Content Health for Confluence
Confluence became your AI assistant's source of truth. It reads the runbook nobody has opened since 2023, and the two policy pages that disagree with each other — and answers with exactly the same confidence either way.
What it finds
Two runbooks disagreeing on how many approvals a deploy needs. A retention policy that says 30 days in one place and 90 in another. When two pages make incompatible claims, one of them is wrong right now — not "probably outdated", actually wrong.
You cannot find this by comparing dates, keywords, or titles, because contradictory pages usually share all three. It requires reading what the pages actually claim, which is why every other tool in this category stops at the six checks below.
The same procedure documented twice in different words — which is exactly why nobody noticed, and why only one of them ever got updated.
Not edited in over a year, still being read, still being cited in answers.
Nothing links to them. That used to mean nobody found them. Conversational search ended that.
Placeholders that quietly became permanent.
Pointing at pages that no longer exist.
Nobody's name is on them. When the answer turns out to be wrong, there is no one to ask.
Permissions
Content Health requests read-only permissions. It cannot edit, archive, move, or delete anything — not as a policy we promise to keep, but because the permissions required to do so were never requested. You can verify that on the listing's permissions tab before installing.
It reports what it found and stops. Every fix stays yours to make.
How it works
Age, links, word counts, and the link graph — across your whole page set, costing nothing.
Near-duplicate detection narrows thousands of pages to a handful of candidate pairs before anything expensive happens.
A nightly incremental pass looks only at what actually moved. Set it up once, then check the dashboard when you want to.
Early access
Scans your 300 most-recently-updated pages and shows you what it finds.
Built on Atlassian Forge. Your content is processed inside Atlassian's infrastructure. The only thing that ever leaves it: short excerpts of pre-filtered candidate page pairs, sent to Anthropic's Claude model through Atlassian's own first-party Forge LLMs API, and only when duplicate and contradiction detection is switched on.