AI analyst
A language model's reading of the last 30 days against the 30 before: what changed, why it matters and what to do next.
The AI analyst reads the workspace's last 30 days next to the 30 before and writes a short report: a headline, a summary, what stands out and what to do next. The page only exists when the dashboard has an AI provider configured; without one it is not in the sidebar.
Running it
Analyse my network starts a run. The page shows what it is reading — players, retention, peak hours, acquisition, the store, performance — and then the report. Analyse again replaces it.
- A run needs a few days of sessions; before that the page says there is nothing to analyse yet.
- One run at a time per workspace, and a waiting time between runs (six hours unless the dashboard sets another). The button says when it is available again.
- The report is written in the language of the member who ran it. Opened in another language, it says so and offers to run it again.
The report
| Part | Content |
|---|---|
| Health | Healthy, Mixed or Needs attention, with who asked for it, when, and which model wrote it. |
| Headline and summary | One sentence, then two to four. |
| What stands out | Three to six findings, each in an area (growth, engagement, retention, acquisition, revenue, performance, moderation, community), marked improving, getting worse or worth knowing, and linking to the page where it can be checked. |
| What to do next | Two to five actions, highest impact first, each tied to an area. |
The model is told to use only the numbers it is given, to cite them, and to give advice specific to a Minecraft network: when to run events, onboarding, vote and comeback rewards, lag on a named server, store bundles, moderation load.
What the model sees
Aggregates only: KPIs against the previous period, revenue, retention, momentum, growth accounting, comebacks, lifecycle segments, session lengths, the busiest hours, the top hostnames and countries, performance and uptime per server, moderation totals, and your annotations. It sees the workspace's name, timezone, currency and server names. No player names, UUIDs or IP addresses leave the dashboard.
Check the figures on the linked pages before acting on them: the report is written by a language model.
Who can use it
AI analyst (view_analyst). The report reads revenue too, so the seeded Viewer role does not have
it.
Something missing on this page? Tell us on Discord