AI Medical Chronology: Turning Thousands of Pages Into a Reviewable Chronology
I designed an AI Summarization tool that helps Medical Practitioners draft medical chronologies, which will be used by Insurance companies to pay for the plaintiffs affected in Personal Injury Cases: From weeks of manual medical record review to minutes spent refining a dependable first draft.
ROLE
Fractional AI Native Product Designer
RESPONSIBILITIES
Own product end to end from research, visual direction, building design system, and hand-off
team
Founder/AI Engineer
23 minutes
saved per medical visit
100%
manual drafting automated
5/5
chronology rating by user
context
Medical Practioners spend days combing through thousands of pages of medical records to manually build chronologies.
personal injury cases
In the USA, a personal injury - accident or medical mal negligence, is followed by medical treatment. The affected person is called Plaintiff. The person or entity causing it is called Defendant.
what is medical chronology ?
Post Medical treatment, the electronic medical records are manually drafted into medical chronologies and demand letters. These are used to assess the condition and extent of damage and the Plaintiff will be paid accordingly by the Defendant (his insurance - third party insurance).
weeks consumed in drafting a single chronology
Medical records for each case might range from 100s to 1000s of pages based on the duration of treatment undergone. The practitioners spend days to weeks to draft a single chronology.
Drafting a medical chronology takes about few days to weeks.
Can we build AI Native Product that helps cut short this to hours ?
Can we remove the manual grunt work involved in this ?
key product decisions
Ground AI output in source material
aisummarizationtool
/anderson/medicalchronology
Medchrono .
Dashboard
Medical Chronology
Search
3
of
367
Summarize
Medical Record: Patient Encounter Summary
Case Type: Alleged Medical Negligence – Delayed Diagnosis / Treatment Complication
Patient Information
Patient Name: Emily Carter
Date of Birth: March 14, 1982
Patient ID: MC-482917
Address: 1458 Willow Creek Drive, Austin, TX 78745
Insurance Provider: Horizon Health Insurance
Policy Number: HH-98217463
Medical Facility Information
Facility Name: Riverside Valley Medical Center (Fictional)
Department: Emergency Medicine
Address: 8200 Westlake Parkway, Austin, TX 78746
Attending Physician: Dr. Michael Reynolds
Specialty: Emergency Medicine
License Number: TX-MD-849302 (Fictional)
Nurse: Sarah Mitchell, RN
Medical Record Number: RVMC-2026-019283
Visit 1: Emergency Department Admission
Date of Visit: January 12, 2026
Time of Arrival: 8:42 PM
Chief Complaint
"Severe abdominal pain, nausea, and persistent vomiting for two days."
Patient Symptoms Reported
Lower right abdominal pain
Fever (101.8°F)
Loss of appetite
Nausea and vomiting
Difficulty walking due to pain
Initial Assessment
Vital Signs
Blood Pressure: 128/84 mmHg
Heart Rate: 104 bpm
Temperature: 101.8°F
Oxygen Saturation: 98%
Physician Notes
"Patient appears uncomfortable but alert and oriented. Abdominal tenderness noted. Differential diagnosis includes gastrointestinal infection, ovarian pathology, or possible appendicitis."
Diagnostic Tests Ordered
Laboratory Result
Anderson v. Westbrook Medical Center
Full Screen
Search
Olivia Rhye
olivia@untitledui.com
CHRONOLOGY
IMAGING
SETTINGS
RECENT CASES
Redo
Show visits
Search
Remove
Edit
Approve
Date of Visit
January 12, 2026
Facility
Riverside Valley Medical Center – Emergency Department
Austin, Texas
Doctors
Dr. Michael Reynolds – Emergency Medicine Physician
Sarah Mitchell, RN – Registered Nurse
Complaints
Patient presented with complaints of severe abdominal pain, nausea, and persistent vomiting lasting approximately two days.
Symptoms
Lower right abdominal pain
Fever (101.8°F)
Loss of appetite
Nausea and vomiting
Difficulty walking due to abdominal discomfort
Assessment
Patient appeared uncomfortable but was alert and oriented. Physical examination revealed abdominal tenderness. The physician considered multiple possible causes, including gastrointestinal infection, ovarian pathology, and possible appendicitis. A CT abdomen/pelvis was performed, which showed findings suggestive of possible early appendiceal inflammation.
Diagnosis
Suspected viral gastroenteritis. CT findings indicated possible early-stage appendiceal inflammation requiring clinical correlation.
Recommendations
IV fluids administered
Pain medication provided
Anti-nausea medication prescribed
Patient discharged with instructions to monitor symptoms and seek follow-up care if symptoms worsened
Link to Pages in Master PDF
Pages 1–6
Includes emergency department intake notes, physician evaluation, nursing documentation, laboratory results, CT imaging report, and discharge instructions.
January 12, 2026
Facility
Riverside Valley Medical Center – Emergency Department
Austin, Texas
Doctors
Dr. Michael Reynolds – Emergency Medicine Physician
Sarah Mitchell, RN – Registered Nurse
Complaints
Patient presented with complaints of severe abdominal pain, nausea, and persistent vomiting lasting approximately two days.
Symptoms
Lower right abdominal pain
Fever (101.8°F)
Loss of appetite
Nausea and vomiting
Difficulty walking due to abdominal discomfort
Assessment
Patient appeared uncomfortable but was alert and oriented. Physical examination revealed abdominal tenderness. The physician considered multiple possible causes, including gastrointestinal infection, ovarian pathology, and possible appendicitis. A CT abdomen/pelvis was performed, which showed findings suggestive of possible early appendiceal inflammation.
Diagnosis
Suspected viral gastroenteritis. CT findings indicated possible early-stage appendiceal inflammation requiring clinical correlation.
Recommendations
IV fluids administered
Pain medication provided
Anti-nausea medication prescribed
Patient discharged with instructions to monitor symptoms and seek follow-up care if symptoms worsened
Link to Pages in Master PDF
Pages 1–6
Includes emergency department intake notes, physician evaluation, nursing documentation, laboratory results, CT imaging report, and discharge instructions.
Previous visit
Next visit
List of visits
Since the stakes are high, the split screen lets users see the source document and the AI output simultaneously. This way the output can be mapped to source document.
Research on AI and LLMS
Turned insights into heuristics for building an AI Native Product
As i was acquainted with the domain, I knew the workflows and did chronologies myself to understand friction points and use cases
I also learnt about LLMs to understand the basics, constraints, and complexities.
Grounding & Trust
The source document should be available to check AI output
Human on the loop
AI drafts; the paralegal decides
Efficiency
The product should let frictionless completion of tasks
Stakes
Since the stakes are high, product direction has been guided by this principle
Human on the loop
We have preserved the human agency allowing users to approve, reject, and edit the outputs.
Redo
Show visits
Search
Remove
Edit
Approve
Date of Visit
January 12, 2026
Facility
Riverside Valley Medical Center – Emergency Department
Austin, Texas
Doctors
Dr. Michael Reynolds – Emergency Medicine Physician
Sarah Mitchell, RN – Registered Nurse
Complaints
Patient presented with complaints of severe abdominal pain, nausea, and persistent vomiting lasting approximately two days.
Symptoms
Lower right abdominal pain
Fever (101.8°F)
Loss of appetite
Nausea and vomiting
Difficulty walking due to abdominal discomfort
Assessment
Patient appeared uncomfortable but was alert and oriented. Physical examination revealed abdominal tenderness. The physician considered multiple possible causes, including gastrointestinal infection, ovarian pathology, and possible appendicitis. A CT abdomen/pelvis was performed, which showed findings suggestive of possible early appendiceal inflammation.
Diagnosis
Suspected viral gastroenteritis. CT findings indicated possible early-stage appendiceal inflammation requiring clinical correlation.
Recommendations
IV fluids administered
Pain medication provided
Anti-nausea medication prescribed
Patient discharged with instructions to monitor symptoms and seek follow-up care if symptoms worsened
Link to Pages in Master PDF
Pages 1–6
Includes emergency department intake notes, physician evaluation, nursing documentation, laboratory results, CT imaging report, and discharge instructions.
January 12, 2026
Facility
Riverside Valley Medical Center – Emergency Department
Austin, Texas
Doctors
Dr. Michael Reynolds – Emergency Medicine Physician
Sarah Mitchell, RN – Registered Nurse
Complaints
Patient presented with complaints of severe abdominal pain, nausea, and persistent vomiting lasting approximately two days.
Symptoms
Lower right abdominal pain
Fever (101.8°F)
Loss of appetite
Nausea and vomiting
Difficulty walking due to abdominal discomfort
Assessment
Patient appeared uncomfortable but was alert and oriented. Physical examination revealed abdominal tenderness. The physician considered multiple possible causes, including gastrointestinal infection, ovarian pathology, and possible appendicitis. A CT abdomen/pelvis was performed, which showed findings suggestive of possible early appendiceal inflammation.
Diagnosis
Suspected viral gastroenteritis. CT findings indicated possible early-stage appendiceal inflammation requiring clinical correlation.
Recommendations
IV fluids administered
Pain medication provided
Anti-nausea medication prescribed
Patient discharged with instructions to monitor symptoms and seek follow-up care if symptoms worsened
Link to Pages in Master PDF
Pages 1–6
Includes emergency department intake notes, physician evaluation, nursing documentation, laboratory results, CT imaging report, and discharge instructions.
Previous visit
Next visit
List of visits
Major explorations and dilemmas
Case management tool
Case centric features
The prototype pushed three different features - chronology and special reports as separate features. However, reports are an adjunct service. Hence the product was made case centric. From the same set of records, user could get the service needed - this way he has to upload records once.
Previously, users were expected to upload merged medical records. This meant, the tool was just a summarizer. However, the tool had to be a case management tool with all records in once place and there is a use case where continuing treatment would mean the chronology be updated. So it is now a case management tool
User onboarding
I initially designed an empty state, asking users to upload the records. However, this would mean, the user had to wait to see the output (latency) and also spend tokens.
To gain trust on the product, I decided to have a case with an AI output readily available - so a new user can explore the capabilities without having to spend tokens.
Dashboard
Medical Chronology
Click here to upload
or
Drag and drop
File format PDF, DOC Size 1 GB
Search
Filter Table
Special reports
Ask GPT
Summarize
Records
Page Count
Summarized on
Status
Previous
1
2
..
8
9
Next
Full Screen
Anderson v. Westbrook Medical Center
medlawgpt.com
/dashboard
Google .
Search
Olivia Rhye
olivia@untitledui.com
CHRONOLOGY
IMAGING
SETTINGS
RECENT CASES
Hello Sam ! Welcome
Add New Case
Favorites
Open cases
Closed cases
All cases
Add New Case
Welcome to MedLawGPT. Start by uploading your merged medical records
medlawgpt.com
/dashboard
Google .
Search
Olivia Rhye
olivia@untitledui.com
CHRONOLOGY
IMAGING
SETTINGS
Dashboard
Medical Chronology
Hello Sam ! Pick up where you left ...
Add New Case
Favorites
Tab Name
Closed cases
All cases
Search
Cases
Case owner
Date
Status
Previous
1
2
..
8
9
Next
medlawgpt.com
/dashboard
Google .
Search
Olivia Rhye
olivia@untitledui.com
CHRONOLOGY
IMAGING
SETTINGS
RECENT CASES
Optimize for MVP
deprecated features
Dashboard
Medical Chronology
Token cost for the users’ business ROI
Design for hallucinations, stakes, bias, assumptions, and cognitive surrender
If a feature like special reports is released, the user would use it. However, it is an adjunct service. Whether value from that service will match the token cost for the user is a questions. Coz the token cost cannot be shown upfront and user cannot make an informed decision.
If a feature like AskGPT, which is a chat interface is released. The user might over estimate the capabilities of an LLM. Example citations, hallucinations. So is the feature needed in first place is a question. Given the stakes are high, is building one with guardrails justfy the ROI ? Will this scale ? What about cognitive surrender of the user ?
REFLECTIONS
The Product is built - you design in the reverse
Tech debt is a given - justify token costs for any change
Product bulldozing - you remove features and bring it to MVP
Domain experience is the MOAT
Distribution can be a MOAT
I set up the design system to enable front end dev and screens were made AI readable.