> ## 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.

# Macro release evidence brief

> Assemble macroeconomic release values, revisions and definitions, such as US employment data, into a reviewable evidence brief and CSV with sources.

## Example

What did the original US Employment Situation release covering January 2025 report, and which earlier months did it revise?

**You get:** A release brief and CSV separating headline observations, prior-period revisions, survey basis and publication date.

## Gather the evidence

Locate the archived Bureau of Labor Statistics release and original tables. Keep establishment-survey payroll data separate from household-survey unemployment. A current series page may contain later revisions and is not a substitute for the original release.

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 release, period 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": "Prepare an evidence brief from the original BLS Employment Situation release covering January 2025. Extract the reported nonfarm payroll employment change and unemployment rate, their units and seasonal-adjustment basis. Extract revisions to prior months stated in that release as separate records. Preserve reference period and publication date. Do not use later revised series values, invent a consensus forecast or make a trading recommendation.",
    "mode": "standard",
    "research_strategy": "Locate and read the archived BLS release and its original tables. Distinguish establishment-survey payroll data from household-survey unemployment. If the original release cannot be retrieved, state that limitation rather than replacing it with a current series page.",
    "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": [
          "series_or_measure",
          "record_type",
          "reference_period",
          "release_date",
          "value",
          "unit",
          "seasonal_adjustment",
          "survey_basis",
          "revision_description",
          "source_url",
          "evidence_limit"
        ]
      }
    ]
  }
  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

* Reference period and publication date are distinct.
* Original values have not been replaced with subsequent revisions.
* Units and seasonal adjustment are correct; expectations are omitted unless supported by a dated source.

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.