Skip to content
Docs
Arcus
Popular questions
↑↓ to navigate↵ to selectesc to close
Book a demo

QI Home overview

QI Home is where Arcus generates test cases, tracks what you accept, plans and executes runs, and reports whether each sprint is ready to ship. Work happens in sprints and Adhoc sessions.

Five stages run in order:

  1. Feed context. Attach sources to a prompt, let a sprint supply its stories, or map developer activity in Context Management.

  2. Generate. The Test Authoring Agent writes test cases grouped by story and module. They arrive in Pending status.

  3. Review. Accept the accurate ones into your library. A test case left pending is a gap, and gaps hold coverage down.

  4. Plan and run. Generate and accept test plans, and their runs report results back.

  5. Read the verdict. Coverage, Pass Rate, Confidence, and Readiness roll up into a Ready, Conditional, or Not Ready verdict.

Stages 2 through 5 all live on Generate test cases.

Automating an accepted test case happens in the Automation section: Learn with Copilot generates its automated steps, and Copilot runs them in a live browser. An automated test case is then available to the test plans you run here.

No test case enters your library, and no plan starts a run, until you accept it.

Open QI Home in the left navigation. A prompt box sits at the top, and 2 tabs list your work beneath it.

AspectSprintsAdhoc
Starts whenYou click Generate on a sprint synced from your connected project management toolYou write a prompt, attach context, and click Send
Context comes fromThe sprint stories and their linked artifactsSources you attach yourself
Use it whenYour team works in sprints and coverage should start with the sprintYou are covering a feature outside a sprint, a hotfix, or an experiment

Everything after generation is identical for both.

Connect Jira, Azure DevOps, Linear, ClickUp, or OpenProject to the project before you use the Sprints tab.

Until a tracker is connected, the Sprints tab shows Bring in your sprints and code context with 2 cards:

  • Project Management Tools: one toggle each for Jira, Linear, ClickUp, Azure DevOps, and OpenProject. Turning one on starts that tool’s sign-in. For Jira, the Atlassian sign-in page opens. A connection that needs renewing shows Expired with a link.
  • Dev Tools and AI: toggles for GitHub, Bitbucket, and GitLab, and an install link for each of the Claude Code, GitHub Copilot, Codex, and Cursor plugins. A connected plugin shows Active.

The empty Sprints tab, with the Project Management Tools and Dev Tools and AI cards outlined

Each tracker connects by signing in to it. Once a tracker is connected, the Sprints tab shows Pick a project. Select one or more of the tracker’s projects and click Link project, or Link projects for more than one. Before you link, the card shows the selected projects’ Active Sprints and Open Stories (Open Sprints and Open Work Packages for OpenProject). If you’ve connected more than one tracker, click another tracker’s card on the right to switch to it. Only one tracker can be linked at a time. See Generate for a sprint.

Each row shows its Readiness verdict, its Coverage, and when it last changed. Sprints are grouped into Current Sprints, Upcoming, and Closed.

The Sprints tab, with the Sprints tab, the Readiness and Coverage columns, and the Current Sprints, Upcoming, and Closed groups outlined

Open any row to get its working view.

An Adhoc session page, with the status chip, Context, the 4 metric cards, Test Case Review, Plans & Execution, App knowledge graph, and Insights and activity outlined

  • The verdict and the reason: a status chip such as Not Ready or Awaiting Run, and a one-line explanation, such as “Coverage is 24%, below the 85% bar.”
  • 4 metric cards: Coverage, Pass Rate, Confidence, and Readiness, each with its threshold marked. Run-based metrics show Awaiting execution until a plan runs.
  • Test Case Review: how many generated cases wait for review, with the highest-value ones to start with.
  • Plans & Execution: the state of the test plans and runs, from “No test plan yet” through to run results that need attention.
  • App knowledge graph: how many orphan nodes the runs observed (elements in the app that no test asserts on yet). See App knowledge graph.
  • Insights and activity: findings ranked Act now, Watch, and Next, such as a module at 0% coverage or flaky tests to stabilize, beside an Activity feed of what changed and when. Insights that name a module or stories link straight to them.
  • Context: a drawer listing everything Arcus read here (requirements, uploads, code changes, run history, and live-app learning), with a Refresh context action.

Insights and activity with the Activity view selected, with the Insights and Activity toggle and the activity feed outlined

An Arcus panel docks to the left of every sprint and Adhoc session page. Ask it about the work, generate more test cases, or refine a plan.

AI in Arcus lists every agent, including Explorer Agent and Copilot, with where you see each one.

AgentOwnsWhere its work surfaces
Sprint Planner AgentBuilds the Generation Plan for a sprint when you click GenerateThe Generation Plan card in the sprint session
Test Authoring AgentWrites test cases from the context it readsSprint and Adhoc sessions, and the review panel
Coverage AgentReports coverage per module, flags gaps, and scores readinessThe metric cards, and Insights and activity
Test Plan AgentBuilds test plans for generated test cases by reading your test case libraryThe Plans & Execution card
Healer AgentCorrects element locators that fail during a runRun results and Copilot sessions. See Healer
Analyzer AgentExplains failed steps, and reads execution results for patterns and risk signalsANALYZER VERDICT on run results, and Insights and activity. See Analyzer
Bug Reporter AgentRaises a failed run as a defect in your issue tracker, written up from the runRaise it as a defect on a run result. See Report a defect from a run

The Healer Agent corrects a failed locator during a run, so a renamed button doesn’t break a test case that is otherwise still valid. The Analyzer Agent surfaces recurring failures and risk signals in Insights and activity. The Bug Reporter Agent raises a failed run as a defect in your issue tracker, with the failed step named in the title and its screenshot attached.

Developer activity arrives on its own. Pull requests from connected repositories, and coding sessions captured by the Arcus plugins for Claude Code, Cursor, GitHub Copilot, and Codex, land in Context Management, along with test cases pushed from the CLI. Linking an entry to a sprint or an Adhoc session sends it to generation.

Install the plugins from Context Management (Install plugin beside each tool), or see Developers.

Was this page helpful?