> For the complete documentation index, see [llms.txt](https://docs.sterlinglabs.co/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.sterlinglabs.co/portfolio/explainer.md).

# Explaining a move

The Explainer answers one question: why did my portfolio move over this window? It splits the change into what the market did, what your style and industry exposures did, and what was specific to the holdings themselves, then names the holdings and sectors that mattered most and how the book compared with a fitting benchmark.

## Asking

1. On the value chart, drag across the window you want explained. A tooltip shows the start and end values and the change.
2. Select **Explain**.

The [Analyst](/the-analyst/analyst.md) opens with a card summarizing the window (range, dates, unit, value change), writes a short narrative, and renders the Explainer card below it. The first explanation of a window can take 20 to 40 seconds; asking about the same window again is quick.

The Explainer always describes the whole book, even if the chart was filtered or comparing when you asked.

## What the card shows

* **Factor attribution.** The move split into market, style, industry, and specific components, in dollars and percent, with the dominant driver named. Style factors are broad traits such as size, momentum, and value.
* **Top contributors.** Up to eight holdings ranked by their dollar contribution, each with its own return over the window.
* **Sectors.** Which sectors contributed and which detracted, as shares of the move.
* **Coverage.** How many holdings, and how much of the book's value, the analysis covers, with each uncovered holding listed and the reason it could not be included.
* **Versus benchmark.** The benchmark chosen, a one-sentence reason for the choice, how well the benchmark explains the book's moves (the fit), and the tracking error. A missing fit means the window was too short to measure it, not that the fit was poor.
* **Risk.** Total volatility, the share of variance specific to your holdings, and the share attributable to each factor group.

The narrative describes the move: its direction, the dominant driver, the comparison with the benchmark, the largest source of variance, the largest mover, how many trades fell in the window, and any holdings left uncovered. It does not give advice.

## Windows

The Explainer works on calendar windows. Windows shorter than 28 days that were not chosen deliberately, for example a window clipped by the start of your data, are widened to 28 days and the response says so. A window you chose deliberately, such as 7D, is kept, with a note that the benchmark fit and risk figures need more observations than it holds. Windows shorter than two trading days are answered with roughly the last month instead. History reaches back to May 2018 at the earliest.

## How the benchmark is chosen

The benchmark is picked by composition: the fund whose exposures most resemble your book's, from a list of twenty broad-market and sector funds. Funds you hold are excluded, and leveraged and inverse funds are never candidates. When nothing resembles the book closely enough, a broad market index is used and the reason says so.

## What is disclosed

The Explainer never folds an unknown into a number. Instead it tells you.

* **Coverage.** Uncovered holdings are listed with a reason: not yet in Sterling's data, no factor identity, no exposures available, not priceable, or not in U.S. dollars. Their value is disclosed, not treated as "specific."
* **Options.** Option positions have no factor identity of their own. They are listed as uncovered with a note, and the card states how any option sensitivities were measured.
* **Funds.** ETFs are looked through to their equity holdings. Bond and commodity funds stay uncovered.
* **"Specific" is a residual.** It is what the factors do not explain, not a score of stock-picking skill.
* **Holdings over time.** Where Sterling has your point-in-time holdings, the window uses them. Where it must project today's holdings backward across a window in which you traded, per-holding rows are withheld with a reason rather than shown wrong.
* **Partial sync.** If some accounts have not synced, the card says so before any figure.
* **Cash-only accounts.** A funded account with no positions gets a cash summary (balance, allocation, as-of date) and a note that deposits and withdrawals are flows, not gains. There is no factor attribution to show.
* **Young books.** Risk statistics are withheld for a book with too little history rather than computed from history the shares never had.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.sterlinglabs.co/portfolio/explainer.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
