Sprint and gates

A sprint is two commands your agent runs for you: sprint start, which plans before any code is written, and sprint complete, which checks the work before the ticket can close. The Quick start walks through one sprint; this page explains the parts.

Plan before code

sprint start makes the agent read your repository and the ticket, then write three files in .tickets/<id>/:

It then stops with a brief and builds nothing until you approve.

Here is the brief for a ticket that adds an "Export CSV" button to a small ToDo app. It says what the change does, picks the tier, lists the files it will touch, checks the plan from the user's, security's and architecture's side, and ends with the acceptance criteria.

The Cockpit session after sprint start: the agent's Sprint brief for the ticket Add CSV support, with Accomplishes, Tier normal, Files index.html only, a Perspective check of user, security and architect, Impact with no high-risk triggers, and Human checkpoint not required, followed by the acceptance criteria.

The agent picks the lightest tier that still protects the work:

Sign off the plan

The ticket's Plan, opened from the Open ↗ link on the Ticket details card, has a Sign-off section: the tier, one line of risk, and a Plan approved box. You tell the agent to go ahead, and it ticks the box. sprint complete refuses to close a ticket whose plan was never approved.

The Plan document of a ticket: the Sign-off section reads Tier normal, Risk new static app in empty repo, only input is user-typed text (rendered via textContent), with a ticked Plan approved box, and the Approach section begins below it.
The sign-off, once approved.

Build and test

While the agent builds, the Test Plan section of Acceptance lists the checks that prove the criteria. The protocol says each box is ticked when its evidence exists, not in bulk. A ticked box is the agent's claim that the check passed. Canon checks that the boxes are ticked, not that they are true; checking that is the evaluator's job.

The Acceptance document of a ticket in progress, scrolled to Test Plan: three ticked checks (node --test passes, a grep for storage APIs and innerHTML returns no matches, and a manual browser pass in light and dark), then QA with Tested locally ticked. The tree at the left shows Criteria 11/11, Test Plan 3/3, QA 1/1 and Sign-off 1/1.
A test plan, with every box ticked.

Close the sprint

Ask for sprint complete. Before it closes anything, the agent runs its own checks in order: code simplification, code review, a security review, a repository check and a docs audit. It skips the ones that do not apply and says why. Then it starts two fresh agents, one after the other, that have never seen the build:

The terminal during sprint complete, after the reviewer's two findings were fixed and committed. The agent says it is dispatching the binding evaluator, and canon-evaluator shows as a backgrounded agent in the bar below. The Ticket details card has an Acceptance updated badge.
The evaluator launches with no memory of the build, once the reviewer's findings are fixed.

The evaluator marks each criterion pass, fail, partial or not-run, with evidence. Anything other than pass makes the verdict fail, and a failing verdict blocks the close. A reviewer's "no" is a note for you; the evaluator's "fail" is a refusal.

Canon also checks the sprint's paperwork. The close is refused if a required file is missing, a checklist item is unchecked, the plan has no approach or no approved sign-off, summary.md or the gates table is missing, or the evaluator's verdict is not pass. A refused close says which of these it was; fix it and run sprint complete again.

For what each gate does and does not cover, see Wrapup gates.

What the ticket shows afterwards

Open the closed ticket on the board. Its tree keeps the record. Wrapup Gates, under Acceptance, is the table of which gates ran, which were skipped, and why.

The Wrapup Gates entry of a closed ticket: a table with a gate, a status of ran or skipped and a reason for each. The reviewer row reads verdict NO with two low findings, both fixed, and the eval row reads verdict pass.
The Wrapup Gates table.

Once the evaluator has run, the Eval Agent entry holds its report: the per-criterion grades with the evidence for each, and the run id that shows it was a separate run. Once the reviewer has run, the Review Agent entry holds its findings and verdict; a bugfix-tier sprint skips the reviewer, so it has none.

The Eval Agent entry of a closed ticket: an evaluator run id and the graded-head commit, the ticket, the date and the model, then a Criteria table with a pass status and the evidence for each.
The evaluator's grades, with evidence.

The Learnings entry holds a candidate lesson from the sprint, written for a later reader to judge; see Learnings. The Summary entry compares what was planned with what was delivered.

The Learnings entry: a candidate marked UNPROMOTED with its ticket and date, and a tree listing Deviations, Evaluator findings, Reviewer findings and Candidate lessons.
A learnings candidate, not yet promoted.
The Summary entry: a table of each acceptance item with its status, delivered, and a Notes column.
Planned against delivered.

A lighter close for docs and demos

For work that is only documents or mockups, or for a live demo, a ticket can be marked Lite when you create it.

Its close keeps the security review and the binding evaluator, which runs on a smaller model, and skips the reviewer and the rest of the checks. It is your choice for a ticket, never automatic, and the evaluator is never skipped. See Lite close.