Documentation
How to do it, step by step.
13 guides, from your first backlog to gates, budgets, pipelines and webhooks. Every one of them describes a screen that exists — nothing here is a plan.
Getting started
From an empty account to a board with real work on it.
QuickstartThe shortest route through Turnado: create an account, start an organisation and a project, paste your analysis, and watch a backlog appear on the board.Analysis to backlogPaste a functional design or an analysis and an agent decomposes it into epics, features and user stories with acceptance criteria — each one pointing back at the section it came from.Working from the chatThe chat is where you say what should happen; the board is where it is recorded. This is what you can ask for, which commands exist, and what lands on a ticket afterwards.
Working on the board
The daily work: writing items, moving them, planning a sprint.
Acceptance criteriaGiven/When/Then criteria are what turns “the model says it is done” into something a test can disagree with. This is how to write them so the gates and the test agent can use them.Statuses and gatesNine statuses, sixteen transitions and eighteen conditions. This is how a transition is refused, how to read the reason, and how a question puts an item on Blocked and an answer takes it off again.Sprint planningA sprint in Turnado has two ceilings: the hours your people have and the euros the agents may spend. This is how to compose one, and what to do with the items that fall outside it.
AI colleagues
Setting up the agents, giving them work, and keeping the bill in view.
AI colleagues and the queueSix agents with roles, a queue with slots and a WIP limit, and an autopilot that is off until you turn it on. This is how work reaches an agent, and why some work never does.Models and EU hostingTurnado splits work into three kinds and picks one model per kind. This is how to connect a key, what each kind costs, and how to refuse any model that runs outside the EU.AI cost and budgetsA ceiling per task, a budget per sprint, an allowance per month, and every run recorded on the work item it was made for. This is how to see what AI actually costs you and where it stops.
Code and delivery
From a repository to a pull request, a pipeline and a release.
Connect a repositoryGive the AI colleagues somewhere to write code: a repository, a branch naming rule derived from the work item, and pull requests you review and merge yourself.Delivery and releasesA four-step wizard from “where does your pipeline run” to a snippet you paste into it — and after that, gates that open because a pipeline reported, not because someone ticked a box.
Administration
Members, roles, models, subscriptions and the wiring to other systems.
WebhooksSubscribe to events, check the signature in Node, Python or C#, and deduplicate on the idempotency key — because delivery is at least once, never exactly once.Team and permissionsRoles are cumulative, seats are only for people who decide, and fourteen permissions are on a list no agent ever gets — however many roles you give it.