> 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/the-analyst/asking-questions.md).

# Asking questions

Type a question in the composer and press **Enter**. **Shift+Enter** adds a line without sending. Select the microphone to dictate instead of typing. Answers stream in as they are written, so you can read while the Analyst is still working.

An empty conversation shows **Trending questions** you can select to start.

## What the Analyst covers

**Company research.** Fundamentals, consensus estimates, earnings scorecards, valuation multiples (trailing, forward, and intraday), what is priced in, price targets, peers, insider transactions, and institutional ownership. When you have a company page open, the Analyst also reads Sterling's research brief on that company.

**Earnings and events.** Live and past earnings calls, corporate and economic calendars, splits and dividends, and the key debates around a stock.

**Comparisons and screens.** Rank or compare companies on a criterion you name. If you ask "by upside to target" or "by revenue growth," the ranking is bound to that criterion and the Analyst says so.

**Market data.** Prices and bars, trailing returns from one day to five years, moving averages, drawdown and correlation, market breadth and sector snapshots, movers, order-book detail, options chains and Greeks, put/call sentiment, futures curves, and prediction-market prices.

**News and commentary.** Buy-side publications, company blogs, central-bank communications, regulatory news, podcasts, social posts, and live web search. There is no toggle for web search; the Analyst reaches for it when Sterling's own sources do not cover the question.

**Macro and alternative data.** Economic series, futures positioning, and dozens of alternative datasets across energy, housing, transport, consumer, gaming, and technology.

**Unusual and political trading.** Large unusual prints and disclosed trades by members of Congress.

**Trade ideas.** Sterling's trade ideas by ticker, theme, or sector.

**Your portfolio.** Why it moved over a window. See [Explaining a move](/portfolio/explainer.md).

## Deep Research

Select the flask icon in the composer to turn on **Deep Research** for the conversation. The Analyst then produces a longer, multi-section report and splits the research across several parallel threads, each shown as a named Sterling analyst in the work panel. Their findings are folded into one answer. Deep Research takes longer and uses more of your balance than a standard question.

## What you see while it works

* **Thinking.** A running summary of what the Analyst is reasoning about and each lookup it makes, labeled in plain language with the ticker or term it is looking up. Lookups are grouped into Filings, Fundamentals, News, Markets, Macro, Alt-data, Web, and Compute.
* **Plan.** For a multi-step question, an ordered plan appears above the composer showing the current step. Expand it for detail. It disappears when the work is done; the record stays in the message.
* **Research threads.** In Deep Research, each parallel thread shows its name, step count, and the lookups it is using.

## Reading an answer

* **Citations.** Factual claims carry numbered source pills. Hover over a pill to see the source; open external sources from the hover card.
* **Tables and math.** Answers use tables where they help and render formulas properly.
* **Charts.** The Analyst draws charts inline: line, candlestick, bar, donut, waterfall, and more. Each chart card offers a table view of its data and a fullscreen view. Long daily histories are thinned so the chart stays legible.
* **Insufficient data.** When the data to answer is not there, the answer says so in a callout rather than guessing.
* **Follow-ups.** Every answer ends with two to four suggested follow-up questions. Select one to ask it.

## Calculations

For arithmetic (ratios, margins, growth rates, compounding, unit conversions, statistics) the Analyst computes exactly rather than estimating. For heavier work, such as reshaping a table or a multi-step computation, it carries out the computation and shows the result. Trailing returns quoted in an answer come from the same figures as Sterling's charts, so they match.

Dates in answers are computed in your browser's time zone.

## What the Analyst will not do

* Invent a figure or cite a source that did not return the data.
* Recommend an instrument you cannot buy. Recommendations assume a U.S. self-directed brokerage and U.S.-listed instruments unless you say otherwise, state that assumption, and name the exchange.
* Change your ranking criterion without telling you.
* Present past trade timing as a verdict on whether a trade was good or bad, or as grounds to suggest one.
* Read anyone's portfolio but yours.
* Keep your uploaded documents. See [Attaching files](/the-analyst/attaching-files.md).

A single answer can run for up to ten minutes. Deep Research answers usually take longer than standard ones. Accounts are limited to 100 messages an hour.


---

# 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/the-analyst/asking-questions.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.
