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

# Earnings and guidance changes

> Compare reported earnings and management guidance changes across quarters with cited sources and a CSV, without mixing periods, metrics or accounting bases.

## Example

What changed between Microsoft fiscal Q3 and Q4 2025 earnings materials, and which outlook statements can actually be compared?

**You get:** A reported-results table and guidance-change CSV preserving the metric, forecast horizon, accounting basis and source statements.

## Gather the evidence

Locate both official releases and associated outlook statements or transcripts. Keep quarter results, prior guidance and new guidance separate. A forecast for a new quarter is not automatically a raise or cut to the previous forecast.

Use [Search](/api-reference/endpoint/search) and [Contents](/guides/content-extraction) if your application already handles the analysis. To generate the brief and CSV together, run the DeepResearch request below.

## Try it

Set `VALYU_API_KEY` in your environment. This is an illustrative request, not a saved result. Replace the company, periods or sources for your own task.

<Accordion title="Run the research request">
  ```bash cURL theme={null}
  curl --fail-with-body https://api.valyu.ai/v1/deepresearch/tasks \
    -H "x-api-key: $VALYU_API_KEY" \
    -H "Content-Type: application/json" \
    --data-binary @- <<'JSON'
  {
    "query": "Review Microsoft fiscal Q3 and Q4 2025 official earnings materials. Extract reported revenue and operating income for each quarter separately. Extract management guidance, preserving metric, forecast period, range, currency and qualifiers. Classify guidance as comparable revision, new forecast horizon, reiterated or not comparable. Do not call a change a raise or cut unless both forecasts concern the same metric and period. Mark missing prior guidance as unavailable.",
    "mode": "standard",
    "research_strategy": "Locate the two original investor-relations releases and associated outlook or transcript passages. Use SEC filings to corroborate reported actuals where needed. Do not mix annual totals with quarter figures or constant-currency growth with reported growth.",
    "report_format": "A concise evidence brief and comparison table. Cite each material finding, retain missing information and separate direct disclosure from interpretation.",
    "deliverables": [
      {
        "type": "csv",
        "description": "Populate the requested evidence fields with source references. Preserve unknown values and do not invent missing disclosures.",
        "columns": [
          "record_type",
          "metric",
          "reporting_or_forecast_period",
          "earlier_value",
          "later_value",
          "unit",
          "accounting_basis",
          "change_classification",
          "earlier_source_url",
          "later_source_url",
          "qualifier"
        ]
      }
    ]
  }
  JSON
  ```
</Accordion>

Save the returned `deepresearch_id` and [poll task status](/api-reference/endpoint/deepresearch-status). When `status` is `completed`, read `output` and download the CSV from `deliverables`; handle failed tasks separately.

## Check before using

* Fiscal periods and forecast horizons match the source.
* GAAP, adjusted and constant-currency measures remain separate.
* A raise or cut has comparable before-and-after statements; missing guidance is explicit.

Keep the accepted output and its evidence together in your analyst workspace. See [Research in your application](/guides/research-in-your-application) for integration details.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.