AI Companion for OncologistsAI Companion for Oncologists

Oncologists' treatment decisions and patients' outcomes depend on their hospital's workflowOncologists' treatment decisions and patients' outcomes depend on their hospital's workflow

Survival rates differ significantly between global centers of excellence and local hospitals. Our thesis: close the outcomes gap by standardizing workflows and empowering oncologists to make the best treatment decisions.Survival rates differ significantly between global centers of excellence and local hospitals. Our thesis: close the outcomes gap by standardizing workflows and empowering oncologists to make the best treatment decisions.

Phase 1: I built a 0→1 web platform to standardize every oncologist's workflowPhase 1: I built a 0→1 web platform to standardize every oncologist's workflow

An EMR-style workspace where oncologists review complex cases: pathology, radiology, treatment science, and clinical impressions in one place. This was Hero's foundation, the structured data layer everything in Phase 2 would sit on top of.An EMR-style workspace where oncologists review complex cases: pathology, radiology, treatment science, and clinical impressions in one place. This was Hero's foundation, the structured data layer everything in Phase 2 would sit on top of.

Only 3% came back, so Phase 2 designed around what made them return: peer discussion, with an AI companionOnly 3% came back, so Phase 2 designed around what made them return: peer discussion, with an AI companion

Only 3% of onboarded oncologists came back. Across 10+ video interviews, one feature kept surfacing: Only 3% of onboarded oncologists came back. Across 10+ video interviews, one feature kept surfacing: Discuss withDiscuss with, pulling in peers for a second opinion, a scan read, or a transfer call. But they were doing it outside the product on local messaging apps where threads were , pulling in peers for a second opinion, a scan read, or a transfer call. But they were doing it outside the product on local messaging apps where threads were fragmentedfragmented, , slowslow, and , and unsafeunsafe. Phase 2 brought that peer loop on-platform with AI as the always-on companion, extending the web workstation into how oncologists work between cases and at the bedside.. Phase 2 brought that peer loop on-platform with AI as the always-on companion, extending the web workstation into how oncologists work between cases and at the bedside.

Oncologists open a case with the record already loadedOncologists open a case with the record already loaded

Oncologists used to paste patient info into their own AI chats just to ask a question. Hero pulls each case straight from the existing EMR into a structured data layer (pathology, radiology, treatment science), so chat can work across the full case the moment it opens. No upload, no setup.Oncologists used to paste patient info into their own AI chats just to ask a question. Hero pulls each case straight from the existing EMR into a structured data layer (pathology, radiology, treatment science), so chat can work across the full case the moment it opens. No upload, no setup.

Oncologists can ask anywhere across the patient recordOncologists can ask anywhere across the patient record

Chat sits on top of every section of the patient record, so oncologists can pull it up from anywhere they're looking and ask in context. AI synthesizes insights up front, the way oncologists already consult peers, so they can question, push back, and refine through conversation rather than structured forms.Chat sits on top of every section of the patient record, so oncologists can pull it up from anywhere they're looking and ask in context. AI synthesizes insights up front, the way oncologists already consult peers, so they can question, push back, and refine through conversation rather than structured forms.

Oncologists get AI answers backed by cancer specialistsOncologists get AI answers backed by cancer specialists

To make AI responses credible enough for clinical use, I partnered with eng to build an internal tool where in-house cancer specialists train our AI agents. Specialists review complex cases, correct outputs, and add their own insights, and that expert judgment feeds back as knowledge, prompts, and model weights, so every answer oncologists see is grounded in specialist review.To make AI responses credible enough for clinical use, I partnered with eng to build an internal tool where in-house cancer specialists train our AI agents. Specialists review complex cases, correct outputs, and add their own insights, and that expert judgment feeds back as knowledge, prompts, and model weights, so every answer oncologists see is grounded in specialist review.

Retention rose from 3% to 15%Retention rose from 3% to 15%

7-day retention rose from 3% to 15%, and conversation engagement (depth, reply rate, cases worked through in chat) confirmed oncologists weren't just opening the app but actively thinking through cases in it. Throughout, I ran regular sessions with a power-user group of oncologists to validate information architecture, conversation quality, clinical accuracy, and workflow fit.7-day retention rose from 3% to 15%, and conversation engagement (depth, reply rate, cases worked through in chat) confirmed oncologists weren't just opening the app but actively thinking through cases in it. Throughout, I ran regular sessions with a power-user group of oncologists to validate information architecture, conversation quality, clinical accuracy, and workflow fit.

Due to an NDA, I can't reveal more information. Please reach out to me via email (glimesong@gmail.com) for further details.Due to an NDA, I can't reveal more information. Please reach out to me via email (glimesong@gmail.com) for further details.