Skip to main content
Example question: What did CodeBreaK 200 and KRYSTAL-12 disclose about previously treated KRAS G12C-mutated NSCLC by the end of 2024? You get: A two-trial landscape and CSV separating registered design from dated result disclosures, including abstract versus full-paper evidence. Start with: Interventions; population and line of therapy; phase; design; disclosure cutoff; required trial identifiers.

Run with DeepResearch

Set VALYU_API_KEY in your environment, then run this illustrative request. Change the question and CSV fields for your own task. The CSV fields below describe the requested output, not a saved result.
cURL
Save the returned deepresearch_id. Poll Get status until the task completes, then read the report and download the CSV from deliverables.

How it works

  1. Find registry records for CodeBreaK 200 and KRYSTAL-12. Extract design and identifiers with record access dates.
  2. Locate original result disclosures available by the cutoff. Label conference abstracts separately from full papers and post-cutoff publications.
  3. Join disclosures to trials using identifiers. Return separate rows for different disclosure dates and distinguish design metadata from reported results.
To build the workflow inside your own agent, use Search to find sources and Contents to read selected pages. Keep the CSV fields above as your extraction schema.

Check the result

Check trial identifiers and publication dates independently. An earlier conference disclosure and a later full paper are different evidence records. Review population, denominator and endpoint definitions before comparing any figures.