Automated lifecycle recommendations
Keeping a large documentation set healthy means constantly asking the same questions: What has gone stale? What needs re-verifying? Are two topics saying the same thing? The lifecycle agent asks these questions for you every night and turns the answers into a short list of concrete, actionable recommendations.
The agent recommends, it never edits. Every suggestion is something a human accepts, acts on, or dismisses. Topicary does not change your content automatically.
What the agent scans for
Each nightly run checks every topic against six signals:
Signal | What it looks for | Suggested action |
|---|---|---|
Staleness | Topics not updated within your staleness threshold | Update |
Verification expiry | Published topics never verified, or verified longer ago than your verification cycle | Verify |
Near-duplicates | Pairs of topics whose content is more similar than your duplicate threshold | Merge |
Low AI-readiness score | Published pages whose GEO (AI search readiness) score falls below your minimum | Expand or Split, depending on the weakest factor |
Orphans | Topics not in any map that are also stale (30+ days) | Archive |
Ambiguous topics | Topics in a gray zone (somewhat stale) where AI judges that action would help | Update, Verify, Split, or Expand |
Each recommendation carries the evidence behind it (the number of days, the similarity percentage, the weakest AI-readiness factor) so you can judge it before acting.
Where recommendations appear
Recommendations show in two places:
Project dashboard: a Lifecycle Recommendations section, grouped by action type.
Analytics > Content Health tab: the same list, alongside the content debt card and other health insights.
The most confident recommendations appear first.
Acting on a recommendation
Each recommendation card has two controls:
Dismiss: remove the recommendation if it is not worth acting on. Dismissing does not change any content.
Accept / open: for recommendations tied to a specific topic, this opens that topic so you can make the change yourself. For project-level recommendations (such as creating a missing topic), accepting marks the recommendation as resolved.
Because the agent never edits, accepting a topic recommendation is an invitation to do the work, not an automatic fix.
Recommendations are advisory. Dismissing or accepting one only updates the recommendation's status; it never publishes, deletes, merges, or rewrites content on its own. The actual edit is always yours to make.
Run a scan on demand
You do not have to wait for the nightly run. In both the dashboard section and the Content Health tab, use the refresh control to queue a scan immediately. The scan runs in the background and new recommendations appear when it completes.
Lifecycle Rules: tuning the thresholds
The agent's sensitivity is controlled per project by the Content health scans settings, found in project Settings. Only people can change these rules; the agent reads them but never writes them.
Setting | What it controls | Default |
|---|---|---|
Enable automated scans | Turns nightly scans on or off for the project | Enabled |
Staleness threshold (days) | How old a topic must be before it is flagged for update | 90 |
Verification cycle (days) | How often published topics should be re-verified | 90 |
Minimum AI-readiness score | Pages whose GEO score (from Analytics, AI search readiness) falls below this (0 to 10) are flagged | 5.0 |
Duplicate detection sensitivity | How much two topics must overlap to be flagged as duplicates. Higher is stricter and produces fewer flags | 0.92 |
Adjust a value, then click Save settings. The new thresholds take effect on the next scan.
If the agent produces too many duplicate flags, raise the duplicate detection sensitivity toward 1.0 so that only very close matches will be flagged. If staleness flags feel premature for content that genuinely changes slowly, raise the staleness threshold to match your real update cadence.
Turning off automated scans stops new recommendations from being generated but does not remove ones already created. Re-enabling resumes scanning on the next nightly run.
See also
Content debt score: The 0-10 score built from the same staleness, findings, verification, and gap signals
Track content freshness: Staleness indicators and human verification that the agent acts on
Content health and governance: How automatic health tracking surfaces decay before readers notice