> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getthread.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Magic Analytics: Things to Know and Gotchas

> Key Magic Analytics caveats: daily data refresh lag, pre-aggregated topics without drill-down, PSA attribution limits for AI overrides and ticket closures.

A few important characteristics of Magic Analytics. Reading these first will save you confusion later.

### Data is about a day behind (not real-time)

Magic Analytics refreshes on a **daily cycle**, so it is **effectively one day behind**. Activity from today (tickets opened this morning, a call that just happened) generally appears the next day.

* Every query shows when it last ran — look for **"Query ran …"** with a date and time on each tile. On any tile, click the **⋮** (three dots) to see the date and time the last query ran.
* Use Magic Analytics for trends, performance, and value reporting — not for live, to-the-minute monitoring.

### It's a large dataset

Magic Analytics sits on a large volume of data. Most dashboards are fast, but the more you widen a date range or remove filters, the more work a query has to do.

<Tip>
  Set your **date range** and any **source / board** filters before digging in. Narrower questions return faster.
</Tip>

### Some topics are pre-aggregated (no drill-down to single rows)

To keep things quick, several topics are **pre-aggregated** — the data is rolled up in advance (for example, summarized by day, by customer, or by feature). That makes queries fast, but it means:

* You **can't drill down to an individual ticket, call, or session** from those topics, because the row-level detail isn't stored there.
* **Aggregate** topics include AI Accuracy, Value Realization, Magic Agent Rollup, Messenger, Service Team Performance, Inbox, and Planner.
* For row-level detail, use a **Detailed** topic such as **Threads** (one row per ticket), **Triage Agent** (per session), or **Voice AI** (per call).

See [*Topics you can explore*](/analytics/topics-you-can-explore) for the grain of every topic.

### Assistive AI: who gets credited for an override (attribution limitation)

The Assistive AI Accuracy dashboard tracks **exceptions** — cases where Thread's AI suggested a value and it was later overridden. There's an important limit on *who* we can credit for that override:

* When the change is made **inside Thread (Inbox or Pods)**, we can attribute it to the specific **member** who made it, along with a reason.
* When the change is made **directly in the PSA**, we **cannot** attribute it to a member. This is a **PSA API limitation around impersonation** — so those changes show up as **PSA / System attributed**.

<Note>
  A high share of "PSA / System" overrides usually means changes are happening in the PSA rather than in Thread — not that there's no human involved.
</Note>

### Who gets credited for closing a ticket (attribution limitation)

Magic Analytics can show **who closed a ticket**, but the same limitation applies:

* We can attribute the **closer** to a specific **member** only when the ticket is closed **from within Thread (Inbox or Pods)**.
* Tickets closed **directly in the PSA cannot be attributed** to the member who closed them — the same **PSA API limitation around impersonation** applies.

<Note>
  Treat closer / "closed by" metrics as a view of closures happening in Thread, not a complete record of every closure across your PSA.
</Note>

### Your PSA is the source of truth (potential for drift)

The numbers in Magic Analytics should track your PSA, but they can occasionally fall slightly out of step:

* Beyond the **daily lag** above, Thread stays in sync with your PSA through **webhooks and scheduled syncs**.
* If an integration isn't fully configured, or a webhook/sync is missed, some records can temporarily drift from what's in the PSA until the next sync reconciles them.

<Note>
  A roughly day-old difference is expected. A **materially** larger gap is worth flagging to Thread Help — and checking that your integrations are fully configured.
</Note>

### You only ever see your own data

Row-level security ensures every user only sees data belonging to your organization.


## Related topics

- [Magic Analytics FAQs](/analytics/faqs.md)
- [Dashboard Agent: query Magic Analytics in plain English](/analytics/dashboard-agent.md)
- [Getting Started with Magic Analytics](/analytics/getting-started-with-magic-analytics.md)