Chat
Volume, latency, error rate and satisfaction for Aria conversations — each tile carrying its own period-over-period delta, so a regression is visible before anyone reports it.
Adoption
68%
p95
4.1s
Errors
0.4%
Turns completed
12,480
+18.2%p95 latency
4.1s
−12.4%Error rate
0.42%
−0.31ppSatisfaction
92%
+4.1ppTurn volume
vs. previous 30d
Cost by feature
Verbatim
“It pulled the right brand comparison first try — this used to be a two-day ask.”
Every view is a live HogQL query against our own PostHog projects — no exports, no spreadsheets, no second copy of the data.
Volume, latency, error rate and satisfaction for Aria conversations — each tile carrying its own period-over-period delta, so a regression is visible before anyone reports it.
Adoption
68%
p95
4.1s
Errors
0.4%
Which generated opportunities got followed and which got rejected, scored against the relevance the model predicted.
Adoption of the add-in by what people actually do with it: chart inserts, bulk slides and the report templates they run.
Graded conversations, churn signals and topic trends — the sentiment and themes behind the counters.
“Saved me a whole afternoon of pivot tables.”
“It lost the thread when I switched brands.”
Who is active, what they touched and when they were last seen, filtered to real end users rather than internal traffic.
The weekly written read: what moved, why it probably moved, and what to look at next.
“Teams turns grew 18% this week, driven almost entirely by two Unilever brand teams adopting the add-in.”
No warehouse to stand up and no second copy of the data — the dashboard reads the PostHog projects we already collect into.
Aria emits typed events from every surface it runs on — the web app, the Teams bot, the Office add-ins. Nothing extra to install.
A protected oRPC procedure fans out a batch of HogQL queries against the PostHog project and maps the rows into one typed object. The PostHog key is read server-side and never reaches the browser.
The client calls that procedure through the typed oRPC + TanStack Query client, so the panel's types follow the handler's return value automatically.
SELECT toStartOfDay(timestamp) AS day,
count() AS turns
FROM events
WHERE event = 'ask_chat.turn_completed'
AND timestamp > now() - INTERVAL 30 DAY
GROUP BY day ORDER BY day DESC| day | turns |
|---|---|
| 2026-07-08 | 1,041 |
| 2026-07-07 | 972 |
| 2026-07-06 | 918 |
Runs server-side in a protectedProcedure
Chat, Social trends, PPT add-in, Quality, Reflect, Customers and more.
Chat and social on one project, the PowerPoint add-in on its own.
The PostHog key is read server-side and never bundled to the client.
Google sign-in, restricted to a.team accounts, sessions in Neon.
This dashboard sits on top of real customer conversations, so access is enforced in code rather than promised in a doc.
The PostHog key is typed server env, read only inside oRPC handlers. Nothing analytics-related is bundled into client JavaScript.
Every analytics call is a protectedProcedure, and /dashboard checks the session before it renders. There is no anonymous read path.
Sign-in is Google, restricted to a.team accounts. Everyone else bounces back to the login screen with an explanation.
The agent API never returns conversation excerpts from list endpoints, and raw transcripts are not reachable from it at all.
Sign in with your a.team Google account and the current week is waiting — no setup, no access request.