# Can an AI copilot help clinicians plan cancer workups?

> Color Health built an LLM-powered 'Cancer Copilot' to assist with the workup of patients newly diagnosed with cancer. Color reports more than 95% concordance with guidelines on a dataset of anonymized real-world patients at UCSF Health.

- **Evidence grade:** B — Named organization with a quantified outcome, from the vendor or the organization's own announcement.
- **Organization:** Color Health (healthcare provider / health tech)
- **Industry:** Hospitals & Health Systems — Virtual cancer care provider
- **Roles:** Clinicians & Clinical Ops
- **Tools:** Cancer Copilot (Color Health)
- **Status:** pilot · **Agent pattern:** copilot · **Autonomy:** 0/4
- **Last verified:** 2026-10-17

## Reported outcomes
- guideline concordance: > 95% on anonymized real-world UCSF Health patients [1] (self-reported)

## How it works
1. Extracts explicit decision factors from the patient record.
2. Applies declarative guideline logic to recommend workup steps.
3. Produces an explanatory summary with a reasoning chain and guideline references, designed for expert review.

## Risks & compliance
- Clinical decision support; not medical advice
- Evaluation was on a retrospective dataset

## Sources
1. Color Health, "Expertise Is What We Want" (2026-01-26) <https://www.color.com/blog/expertise-is-what-we-want/>
   > "The system achieved a high degree of concordance with guidelines (> 95%) on a data set composed of anonymized real-world patients at UCSF Health."

Canonical: https://agentcasefile.com/cases/color-health-cancer-copilot-workup/ · License: CC BY 4.0 (summary) · Source: Agent Casefile