[DOCS] Workflow docs omit `/deep-research` `unverified` result when verifier failures occur

Documentation Type

Incorrect/outdated documentation

Documentation Location

https://code.claude.com/docs/en/workflows

Section/Topic

The bundled workflow description for /deep-research.

Current Documentation

The workflows page describes /deep-research as:

"/deep-research <question> | Fans out web searches on a question across several angles, fetches and cross-checks sources, votes on each claim, and returns a cited report with claims that didn't survive cross-checking filtered out."

The page does not describe a separate "unverified" state when the verifier fails or cannot complete its check.

What's Wrong or Missing?

Claude Code v2.1.196 fixed /deep-research misreporting verifier failures as "all claims refuted" instead of unverified. The docs currently imply that claims that do not survive cross-checking are simply filtered out, but they do not distinguish between a claim being refuted and a verification process failing. Users reading a /deep-research report need to know that unverified means the verifier did not prove the claim false; it means the check did not complete or could not establish the claim.

Suggested Improvement

Update the /deep-research row or add a short note:

/deep-research separates refuted claims from claims whose verifier failed or could not establish a result. Verifier failures are reported as unverified, not as "all claims refuted".

This helps users interpret the report correctly and decide whether they should rerun the workflow or manually inspect the underlying sources.

Impact

Medium - Makes feature difficult to understand

Additional Context

Affected Pages:
| Page | Context |
|------|---------|
| https://code.claude.com/docs/en/workflows | Bundled /deep-research workflow behavior |

Total scope: 1 page affected.

Claude Code v2.1.196 changed /deep-research verifier-failure wording from "all claims refuted" to unverified.