Research software evaluation with AI

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.

Run the research request

cURL

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": "Evaluate openBIS and eLabFTW as components in a research workflow connecting strain identifiers, screening experiment records and fermentation measurement files. For each stage, distinguish documented native capability, documented integration and unsupported or unknown capability. Use official documentation, repositories and license files. Record edition and version when stated. Identify integration questions without inventing implemented features. Do not claim either candidate is a complete fermentation-control system or has industrial validation without specific evidence.",
  "mode": "standard",
  "research_strategy": "Prioritize project documentation, release notes, license files and documented APIs. Treat vendor deployment claims separately from independently published validation. Cite every row; mark missing or inaccessible evidence.",
  "report_format": "A concise evidence table, comparison limits and unresolved questions.",
  "deliverables": [
    {
      "type": "csv",
      "description": "One row per evidence item with the requested fields and supporting source URL.",
      "columns": [
        "candidate",
        "version_or_commit",
        "workflow_stage",
        "requirement",
        "support_type",
        "evidence_url",
        "license",
        "edition",
        "integration_gap",
        "verification_date"
      ]
    }
  ]
}
JSON

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

Write the required chain: strain identifier → screening experiment → fermentation run → measurement file. Assign explicit requirements to each step.

Read official versioned documentation, repository license files and interface specifications for each candidate. Separate community and hosted editions.

Record native support, documented integrations and unverified gaps per requirement. Hand the resulting matrix to engineers for a representative integration test.

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.

Start here

APIs

Finance workflows

Sciences workflows

Build and connect

Comparisons

Strain-to-fermentation software evaluation

Run with DeepResearch

How it works

Check the result

​Run with DeepResearch

​How it works

​Check the result

Run with DeepResearch

How it works

Check the result