InPractice vs Supio: how they compare in 2026
InPractice and Supio both read medical records for plaintiff firms, but one sells a single task and the other sells the case. InPractice turns records into chronologies and narrative summaries at about three seconds a page, lets a reviewer check each entry beside the source, and answers questions through Case Chat. A firm buys page packs online, from $150 for 1,000 pages, with no subscription. Supio covers a personal injury or mass tort case from intake to litigation. Its MedChron chronologies feed demand letters, case economics ledgers, litigation drafts and deposition analysis, Supio Agent takes instructions across a case, and human experts check bill totals and damages on high value cases. Supio connects to Litify, SmartAdvocate, CasePeer and MyCase and is sold after a demo, with no published price. Their paper differs too. Supio states SOC 2 Type II certification and publishes retention and hosting on a trust center, while InPractice publishes no terms of service. A firm that wants chronologies without a platform fits InPractice. A firm that wants one system behind every demand fits Supio.
Which one fits
Choose InPractice if
- You need chronologies, not a platform. InPractice does medical record review only, so there is nothing else to configure or pay for.
- You want to start today. Page packs are bought online with no demo or subscription, and a free trial covers 500 pages without a card.
- Volume swings from case to case. Packs run from $150 for 1,000 pages to $7,000 for 100,000, credits never expire, and every user on the account shares them.
- Reviewers edit before anything leaves. Each summary sits beside its source record, every entry can be changed, and exports go to Word, Excel or PDF.
- Medical examiners or insurers do the review. InPractice sells to independent and qualified medical examiners and to insurers as well as to firms.
Choose Supio if
- The demand is the goal. Supio runs from MedChron chronologies to demand letters with a page citation behind every claim, then on to case economics and litigation drafts.
- High value cases need a second check. Human experts verify medical bill totals and damage calculations before delivery.
- Your firm runs on a plaintiff case system. Supio connects to Litify, SmartAdvocate, CasePeer, MyCase, Smokeball, Jove and Neostella, and records sync from Dropbox, OneDrive, SharePoint, Box and Google Drive.
- You want an agent across the caseload. Supio Agent takes plain language instructions across cases, alongside Supio Intake and Case Communications.
- Peer results matter to your partners. Supio's customer stories name Phillips Law Group, Lundy Law, J.Chrisp Law and TorHoerman Law, with results such as more than 80 hours saved per case.
At a glance
All 15 axes, side by side
The same grid applied to every vendor in the index, graded from public sources. Hover a grade to see what the letter means on that axis.
AI Centrality
How much of the product is actually AI. Whether the machine learning is the mechanism the buyer is paying for or a feature layered onto conventional software, and whether the vendor is specific about which is which.
Every function is model output: chronology construction, narrative summarization, OCR search, duplicate detection and the Case Chat feature that answers questions against the record set. The product is billed per page processed, with no seat fee and no subscription, so a customer pays for inference directly. The vendor describes itself as specializing exclusively in medical record review rather than offering a broad legal AI platform. Without the models there is a file store with a search box.
Supio was founded in 2021 to build this product, with no earlier product to attach models to. CaseAware AI is named as its proprietary technology, described as distinguishing facts from opinions across large volumes of records, which is a claim about what the model does. Every deliverable is generated: chronologies from raw medical records, demand letters, case economics ledgers, litigation drafts and deposition analysis. Supio Agent, launched in the first half of 2026, is directed by natural language instruction rather than configured through forms, an agentic design rather than an assistant added to a case system. Without the models there is no product, only a connection to case management systems the firm already owns.
Citation Accuracy and Hallucination Disclosure
Whether the vendor publishes measured accuracy on citations and assertions, grounds output to primary sources, and says plainly what its system does when it does not know. Legal has a documented public record of fabricated citations reaching filed briefs, so an untested claim of accuracy is not evidence.
Chronology entries carry an outline view that jumps directly to the underlying source document, and a side by side review places each generated summary and chronology entry next to the original medical record for verification and editing. Export can optionally include the original records, so the chain from output back to source survives outside the platform. The vendor's published limitations state that the product requires human oversight for final verification and that AI generated content needs review. No accuracy figure, test set or evaluation is published; the one published number, three seconds per page, measures throughput.
Citations point to the page of the source document for any claim in a demand, and in medical records one treatment note in a 400 page file may be the evidence. For high value cases, human experts verify medical bill totals and damage calculations before delivery. No extraction accuracy, recall on treatment events, error rate on bill totals, or evaluation of CaseAware's separation of facts from opinions is published. Nothing says what happens when records are illegible, contradictory or incomplete. The one circulating figure, 80 or more hours saved per case, measures speed, not accuracy, and independent material reporting it notes that most such figures come from vendor marketing.
Autonomy and Oversight Model
What the system decides on its own, what a lawyer must approve, and whether the vendor documents where the review point sits. A tool that drafts under review and a tool that files without one are different products and different risks.
Generated summaries and chronology entries sit next to the original records in the side by side view, and every entry is individually editable before export, so the user controls what leaves the system. The vendor's published limitations state that human oversight is required for final verification and strategic decision making. Duplicate detection operates unattended and is described as hiding exact duplicates only. No threshold is published at which the system defers or flags low confidence, nothing describes what happens when an error survives review, and there are no terms of service in which a supervision obligation would sit.
For high value cases, human experts verify medical bill totals and damage calculations, so the human check targets the numbers that drive settlement. The agentic layer works on the attorney's explicit instructions. Published examples show the lawyer specifying what to emphasize and asking the system to recheck a medical bill total. Every output is presented as a draft with linked sources for checking. Nothing says what makes a case high value enough for expert review, what the experts check or against what standard, whether generated content carries any confidence signal, or what Supio Agent may do unattended once instructed.
Operational and Outcome Evidence
Named, dated evidence that the product works in production at real firms or legal departments. Case studies with figures and identified customers count. Unattributed testimonials and launch announcements do not.
Five testimonials carry both a person and an organization: Wayne Winders of Williams and Swee, Dylan Barket of Barket Lawyers, Simone Sacks of Orthopedic Expert Services, George Gluck MD of the Hand Center of Nevada, and Jaclyn Meeks of AmarilloMD, spanning the legal and medical examiner segments. Winders reports that case preparation time was cut by half and that demand letters improved because detail buried in hundreds of pages was no longer missed. The vendor separately claims use by hundreds of firms and organizations nationwide. The single figure is self reported, with no matter volume, period or method, nothing is dated, and no case study is published on the site.
Named firms report results on Supio's customer pages. Phillips Law Group reports settlement values up 17 percent and cases closing 26 percent faster, and Lundy Law describes a $25,000 case that became $250,000 while its demand output tripled. Paralegals at J.Chrisp Law report more than 80 hours saved per case on medical chronologies, and TorHoerman Law credits Supio in its $495 million verdict against Abbott Laboratories. D'Amore Law Group, Prince Law Firm, Galligan Law, Whitley Law, Rampart Injury Lawyers, Travis Law Offices and Welsh & Welsh are named as well. The stories give no method or measurement period for their figures. Supio has raised about $85m to $91m, including a $60m Series B in April 2025 led by Sapphire Ventures, and Thomson Reuters is both an investor and a partner.
Privilege and Confidentiality Posture
How client confidences are handled: attorney client privilege and work product treatment, segregation of one client matter from another, whether client data trains any model, and what the vendor commits to in writing rather than in marketing.
The privacy policy states in its second paragraph that it does not apply to protected health information processed on behalf of customers, which is governed by the business associate agreements InPractice has with its customers, and those agreements are not published. The input to the product is medical records, so the published policy covers account and marketing data. The security page states that customer information is never used to train AI models or shared with third parties, and describes 256-bit AES at rest, AES encryption in transit and multi factor authentication by SMS or TOTP. Nothing addresses privilege or work product, nothing describes separation between customers or matters, and no retention or deletion position is published. No model provider is identified, so what any underlying provider may retain is unstated.
The vendor states SOC 2 Type II certification and compliance with HIPAA, PHIPA and GDPR. PHIPA, Ontario's Personal Health Information Protection Act, governs health information custodians in Canada, and it is named alongside Canadian data centers, so a regional health privacy law is addressed beyond HIPAA. The platform holds complete medical records of injured claimants. Nothing addresses legal professional privilege or attorney work product, although demand strategy, case economics ledgers and litigation drafts are work product.
UPL and Professional Responsibility Posture
Whether the vendor is clear that it supplies a tool rather than legal advice, who its audience is, and how it addresses unauthorized practice of law, competence and supervision duties, and jurisdiction limits. ABA Formal Opinion 512 is the reference point. Where the advice line is not the duty a product raises, the axis is read through the nearest professional duty it does raise: judicial conduct rules and the reviewing duty for products sold only to courts, and the duty to bill for time actually spent for products that draft time entries.
The site publishes no terms of service, customer agreement or acceptable use policy: the navigation carries Product, Industries, Security, Pricing and Company, and the footer carries a privacy policy alone. Nothing states that output is not legal advice or not medical advice, and no attorney client or clinician patient boundary is addressed. The same product is sold to attorneys, to qualified and independent medical examiners who write expert reports, and to insurers adjusting claims, and its output is a medical chronology used to argue causation. The published limitations state that human oversight is required for final verification and strategic decision making, which concerns output quality rather than the advice boundary.
The platform drafts demand letters sent under the firm's name to adverse insurers, produces litigation drafts, and generates case economics that inform settlement advice to an injured client. Nothing published addresses the supervising attorney's duty over machine drafted advocacy, the professional responsibility dimension of relying on generated damage calculations when advising a client whether to accept an offer, or any bar guidance. The human expert verification tier is a quality control mechanism operated by the vendor rather than a statement about the attorney's own professional obligations.
AI Governance and Bias Disclosure
Published governance over model behavior: who owns it inside the vendor, what is tested before release, and what is disclosed about disparate output across matter types, parties, or populations.
No responsible AI statement, governance framework, named owner accountable for model behavior, description of evaluation before release or testing result is published. Nothing addresses bias: a chronology tool determines which diagnoses, gaps and preexisting conditions surface, and uneven performance across record types, providers or handwriting quality would change what a reader concludes about causation. The Vanta partnership named on the security page automates compliance monitoring for HIPAA, a security function.
Nothing is published about how the models are governed, evaluated or monitored: no AI policy, model card, bias or fairness testing, evaluation method or result, accuracy monitoring, drift statement, named governance body or ISO 42001. The product produces case economics ledgers and damage calculations that shape what an injured claimant is told their case is worth. Any systematic tendency in how the models weigh treatment, life impact or pain and suffering evidence would fall on claimants rather than on the firm, and nothing indicates it has been tested. CaseAware is named for separating facts from opinions in medical records, an interpretive judgment about clinical documents, and nothing indicates that judgment has been evaluated.
AI Safety and Data Stewardship
Retention, deletion, access control, and what happens to prompts and documents after they are processed. Whether the vendor states its subprocessors and its incident practice, or leaves the buyer to assume.
The privacy policy states that it does not apply to customer protected health information, the material the product processes. Published access controls are 256-bit AES at rest, AES encryption in transit and multi factor authentication supporting both SMS and TOTP. Infrastructure suppliers are named as AWS, Google Cloud Platform and Microsoft Azure, and Google Analytics and Google Ads are named in the privacy policy. No retention period is published for uploaded records, summaries or chat content, no deletion commitment or route exists, and no incident or breach notification practice is published. The privacy policy provides that personal information may be transferred, processed and stored anywhere in the world.
Retention is set out in Supio's trust center. Data is kept for a trial, typically about two weeks, or for the length of the agreement, then held for one year after the relationship ends for a possible return, unused, and deleted. Data is destroyed at the end of its retention period or on request, under ISO certified standards. Hosting is on Amazon Web Services and Azure in the United States, and data stays in its country of origin across data centers in the United States, the United Kingdom and Canada. The trust center, run on Vanta, shows controls for encryption, restricted key access, access control, penetration testing, disaster recovery, cybersecurity insurance and deletion of customer data on departure, and every employee passes a background check. No subprocessor list or breach notice practice is published, and nothing says whether submitted records train CaseAware.
AI Liability and Recourse
What the vendor stands behind contractually when its output is wrong. Indemnities, caps, carve outs, insurance, and whether any of it is published or only reachable through a negotiated agreement.
No terms of service, master subscription agreement, customer agreement or order form template is published; the navigation has no legal section and the footer's only legal link is the privacy policy. No indemnity, liability cap, warranty of any kind, service level or insurance position is published. The pricing page invites buyers to purchase page credits self-serve with a credit card. The business associate agreements referenced in the privacy policy govern data protection rather than liability for output, and are unpublished.
Nothing is published on liability for AI output, warranty, service levels or remedy. An understated medical bill summation or a missed treatment event flows into a demand and can settle a claim below its value. The person who bears that loss is the injured claimant, who is not a party to the contract between the firm and the vendor and has no visibility into how the number was produced. The vendor's own answer to this risk is operational, being human verification on high value cases, rather than contractual, and no contractual position is public.
Practice Systems Integration Depth
How deeply the product reaches into the systems legal work already lives in: document management such as iManage and NetDocuments, Word and Outlook, contract lifecycle management, matter management, e-billing, and court filing systems.
No case management system, document management system, medical record retrieval service, intake platform or electronic signature product is named, and there is no integrations page, API reference or developer documentation in the navigation or footer. Chronologies and summaries export to Word, Excel or PDF with a choice of fields, filters and layouts and the original records optionally included, which moves a finished document out of the platform; records arrive by upload. The vendor states that the product is not an EHR or EMR system.
Named integrations reach the systems plaintiff firms work in. Case management connections cover Litify, SmartAdvocate, CasePeer, MyCase, Smokeball, Jove (formerly GrowPath) and Neostella, and Litify and SmartAdvocate users can reach analyzed records and case intelligence from inside those systems. Records sync into Supio from Dropbox, OneDrive, SharePoint, Box and Google Drive, and Westlaw Advantage comes through a Thomson Reuters partnership. What each case management connection writes back, and what a firm must configure, is not documented.
Deployment Model and Data Residency
Where the software runs and where the data sits. Multi tenant cloud, single tenant, private deployment, on premises, and whether region of residence is a published option or an enterprise conversation.
Three cloud providers are named on the security page, AWS, Google Cloud Platform and Microsoft Azure, and no region, country or data center is given. Nothing describes whether the platform is single or multi tenant, and no dedicated, private or isolated option is offered at any tier. The privacy policy provides that all personal information processed may be transferred, processed and stored anywhere in the world, including but not limited to the United States or other countries with different privacy laws, for a platform whose stated market is the United States only and whose content is protected health information.
Cloud infrastructure runs on Amazon Web Services and Azure in the United States, with customer data stored in additional countries as needed. The security page says data stays in its country of origin, with data centers in the United States, the United Kingdom and Canada, each paired with its health privacy regime. No single tenant or dedicated option is described, and nothing says whether model inference runs in the same country as storage.
Security Certifications and Trust Center
Independent attestation a buyer can pull without a sales call: SOC 2, ISO 27001, penetration test summaries, a trust center with current reports and named scope rather than a badge image.
HIPAA compliance is claimed, and HIPAA has no certification scheme; the security page describes a partnership with Vanta, a compliance automation vendor whose product monitors controls, so the Vanta HIPAA badge evidences a monitoring subscription rather than an audit. No SOC 2 of any type, ISO certification, auditor, report date, scope statement or penetration testing is published, there is no trust center, and no report is offered at any access tier, including on request.
Supio states SOC 2 Type II certification and lists SOC 2, HIPAA and GDPR on a trust center run on Vanta, which shows its infrastructure, organizational, product and internal security controls under continuous monitoring. No auditor, examination period or report is offered there, and security questions go to an email address. HIPAA and PHIPA compliance are stated alongside GDPR, matching its data center countries.
Model Supply Chain Disclosure
Which models sit underneath, whose they are, where they run, and whether the vendor commits to telling customers when that changes. A legal buyer inherits every dependency it cannot see.
No model is named, no model provider is identified, no subprocessor list exists, no location is given for inference, and no commitment to notify customers of a change is published. AWS, Google Cloud Platform and Microsoft Azure are named on the security page as the cloud platforms the product runs on. The security page says customer information is never shared with third parties, and nothing says whether inference runs on a proprietary model or a third party one.
CaseAware AI is named and presented as the vendor's own technology, which is an ownership statement rather than a supply chain disclosure. No foundation model provider is named, nothing states whether third party models sit underneath CaseAware or process any part of the pipeline, and no subprocessor list is published. The Thomson Reuters and Westlaw Advantage integration establishes at least one external data relationship, and the stated three country data center footprint implies infrastructure providers, and none of those parties is identified. The platform processes protected health information across three regulatory regimes, and no processor is identified in public material.
Commercial Transparency
Whether a buyer can learn what this costs without entering a sales process: published rates, the unit being charged, what sits behind an enterprise tier, and what implementation adds.
Prices are public and sold in page packs, with no subscription and no per user charge. A pack of 1,000 pages costs $150 at $0.15 a page, 5,000 pages cost $600 at $0.12, 20,000 pages $2,000 at $0.10 and 100,000 pages $7,000 at $0.07, all bought self serve. Every pack includes unlimited users, chronologies, AI summaries, export, OCR and live support, and credits never expire and can be used across cases. Buying needs no sales call: a firm buys a pack and uploads records, and a free trial of 500 pages needs no credit card.
No pricing is published at any level. There is no price, no range, no unit of charge, and no indication of whether the model is per case, per seat, per page of records processed or per demand produced, which scale very differently for a plaintiff firm and determine whether the cost is a case expense or firm overhead. Independent review notes the product is sold entirely behind a demo with no published pricing. Every route is a sales conversation. Contingency fee firms advance case costs and recover them from a claimant's settlement, so per case pricing comes out of an injured person's recovery.
Firm and Practice Coverage
Who the product is actually built for. AmLaw, midlaw, small firm and solo, in house departments, government and courts, and which practice areas are supported rather than merely claimed.
Three buyer segments each have their own page: legal, medical examiners and insurance. Practice areas are named as personal injury, workers' compensation, medical malpractice and mass tort, and the medical examiner audience is identified as qualified and independent medical examiners scaling their practices. The vendor states what it does not do: it specializes exclusively in medical record review rather than general legal AI, it is not an EHR or EMR system, and it serves the United States market only. Firm size is not addressed, in house legal departments and government use are not mentioned, and nothing states a record volume limit or the document types the system cannot process.
The vendor says the platform is built only for plaintiff law and is of no use outside it, and independent review agrees. Within that scope it covers the whole case lifecycle: intake, medical chronologies, demand letters, case economics ledgers, litigation drafting, deposition analysis and firm analytics. Mass tort is named alongside personal injury, a different workload of thousands of claimants against common defendants. Nothing says which record types, providers or formats ingestion handles, what jurisdictions the litigation drafting covers, or how deep the mass tort support is compared with single plaintiff work.
The 12 legal signals, side by side
Recorded rather than graded. These are the questions a practitioner has to answer before a tool touches a client matter, and the answers are taken from public material only.
Client Data in Training
Can material a lawyer puts into this product be used to train a model?
The security page states without qualification that InPractice never uses customer information to train AI models or shares it with third parties, and that the data belongs to the customer, with no exception for deidentified or aggregated data. The statement sits on a marketing surface: the site publishes no terms of service, customer agreement or data processing agreement, and the privacy policy states that it does not apply to customer protected health information, pointing instead to business associate agreements that are not published.
Nothing published says either way whether medical records, case files, demand drafts or deposition transcripts submitted by firms train or improve CaseAware. The closest data handling statement, on the demand letter page, offers linked sources for any claims made in your demand, which concerns checking output rather than use of input. SOC 2 Type II, HIPAA, PHIPA and GDPR compliance describe how data is protected, not what it is used for.
The health information belongs to an injured claimant who is not a party to the contract between firm and vendor, so a training use they cannot see or object to differs from a customer consenting for itself.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
No retention period is published for uploaded records, summaries, chronologies or Case Chat content: the privacy policy has no retention section, the security page carries no retention statement, and there are no terms of service. No deletion commitment, deletion route or end of engagement position is published, and nothing states what happens to a case file once page credits are exhausted or an account goes dormant. Page credits never expire.
Supio keeps data for a trial, typically about two weeks, or for the length of the agreement. After the relationship ends it holds data for one year for a possible return, unused, then deletes it, and it destroys data earlier on request. No separate period is stated for agent instructions or generated drafts.
Ethical Walls and Matter Segregation
Does retrieval respect the firm’s ethical walls, or can the model read across them?
Nothing states whether the platform is single or multi tenant or how one customer's records are separated from another's. Within an account, credits can be shared across team members and used across cases, users are unlimited at every tier, and the privacy policy records that a customer may access information associated with a user's use of the Services, including the contents of files associated with that account. No role model, permission structure or matter level access control is described, and multi factor authentication is the only access control published.
No permission model, matter level access restriction or tenant segregation is described. A mass tort workload involves thousands of claimants against common defendants, often with multiple firms coordinating, and nothing published describes how one firm's claimant records and work product are separated from another's inside a platform serving the same litigation. Integrations exist with case management systems that hold their own permission models, and nothing states whether Supio inherits them.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
The privacy policy reserves the right to disclose personal information as required by law and where InPractice believes disclosure is necessary or appropriate to protect rights, property or safety, enforce policies or contracts, assist an investigation, or comply with a judicial proceeding, court order or legal process served on it. No commitment to notify the customer of such a request appears, and no discretion over notice is reserved either.
The policy states at the outset that it does not apply to customer protected health information, so this provision governs account and marketing data, and nothing published addresses compelled disclosure of the medical records. No transparency report is published.
Disclosure is allowed when Supio is compelled by law enforcement through a warrant, subpoena or court order, or to comply with valid government requests. No commitment to notify the customer first is made, and no transparency report is published.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
InPractice reads the medical records the customer uploads to a case and produces chronologies and summaries from them, rather than retrieving external content. No external database, publisher, clinical coding set or reference source is named, and no license basis is stated.
The platform works on the customer's own case files, medical records and transcripts rather than a published legal collection, so there is no outside legal source to name or license. Legal authority arrives through the Westlaw Advantage integration, whose content belongs to Thomson Reuters. Nothing says what CaseAware was trained on. Separating facts from opinions in clinical documents implies a large body of medical records, and nothing says whether it was licensed, synthetic, public or built from customer matters. No settlement or verdict database is named as a separate asset.
Good Law Verification
Does the product tell you when the authority it just cited has been overruled?
The product does not retrieve or present primary law: it summarizes and sequences the medical records supplied for a case, so no citator applies, and none is claimed.
The product writes litigation drafts and integrates Westlaw Advantage for legal research, so legal authority reaches its output. Whether cited authority is verified for current treatment before it appears in a draft, whether the Westlaw integration carries KeyCite treatment data or only citations, and whether an overruled or superseded case would be flagged are not stated.
Refusal and Uncertainty Behavior
What does the product do when the answer is not in the corpus?
The vendor's published limitations state that AI generated content needs review and that human oversight is required for final verification. No abstention path, no-answer state or confidence or grounding score surfaced to the reviewer is described, and nothing states how the system handles illegible handwriting, poor scans or gaps in a record set.
Nothing describes a no answer path, abstention behavior or confidence signal. CaseAware is named for separating facts from opinions in medical records, which is a sorting capability, not behavior under uncertainty. Nothing says what happens when a record is illegible, when two providers record contradictory findings, or when a gap in treatment cannot be explained from the file. Human verification on high value cases is a check after generation, not a behavior of the system, and it does not cover every case. Nothing indicates that a chronology built over an incomplete record would be flagged.
Fabricated Citation Record
Does a public court record exist addressing fabricated or hallucinated legal citations in output from this product?
The AI Hallucination Cases database kept by Damien Charlotin holds no entry naming InPractice or InPractice, Inc.
The AI Hallucination Cases database kept by Damien Charlotin holds no entry naming Supio. The platform generates litigation drafts filed with courts as well as demands sent to insurers.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions its buyers are bound by?
No bar association, regulator, rule of professional conduct or ethics opinion is named on the home page, security page, pricing page, privacy policy or AI information page, and there is no terms of service or acceptable use policy. A blog post cites American Bar Association survey data on the rate of AI adoption among legal professionals, as a source of statistics.
No named ethics opinion, ABA Formal Opinion 512, state bar guidance or engagement with professional conduct rules is published. The platform produces litigation drafts filed under an attorney's signature and case economics that inform settlement advice, both of which sit inside the competence, candor and supervision duties that bar guidance on AI addresses.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
Case Cost Statements are described as clear reporting of page usage and total spend per case, exportable to PDF to support internal tracking or case billing. The product is AI processing charged per page, so every figure on that statement records AI assisted work on that matter: the pages counted are the pages the model read. Nothing addresses how that cost should be disclosed to a client or described on an invoice, no guidance on fee treatment is published, and nothing addresses what happens to an hourly entry when review time falls from days to minutes.
The published figure is 80 or more hours saved per case when combining AI chronologies with demand letters, which describes the firm's own labor and has no baseline, sample or definition; independent material notes that most such figures come from vendor marketing. Nothing addresses the claimant's side. In contingency work the firm advances case costs and recovers them from the settlement. Nothing says whether platform cost is a case expense or firm overhead, how it is disclosed to the client, or what record could show how much of a demand was machine generated.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
No subprocessor list is published, no model provider is identified, and no data processing agreement, consent pack or notification template exists at any access tier. AWS, Google Cloud Platform and Microsoft Azure, named on the security page, are infrastructure. Business associate agreements are referenced in the privacy policy as governing customer protected health information, are not published, and no route to obtain one before contracting is described.
Four compliance regimes are named, SOC 2 Type II, HIPAA, PHIPA and GDPR, along with data center locations. No trust center, security page, request path for the SOC 2 report, subprocessor list, named model provider or business associate agreement material is published. Nothing published says which third parties process claimant health data.
Court Disclosure Support
If a judge’s standing order requires an AI disclosure, can the product produce one?
Chronology entries link to the underlying source document, and the side by side view pairs each generated entry with the original record. Export can optionally include the original records with the chronology, and Case Cost Statements record pages processed and spend for each matter. Nothing states that the model behind a given entry is recorded or disclosed, no exportable log of which entries a person edited or approved is described, and no disclosure guidance or template for a court or an opposing party is published.
Citations point to the page of the source document for any claim, so a party can show the exact page of a medical record behind a factual statement in a demand or litigation draft. For high value cases, human experts verify bill totals and damage calculations, so a verification step does occur. Nothing indicates that output records which model produced it, and no record of the human verification reaches the customer, so a firm cannot show the check happened even when it did. Litigation drafts bring this into the courtroom, not only the claim file.
The questions both sides leave open
Derived from the records above rather than written, so it cannot favor either vendor. Take these into both conversations and ask each side the same question.
- UPL and Professional Responsibility Posture
- AI Governance and Bias Disclosure
- AI Liability and Recourse
- Model Supply Chain Disclosure
- Ethical Walls and Matter Segregation
- Primary Law Corpus Provenance
- Good Law Verification
- Refusal and Uncertainty Behavior
- Bar Guidance Alignment
- Outside Counsel Guideline Readiness
In summary
InPractice
InPractice is a self serve medical record review tool from Goleta, California. A user uploads records to a case and gets a date ordered chronology and a narrative summary, with an outline that jumps to each source page. A side by side view supports checking and editing, alongside OCR search, automatic removal of exact duplicates and Case Chat for questions. Buyers are personal injury, workers' compensation, medical malpractice and mass tort firms, medical examiners and insurers in the United States. According to the AI Legal Index, page packs start at $150 for 1,000 pages with unlimited users, and InPractice states that it never trains AI models on customer information. The main caveat is the contract: no terms of service, liability position or retention period is published.
Supio
Supio, founded in Seattle in 2021, builds agentic AI for plaintiff personal injury and mass tort firms. Its MedChron chronologies, demand letters, case economics ledgers, litigation drafts and deposition analysis run on CaseAware AI, which separates facts from opinions in the record, and Supio Agent takes plain language instructions across a case. Every claim in a demand cites the source page, and human experts verify bill totals and damages on high value cases. Named customers include Phillips Law Group, which reports settlement values up 17 percent, and TorHoerman Law. According to the AI Legal Index, Supio hosts on Amazon Web Services and Azure, with data kept in its country of origin across the United States, the United Kingdom and Canada. The main caveat is price and paper: no price, model provider or customer agreement is published.
Questions buyers ask
How does InPractice compare to Supio?
Both build medical chronologies for plaintiff firms. InPractice stops at record review, with chronologies, summaries, side by side checking and Case Chat sold by the page. Supio carries the case from intake to litigation, adding demand letters, case economics, litigation drafts, deposition analysis and an agent, and connects to plaintiff case management systems. From the AI Legal Index, based on each vendor's own published materials as of November 16, 2026. No vendor pays for placement.
What do InPractice and Supio cost?
InPractice publishes page packs from $150 for 1,000 pages down to $0.07 a page for 100,000 pages, with no subscription and a 500 page free trial. Supio publishes no price or unit of charge, and buyers reach a price through a demo. From the AI Legal Index, based on each vendor's own published materials as of November 16, 2026. No vendor pays for placement.
Do InPractice and Supio train AI on client records?
InPractice states on its security page that customer information is never used to train AI models. Supio publishes nothing either way on whether submitted records train CaseAware. From the AI Legal Index, based on each vendor's own published materials as of November 16, 2026. No vendor pays for placement.
How do InPractice and Supio handle security and retention?
Supio states SOC 2 Type II certification, runs a trust center on Vanta, hosts on Amazon Web Services and Azure, keeps data for the agreement plus one year and deletes it on request. InPractice describes encryption, multifactor authentication and HIPAA compliance monitored through Vanta, and publishes no retention period or SOC 2 report. From the AI Legal Index, based on each vendor's own published materials as of November 16, 2026. No vendor pays for placement.
Which firms use InPractice and Supio?
InPractice serves personal injury, workers' compensation, medical malpractice and mass tort firms, medical examiners and insurers. Supio is built only for plaintiff personal injury and mass tort firms, and its customer stories name firms such as Phillips Law Group, Lundy Law and TorHoerman Law. From the AI Legal Index, based on each vendor's own published materials as of November 16, 2026. No vendor pays for placement.
Neither vendor paid for inclusion, placement or a grade, and neither reviewed this page before it published. Everything on it comes from public material on the dates shown. How the index grades.
Neither vendor names the model behind its chronologies or publishes an accuracy figure for them, and neither publishes a customer agreement with a liability position. InPractice publishes no terms of service or retention period for uploaded records. Supio publishes no price, subprocessor list or statement on whether submitted records train its models.