The Academy
Learn to run agent teams, one lesson at a time.
Four short courses, shaped like the four questions every team asks: who the Workers are, how you set them up, how you train and manage them, and how you work with them from your own tools. Read in order, or jump to the surface in front of you.
The YAGNI Academy is the guided way to learn agent Teams: short lessons, grouped into four courses, that take you from meeting the six Workers and your first work item to setting up a Team, training and managing it on the Ladder, and working with it from your own tools. Each lesson covers one surface or one habit, with videos added as they are recorded.
Course I
Start here
What YAGNI is, who the six Workers are, and one work item moving from the backlog to a merged pull request. Orientation for the first week.
What is YAGNI and how does it work?
An orientation to YAGNI: agent Teams that mirror your engineering org, six named Workers with boundaries, the work item and its four gates, and autonomy that is earned on the record.
Read the lesson Lesson 2Who are the six YAGNI Workers and what does each one do?
Bailey, Reeve, Wright, Proctor, Fletcher, and Harper: what each Worker reads, what it produces, and the boundary it never crosses, in the order the work moves.
Read the lesson Lesson 3How does your first work item move from the backlog to a merged pull request?
One ticket, seven steps, four gates: Bailey proposes, Wright plans, Reeve critiques, Wright builds, Proctor reviews, Fletcher tests in a browser, you merge, Harper reports.
Read the lessonCourse II
Set up a Team
Connect the tools you already run, create a Team that mirrors yours, engage Workers, and give Fletcher an environment to test in.
What is a YAGNI Team and what are its Responsibilities?
A Team mirrors one of your engineering teams, never a repository. It carries the Responsibilities, the repos, the backlog, the Playbook, the budget, and one accountable person. How to create one and when to add another.
Read the lesson Lesson 2Which tools does YAGNI connect to, and what does it do with them?
GitHub first through the workspace App, then Jira or Linear for the backlog, Slack for gates and standups, and Confluence or Drive for the export, plus the rest of the native connectors, MCP servers, and custom services.
Read the lesson Lesson 3How do you set up a repository environment so Fletcher can test a pull request?
Begin setup reads the repository and fills in the install steps, services, and variables. You add the dependency repos and their pins, the secrets, and the auth mode. Then Fletcher boots the app and walks the change in a browser.
Read the lesson Lesson 4What is an Engagement, and how do Cadence, Authority, and Brief work?
An Engagement is a Worker's employment on one Team: when it runs here, what it may do alone here, and what it knows here. How settings inherit, how caps bound spend, and why every Engagement starts at Training.
Read the lesson Lesson 5How do you connect Okta single sign-on to YAGNI?
The full Okta SAML setup for a YAGNI workspace: create the app, exchange the two sets of values, map your admin groups, and turn on the Okta tile. About ten minutes of copy-paste.
Read the lessonCourse III
Train, monitor, manage
The Ladder and the track record, the Playbook, the Brief and the standup, Work and the case file, and what to do when a Worker gets it wrong.
How does the Ladder work, and how does a Worker earn autonomy?
The three rungs an Engagement climbs, the track record a promotion cites, what lowers a rung, and the floor that never moves whatever the rung.
Read the lesson Lesson 2How does a Team's Playbook learn your rules?
Where a Team's rules come from, how a proposed rule is adopted or dismissed inline, how business rules and engineering guardrails differ, and what a Play is.
Read the lesson Lesson 3How do you read the Brief and Harper's standups?
Harper composes the Brief each weekday morning and posts the standup to your Team's channel: what shipped, what is in flight, what needs a person, with the evidence linked.
Read the lesson Lesson 4How does Work and the case file track a work item?
Work is the queue and the record: by-Team lanes over live work items, with the case file as the one page where all four gates, the runs, and the costs resolve.
Read the lesson Lesson 5What do you do when a Worker gets it wrong?
The runbook for a bad run: open it from the case file, read what the reviewer discarded, correct it in the moment, retry, lower a rung, and ask @yagni.
Read the lessonCourse IV
Work from your own tools
YAGNI Code in the terminal and on the desktop, managing Teams from Claude Code or Codex, MCP servers, telemetry, and asking @yagni.
What is YAGNI Code and how do you work with it?
The coding agent your engineers run by hand, as a desktop app or in the terminal: install, the plan, implement, review rhythm you drive, your skills, plugins, and MCP servers, and the models, meter, and record it shares with your Teams.
Read the lesson Lesson 2How do you manage YAGNI Teams from Claude Code or Codex?
Two separate lanes for a harness your engineers already love: add the YAGNI MCP server to manage Teams from inside Claude Code or Codex, and run yagni connect to route that same harness through YAGNI's models.
Read the lesson Lesson 3How do you set up MCP servers in YAGNI Code?
Bring the MCP servers your team already uses into YAGNI Code: repo .mcp.json files work as-is, a one-command import moves your Claude Code setup, OAuth logins open from the session panel, and vendor-approved remote servers are the one honest edge case.
Read the lesson Lesson 4How do you export YAGNI Code telemetry to Datadog?
Send every YAGNI Code session in your workspace into Datadog: one admin setup in Settings, the Datadog direct-SaaS preset fills in the endpoint, and yagni doctor confirms Datadog accepted a real record. Traces, metrics, and log events carry tokens, cost, lane, and tool calls in the same shape Claude Code emits.
Read the lesson Lesson 5How do you ask @yagni for help?
The rail beside the case file, the pinned composer on the Front, and the full-page Ask: one voice with one memory, grounded in the decision ledger, your Teams' record, and the live rows of your connected tools.
Read the lessonThe best classroom is your own backlog.
Connect a repository, engage the first Workers at Training, and watch one work item cross the Team this week. The lessons will still be here when you have questions.
or read how agent teams work