Context and starters

Integrity AI can summarize and connect the workspace objects you can access. Supported actions can also change product data when you explicitly request them. Review a proposed change before applying it; actions such as archiving a saved view require confirmation. See Manage Issue views with AI for the supported Issue-view workflow.

Every retrieval uses your current Integrity access. Private Teams, private Issues, unavailable objects, and deleted references remain behind the same permission and display-safety rules as the product. A later access change can also lock an older answer when you reopen its conversation.

Supported workspace context

Integrity AI has bounded readers for:

• workspace overview, Inbox, Meeting Minutes, Favorites, and recent Activity;
• Initiatives, Projects, Workspace Views, Teams, Triage, Issues, Team Projects, and Team Views.

Coverage is checked from an independent product-intent catalogue rather than from the tools that happen to exist. The release gate checks required read-only intents across the supported workspace areas. Deliberately unavailable intents are recorded explicitly rather than treated as silently covered.

It can answer exact caller-accessible counts where a narrow count reader exists, including Initiatives. For Initiative and Project collections it can also return a bounded browse result with the exact matching total reported separately from the number of displayed rows. Meeting Minutes support the same bounded collection behavior plus title search and scope, status, and Team filters. Selecting one Meeting can return display-safe Notes, attendees, linked context, transcript and correction context, AI summaries, action relationships, and lifecycle state when your current access allows it.

For a selected Project or Initiative, Integrity AI can show direct Blocked by, Blocking, and Related relationships. A detail answer previews up to five visible connections in each direction and reports each exact visible total. A follow-up can page through direct connections with a bounded result and continuation cursor. It does not follow the graph recursively or change relationships. A reference without a safe route is not cited as a link.

Integrity AI also reads each Project's Readiness, the same result the green check and the red blocked count show in your views. It can list the Projects that are Ready or Blocked and report exact totals for both. A Project is Ready when its status is in the Planned category and no blocker is open. See Readiness.

When you ask an agent that can create Projects to record an idea, it puts the Project in a Backlog status, because an idea is not yet committed work. It uses a Planned status only when you say the work is committed or ask for that status. See Backlog or Planned.

Collection browsing returns a bounded number of rows. When more objects match, Integrity AI states that the result is partial, reports how many were omitted, and asks you to narrow the request. It does not automatically page through the workspace, expose generic database queries, or send the whole workspace to a model.

Prompt starters

Try natural questions such as:

• “How many Initiatives can I access?”
• “List the names of those Initiatives.”
• “Tell me about the Initiatives in this workspace.”
• “Show active Projects related to verification.”
• “What is blocking this Project?”
• “Which Projects are ready to start?”
• “How many Projects are blocked, and by what?”
• “Which Initiatives are related to this one?”
• “Show my open Issues and summarize their priorities.”
• “List the Meeting Minutes I can access.”
• “Show the second Meeting’s Notes, attendees, linked context, and actions.”
• “Find archived Meeting Minutes about release readiness.”
• “What changed recently in the workspace?”

Use a follow-up when you want to narrow the result:

• “Only show active items.”
• “Search for thermal.”
• “Open the second result.”
• “Tell me about the second Project.”
• “Summarize its related Issues.”

How to read an answer

Exact counts are computed through access-aware readers and do not require listing every row. Browse and search answers are bounded, use stable ordering, and cite only returned objects that can safely be referenced. Zero results are kept distinct from unavailable, denied, or incomplete coverage.

Follow-ups perform a fresh access-aware read. If your access or an object's lifecycle changes between turns, the later answer reflects the current state instead of reusing stale names or content.

Limitations

• Integrity AI changes product data only through the supported actions you explicitly request, and does not perform remediation or approvals.
• It does not reveal hidden object names, routes, descriptions, membership, or restricted content.
• It does not provide an unbounded export or a generic cross-domain query.
• Some operations and transient/provider-owned data are deliberately unavailable; Integrity AI offers the nearest safe read or navigation path instead of inventing an answer.
• A cited historical answer can become unavailable after access or lifecycle changes.
• Answers should be treated as a navigation and synthesis aid; the cited Integrity objects remain the durable source of truth.