and high-blast actions wait for a person at every level.
Where does YAGNI sit in your stack?
On top of it. YAGNI connects to the tools you already pay for, reads across them, and ships approved work back into them. It never hosts your apps or migrates your data. The Connections lesson covers the native connectors, and the security page covers how workspace data is isolated and audited.
Where should you start?
Onboarding is a conversation, not a funnel: book 30 minutes and we set the workspace up together, GitHub first. If you are a developer whose workspace already exists, install YAGNI Code and run your first /go. The next lesson, How do you get your first Brief?, walks through day one.
Common questions
Does YAGNI replace the tools my team already uses?
No. YAGNI is additive and drop-in. Your skills, plugins, and MCPs slot straight in at the terminal, and the workspace reads the tools you already pay for and ships approved work back into them. Your issues stay in Jira or Linear and your repo stays on GitHub.
Is YAGNI one agent or many?
One voice, many hands. You talk to @yagni: one identity, one memory, across everything you connect. The work itself is carried by agent workers engaged on your Teams, a proposer, a builder, a reviewer, and the work is credited to the Team that did it.
Does the agent act without my approval?
Only where it has earned the right to. Every Team starts in Training, where nothing ships without you. Autonomy is promoted from the record, one rung at a time, and irreversible acts like a production deploy or an external send stay gated at every level, forever.
What does the name YAGNI mean?
It is the software-engineering principle You Ain't Gonna Need It. The only thing YAGNI replaces is the frontier API bill you were about to renew and the checking work that was never really the job.
Who is YAGNI for?
Engineering teams who already run coding agents and want them to work as a team: shared knowledge, shared review rules, one record, one bill. The pitch is not a different way to write code; it is a harness the whole team compounds inside.