Anima integrates patient requests, clinical documents and follow‑up tasks into a single platform that uses OpenAI models to help clinic teams respond faster. The company’s stated goal is personalized healthcare driven by need.
Scale and deployment
Anima launched in the United Kingdom and now serves more than 1,000 clinics and about 14 million patients, processing over 800,000 cases per month. The company is expanding into the United States, Australia and other markets.
Why OpenAI?
Shun Pang, Anima’s CEO and co‑founder, says the company selected OpenAI after benchmarking closed‑source and open‑source alternatives because of the models’ intelligence, intelligence‑per‑dollar and steerability via in‑context learning. The company uses GPT‑6 in its document pipelines and GPT‑Live for calls.
Pang’s clinical training influenced the product: he witnessed a case in which abnormal test results sat in a queue for six months, motivating him to tackle information flow rather than medical knowledge alone.
Andi: AI receptionist for phone intake
Anima’s AI receptionist Andi runs on GPT‑Live. Patients describe symptoms by phone while Anima’s proprietary policy engine guides the conversation through deterministic, clinically approved intake workflows. GPT‑5.4 mini selects the right questionnaire and the completed history appears as a structured case in the clinic dashboard.
According to Anima’s measurements, clinics using Andi have reduced phone wait times from 40–50 minutes to about 10 minutes — at least a 75% reduction. In patient surveys, 86% said they would use Andi again. Pang noted that people in their 80s and 90s were among the happiest users: “It’s infinitely patient and very polite.”
Documents: extracting and routing clinical paperwork with GPT‑6
Anima Documents uses GPT‑6 models to extract sender, recipient, document type and event dates from incoming clinical documents. A multi‑stage pipeline then matches each document to the correct patient, suggests clinical codes and proposes the next action for staff review.
Clinical coding was one of the more challenging problems. Michael Skupien, Engineering Lead at Anima, points out there are around 800,000 possible SNOMED codes; only a fraction are used regularly and different practices make different coding choices.
Rather than ask each clinic to configure the system or fine‑tune separate models per customer, Anima adapts model decisions to each practice via in‑context learning. This approach requires models that follow instructions consistently.
Anima reports that practices which previously processed about 15 documents per hour now typically handle 30–45 documents per hour, while top performers process 45–60 per hour. Pang says some clinics have cleared backlogs of more than 100,000 documents within days of adopting Anima, ensuring medication changes and updates reach clinicians promptly instead of languishing in queues for months.
Scribe: turning consultations into notes and follow‑ups
Anima’s Scribe product uses GPT‑5.6 Luna to convert consultation transcripts into structured clinical notes and then reuse that context to draft referral letters and patient follow‑up messages.
The result is that clinicians can spend more of the appointment listening rather than typing. Anima says consultation notes that once took several minutes to write are now drafted in seconds for clinician review, and referral letters that previously required 5–15 minutes can be drafted within seconds based on the consultation and patient record.
Pang says: “Patients receive clear follow‑up messages shortly after the consultation, reducing anxiety and improving recall. We often hear that doctors now finish their day on time instead of working until 8 or 9 p.m.”
Impact and outlook
Anima reports most cases on its platform are resolved within 24 hours, with a median resolution time of approximately 3.5 hours. Pang describes the platform as mission‑critical for the patients and clinics it supports across roughly 14 million UK patients using OpenAI models.
By automating intake, document processing and note drafting, Anima says it gives care teams more capacity today and helps build pathways and services for the future.
