#04 · Planning, Jira and Azure DevOps

How do you plan a sprint run by people and AI agents?

The HumanAI sprint plan orders Jira tickets per person, with dependencies, and dispatches the work to the agents. Azure DevOps pull requests, runs and approvals show up in the same place.

Video: in the sprint plan, a ticket moves from running to waiting for validation and then to done — Real cockpit, shown in Portuguese, with demo data; technical details omitted.

HumanAI cockpit: sprint plan with per-person lanes, dependencies and an item waiting for human validation — Real cockpit, shown in Portuguese, with demo data; technical details omitted.

The problem

The plan lives in one tool, the code in another and approvals in a third. Nobody sees the right order of execution.

How it works

Everyone sees their Jira tickets in the cockpit, with their own credential.
The manager builds the sprint plan with the order of execution and dependencies.
The plan dispatches work to the agents and follows progress.
Pull requests, runs and approvals show up in one place.

What it includes

Tasks with sprint, burndown, ticket canvas and «start on a machine»
Sprint plan with dependencies, per-person lanes and reminders
Automatic sprint cycle, with manual trigger
Pull requests and runs: vote, comment, review
Azure DevOps events that become work or a notice
Sprint documentation and archive, portfolio and dossier

What sets it apart

The plan triggers the agents' work and follows it through to the end.

Questions

Does it replace Jira?

No. It reads Jira with each person's credential and shows the plan on top.

When does a ticket close?

When the validator confirms the expected outcome, not when the code merges.