IntakeOS vs Reflekt Legal: how they compare in 2026
IntakeOS and Reflekt Legal both automate intake for law firms with AI and write the result into the firm's case management system, but they start at different doors. IntakeOS starts on the website. Chatbots and webforms capture the prospect, and Waypoint scores the finished intake against the firm's written criteria. Strong leads go to the firm's own agents through a live transfer queue, with the retainer signed in the same session. Reflekt Legal starts on the phone. Its AI receptionist answers every call in English and more than 15 other languages, runs the firm's intake script, then transfers, books, refers or takes a message. Outbound agents chase new leads, remind clients and call on past due invoices. Both sync to Clio, Filevine, Lead Docket and Litify. Reflekt Legal publishes its prices, from a free plan for 30 calls to $1,000 a month for 500, and IntakeOS is quoted after a demo.
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.
Waypoint is the model driven part of IntakeOS. It reads each completed intake and returns a numeric score, a breakdown by category such as case value, liability, evidence quality and urgency, a written summary and red flags. The criteria come from the firm, written in plain language in a criteria editor. Separate rubrics cover mass tort, workers' compensation and personal injury work, and prebuilt sets cover active torts such as Roundup and hair relaxer. Waypoint calls OpenAI with the firm's own API key. The intake chatbot runs on Microsoft Bot Framework and Azure Cognitive Services, and optional Whisper transcription turns recorded calls into text for quality review. A read only connector lets Claude answer staff questions about leads, scores, timelines and documents. Around the models sit branching forms, live transfer, electronic signatures, SMS and email nurture, referral tracking, MDL portfolios and CMS sync, all of which run without them. Case Compass calls the product an operating system for intake rather than a chatbot.
The product is a set of AI agents, sold as AI employees. An AI legal receptionist takes inbound calls, and AI legal intake runs structured screening. AI lead follow up calls, texts and leaves voicemail within seconds of a new lead, and AI outbound calling handles appointment reminders, intake interviews by phone, billing follow ups and status checks. Conversations run on a purpose built legal intake dialogue engine configured to each firm's script and qualification rules. OpenAI supplies the language model and ElevenLabs the synthesized voice, with Twilio carrying calls and texts. The same agents work over voice, SMS, WhatsApp, email and web forms, in English and more than 15 other languages, including Spanish, Arabic, Portuguese, Cantonese and French. Feature agents sit on top: conflict and jurisdiction screening, treatment tracking for personal injury clients, referral handoffs for cases the firm cannot take and collection calls on past due invoices. Without the models there is no receptionist and no intake to sell; the rest is routing and CMS sync.
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.
IntakeOS cites no legal authority and runs no legal research. Its legal content belongs to the firm: the branching questions and the Waypoint criteria, which can cover exposure windows, diagnoses and statutes of limitations. Waypoint's output is an assessment of a claimant's case, with a summary and flags that staff use to decide which leads to work first. No accuracy figure, error rate, test set or comparison against case outcomes is given for those assessments. A March 2026 release describes faster and more reliable scoring with better handling of edge cases, without a measure. Case Compass's own AI principles say models trained on patterns can miss unusual case types, edge fact patterns and jurisdictional nuance, and that AI can miss the human context behind an intake. Prebuilt tort criteria come from Case Compass, and only one set names a reference standard, NIH benchmarks for a uterine cancer screen. The chatbot's answers to visitors carry no accuracy statement either.
The agents talk to callers rather than cite law, so the accuracy question concerns what they capture and say. The home page describes callers being handled accurately and professionally because the engine follows the firm's script and qualification rules. No error rate, test set or evaluation of call outcomes backs that statement. Quality control is described as logging. AI inputs and outputs are logged for quality assurance and audit, and LLM interactions are traced in Logfire and LangSmith. Every call also produces a transcript and a recording that the firm can review. No legal authority is researched or cited, and the company states that it is software, not a law firm, and gives no legal advice. Nothing describes how often a caller is screened out in error or how transcription accuracy holds across the 15 or more languages offered. No step compares the summary written to the CMS with the recording of the call.
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.
The chatbot and webforms run unattended around the clock, and the firm's branching rules decide which questions each prospect sees and which leads move on. Waypoint applies the firm's criteria to every submission and presents the result for staff review. It does not accept or decline a case. Case Compass's design principle puts the firm's team in charge: full visibility, override authority and final judgment, with the decision to take a case never left to AI alone. The review points are concrete. Each score arrives with category reasoning and a written summary, and the full transcript stays on the lead. A live transfer queue shows every prospect waiting for an agent, and an agent can take over a bot conversation from the inbox. Automation also reaches the retainer. An April 2026 guide says a lead can go from intake to signed retainer without a person in the loop. When no agent is free, the platform can send the retainer for signature and book a callback. No point is set at which a person must review a lead before a retainer goes out; that depends on how each firm configures its timeline.
Calls are handled by AI from start to finish unless the firm's rules send them to a person. The firm defines the questions, the qualification rules and the handoff, and the agent applies them the same way on every call. Possible outcomes are a live transfer to firm staff, a booked consultation, a text or email, a referral or a message. Several checkpoints put a person back in the loop. Urgent calls are escalated to the firm's team. During conflict and jurisdiction screening the agent records parties, adverse parties, venue and matter type, and matters that need an attorney's eyes are flagged for review before a consultation is booked. Out of jurisdiction matters go to the firm's referral process. Collection calls route disputes to the firm's staff, and a whisper message briefs the staff member before a transfer connects. Review happens after the fact through transcripts, recordings and the summary in the CMS. No threshold is published at which the agent must stop and transfer a caller who is distressed or confused, beyond the firm's own routing rules.
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.
Case Compass reports three customer results for IntakeOS. Stern & Cohen reports a 75% chat to client conversion rate. McCune Law Group reports a 70% increase in conversions. An unnamed nationwide mass tort firm reports a 90% reduction in case acquisition costs. None of the three carries a date, a baseline or a measurement period, and each is labeled as a reported result that varies by implementation. Across the company, the platform has handled tens of thousands of intakes in mass torts, mass arbitration and personal injury. Waypoint is in use for mass tort, workers' compensation, personal injury and landlord and tenant matters, and the active campaigns named include Roundup and personal injury mass torts. The Clio app directory still lists the product under the Gideon name, describing matter creation in Clio Manage with chat conversations saved as documents. The product lineage runs to February 2017, when Gideon launched; its founder presented it at a Stanford CodeX meeting that May.
Three named firms speak for the product on dedicated customer pages, each with a named person. Chris Earley of Earley Law Group describes about a year of use. Ghassan Shamieh, managing partner of Shamieh, Shamieh & Ternieden, runs a San Francisco immigration firm with about 15 legal staff. He describes routed calls replacing a phone load that interrupted client meetings and court preparation, with callers served in Spanish, Arabic, Portuguese, Cantonese and French. Debbie Ames, COO of Fears Dudley Injury Law in Texas, describes a single receptionist covering several entities before the switch, and now reads transcripts and listens to recordings in place of call volume reports. The accounts are qualitative. None gives a conversion rate, a count of answered calls or a before and after figure, and none is dated beyond the length of use. The home page carries general claims about higher response rates from dormant leads and more cases signed, with no method or customer attached, and an ROI calculator.
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.
No customer agreement or data processing addendum is public, so the confidentiality position comes from the security page, the privacy policy and product posts. Waypoint sends intake data to OpenAI under the firm's own API account, so claimant data does not flow through Case Compass's AI infrastructure. Case Compass says that data never trains a shared or third party model, is never pooled with other customers' data, and that the firm keeps audit rights over its own OpenAI account. Requests are isolated to each customer account, and staff reach leads through role based access. Intake forms, signed retainers and case notes count as client data entered by the firm under the privacy policy, and the firm can ask for that data to be deleted. The policy also keeps a right to build aggregated, anonymized insights to improve the platform. Privilege and work product are not addressed, nor is the treatment of a prospect's account when the firm declines the matter. The chatbot runs on Microsoft's Azure services, and nothing covers what Microsoft keeps from those conversations.
The Terms of Service, updated 10 March 2026, carry a customer data clause that reaches the portal and related services. The firm keeps all rights to its data. The company takes a limited right to access, use, process, store and transmit it only as needed to provide, operate and improve the services under the firm's instructions. It will not sell that data or use it for any other purpose unless the law requires. The security policy, last updated May 2025, says OpenAI processes customer data transiently during intake conversations and does not use it to train or fine tune models under Reflekt Legal's enterprise API agreements. The FAQ adds that firm and client data does not train public models and that retention limits follow the firm's own policy. Data access is scoped by project membership, so users cannot reach data from projects they do not belong to. Privilege and work product are not addressed, and nothing describes how a prospective client's confidences are handled when the firm cannot take the matter and the agent refers it to a partner firm. The services themselves run under a separate executed agreement that is not public.
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.
Case Compass's statement on AI treats the decision to take a case as a legal and business judgment. AI can inform it with scores, flags and summaries, the statement says, and should never make that call alone. The same page says a fully automated experience can feel cold to people seeking help, and that a handoff to a person at the right time matters. That position concerns the firm's own decision. Nothing addresses what the chatbot may tell a prospective client about the merits of a claim, or whether visitors are told they are talking to software. Supervision of the scripts and criteria that drive each conversation by the firm's lawyers is not addressed either. Agent scripts can carry the compliance disclosures a firm writes for each practice area, and those words are the firm's. No bar rule or ethics opinion on advertising, solicitation, prospective clients or AI use is named. No published terms say who may use the product or set its limits, and no jurisdiction is named.
The product's limits are stated plainly. A reference page says it is software, not a law firm, and gives no legal advice. It sells to law firms, does not refer members of the public to counsel and is not a human answering service. Calls are handled by AI, with live transfer to firm staff when the firm's rules call for it. The conflict and jurisdiction feature keeps legal judgment with the firm. It captures parties, adverse parties, venue, matter type and dates, flags matters for attorney review before a consultation is booked and sends out of area matters to referral. The supervision side is not covered. Nothing describes whether callers are told they are speaking with AI, and one customer page quotes a caller who thought she was talking to a real person. No bar opinion on AI, solicitation, prospective clients or nonlawyer assistants is named, and nothing addresses how a firm supervises scripts in different states. Service is limited to the United States and Canada.
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.
Under the heading of its approach to AI, Case Compass sets out where it thinks AI helps and where it does not. The help column covers speed at volume, consistent screening, pattern recognition and routine logistics. The shortfall column covers nuance and context, novel situations, final case decisions and client trust. The stated design principle is human in the loop as the architecture, with transparent scores, configurable criteria and nothing treated as a black box. No owner, review body, release testing, monitoring or bias evaluation sits behind those principles. Waypoint applies the same written criteria to every claimant, which Case Compass presents as a consistent and defensible standard. No review of how scores fall across claimant groups, case types or languages is offered. Age based rules, added in March 2026, let criteria screen claimants on an age computed from date of birth, for case types with age eligibility requirements. No guidance on how firms should use them accompanies the feature. ISO 42001 and the EU AI Act are not mentioned.
No AI policy, responsible AI principles, model evaluation, bias testing or named owner for AI decisions is published. The controls Reflekt Legal describes sit in its security policy. LLM interactions are traced in Logfire and LangSmith for audit and performance monitoring, and AI inputs and outputs are logged for quality assurance. Personal data sent to the model is limited to names, contact details and conversation content. The agents decide which callers reach a consultation and which go to referral, in many languages. No review of how screening outcomes differ by language, accent or caller group is offered, and nothing describes testing before a new practice area script goes live. ISO 42001 and the EU AI Act are not mentioned.
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.
Case Compass hosts IntakeOS on AWS with all data in United States data centers and least privilege access to infrastructure. Data in transit uses TLS 1.2 or later, data at rest uses AES 256 encryption, and keys rotate on a regular schedule. Users sign in with multifactor authentication and see only what their role allows. Backups run daily with point in time recovery and are kept for 30 days, encrypted. Lead access, intake submissions, user changes and API calls are logged and kept for compliance review, with no log retention period given. A privacy policy effective 1 January 2025 keeps information as long as needed to provide the service, meet legal duties and resolve disputes, and lets a firm ask for client intake data to be deleted. Data about minors gets heightened controls, collection limited to what the service needs and parental review and deletion rights. No subprocessor list is public beyond the providers the security page names, and no incident response or breach notice commitment appears.
The security policy covers most of the ground in specific terms. Data in transit uses TLS 1.2 or higher and data at rest uses AES 256 on Google Cloud. Passwords are hashed with bcrypt, sessions use signed tokens with expiry, roles are scoped to projects, and every query checks project membership before returning data. Login attempts and lead lifecycle events go to dedicated audit tables. A subprocessor table names Google Cloud, OpenAI, Twilio, SendGrid, ElevenLabs, Stripe, Sentry, Cloudflare, DocuSign and Clio, each with its purpose. A documented incident response procedure covers identification, containment, eradication, recovery and review, and vulnerabilities are fixed within 7 days for critical and high severity, 30 for medium and 90 for low. Retention is the softer part. The privacy policy, updated 12 May 2026, keeps personal information as long as needed for the service, answers verified deletion requests within 30 days and deletes Google tokens within 30 days of disconnection. Intake retention follows the firm's policy with no default period, and breach notice follows applicable law with no stated window.
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.
Case Compass offers no public customer agreement, terms of service or service level commitment for IntakeOS. The website has no terms page, and the privacy policy is the only legal document linked from it. No warranty covers chatbot answers or Waypoint scores, and no indemnity, liability cap or remedy is set out. The rebrand note tells existing customers that their agreement with Case Compass is unchanged, since the contracting entity is the same, and that agreement is private. A firm learns how loss is allocated, including for a prospect turned away by its own criteria or a retainer sent without review, only in a negotiated contract. On risk, the privacy policy carries only a statement that no system is completely secure and that Case Compass cannot guarantee absolute security.
The public Terms of Service, governed by Texas law with courts in Travis County, provide the website, portal and related services as is and as available. They disclaim all warranties, including accuracy and fitness for purpose, and exclude liability for damages of any kind arising from use. The firm indemnifies Reflekt Legal, and the firm warrants that it holds the rights, notices and consents needed for the client data it puts through the service. The lead conversion services themselves run under a separate signed agreement that is not public, so any cap, indemnity or service level commitment for missed or mishandled calls is negotiated. The Stripe fulfillment policy makes every purchase final, with no refunds or credits for partial use, downgrades or unused time. Monthly plans can be cancelled at any time, which is the main remedy described.
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.
Signed cases and intake data move one way, from IntakeOS into the firm's systems, and the integrations page says what each connection carries. Litify receives practice areas as case types, marketing campaigns, the originating URL, lead status, intake answers and Waypoint scores, with webform leads labeled as such. Filevine matters receive intake answers, lead status, attribution and scores. Lead Docket receives new leads with full answer mapping, scores and referral partner attribution. In Clio, an accepted intake can create a matter in Clio Manage with fields mapped, contacts sync to Clio Grow, and chat conversations are saved as documents. HubSpot, Zapier, CallRail and RingCentral connect as well, and a WordPress plugin and a JavaScript embed place forms inline on any site without an iframe. Setup steps are spelled out for RingCentral, from dial mode to inbound number and call recording, but not for the case management connections. Leads export to CSV, and the Claude connector offers read only access through an MCP endpoint at api.casecompass.io.
The agents work inside the firm's existing systems rather than a separate dashboard. Integration pages cover Clio and Clio Grow, Filevine, Lead Docket, Litify, MyCase, Smokeball, SmartAdvocate, Neos, CASEpeer, Lawmatics, Law Ruler, Lawcus, Backdocket and Docketwise. LawPay, Vinesign, Salesforce, HubSpot, Calendly, Cal.com, Google Calendar, Outlook, Slack, Teams and Google Drive are covered too. The Clio and Filevine pages list what the agent does. It creates and categorizes contacts, updates contact details in real time and creates follow up tasks, or new Filevine projects with fields filled. It attaches transcripts, signed forms and documents to the client record and updates lead and matter statuses. During a call it can look up existing matters to answer with context, so data moves both ways. Clio connects through OAuth 2.0 with PKCE. Setup is handled by Reflekt Legal, which reviews the firm's configuration and trains the agent on it in one to two days. Field mappings and what the firm itself must configure are 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.
IntakeOS runs as a hosted service on AWS, with all data stored in United States data centers. Firms reach it in the browser at app.casecompass.io, and intake forms embed in the firm's own website. Processing happens in more than one place. Chatbot conversations run through Microsoft Bot Framework and Azure Cognitive Services, with no Azure region named. Waypoint sends intake data to OpenAI under the firm's own account, so processing location and retention at OpenAI follow the firm's own agreement with OpenAI. Optional Whisper transcription also runs through OpenAI. No single tenant, private cloud or on premises option is offered, and no region outside the United States. Users outside the United States may have their information transferred to and processed in the United States, according to the privacy policy.
Reflekt Legal runs on Google Cloud as two separate deployments, one for the United States and one for Canada, each with its own database and infrastructure and its own app address. Production runs in containers built from patched base images and deployed as infrastructure as code. Calls to outside providers go to region appropriate endpoints where the provider supports them. OpenAI handles the language model, ElevenLabs the voices and Twilio the calls and texts, and the policy does not say where each processes Canadian traffic. Canadian personal information is handled under PIPEDA and United States data under state privacy laws such as the CCPA. No single tenant or on premises option is offered, and nothing changes between plans on where data sits. Service is offered only in the United States and Canada.
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.
No SOC 2 report, ISO 27001 certificate, penetration test summary or named auditor is offered for IntakeOS or for Case Compass, and there is no trust center. The security page cites AWS's SOC 2 Type II certification for the hosting layer. That is Amazon's attestation for its own infrastructure rather than an audit of Case Compass. The controls themselves are described in prose, among them TLS 1.2 or later in transit, AES 256 at rest, rotated keys, multifactor authentication, role based access, audit logging and encrypted daily backups. Case Compass invites a firm's IT team or compliance counsel to contact it for a walkthrough of its security posture, with no report or questionnaire offered in advance.
No SOC 2 report, ISO 27001 certificate, penetration test summary or named auditor is offered, and there is no trust portal. In place of an attestation, the company publishes a detailed security policy, last updated May 2025. It covers hosting, encryption, authentication, role based access, tenant isolation through project membership, SQL injection protection, input validation, rate limiting, pinned dependencies, error monitoring and remediation timelines by severity. Security researchers can report vulnerabilities by email. The engineering lead's background in red team work and bot detection at Cloudflare appears on the about page. None of this is independently audited.
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.
Three providers are named. Waypoint uses OpenAI through the firm's own API key. Whisper from OpenAI handles optional call transcription for quality review. Microsoft Bot Framework with Azure Cognitive Services carries the chatbot conversations. Because the firm supplies the key, Waypoint traffic is governed by the firm's direct agreement with OpenAI, and the firm can see what was sent, audit usage with OpenAI and revoke access. No model family or version is named for Waypoint or the chatbot. AWS hosts the platform. RingCentral carries calls when a firm connects its own account. Nothing commits Case Compass to notifying customers when a provider or model changes, and no subprocessor list exists to track such a change.
OpenAI is named as the language model provider for every AI feature, and ElevenLabs as the provider of voice synthesis. Twilio carries calls and texts, and both appear in the published subprocessor table with Google Cloud, SendGrid, Stripe, Sentry, Cloudflare, DocuSign and Clio. OpenAI processes conversation data transiently, under enterprise API terms that exclude training and fine tuning. LLM calls are traced through Logfire and LangSmith. No model family or version is named, and the dialogue engine on top is described only as purpose built for legal intake. Nothing commits Reflekt Legal to notifying customers when a model or subprocessor changes.
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.
IntakeOS is priced after a demo. No price, plan name, tier or unit of charge is public, so nothing shows whether cost follows seats, leads, conversations or signed cases. A few terms of the deal are described. Onboarding is included: the Case Compass team builds the first intake flow and the Waypoint criteria, and most firms go live within a week. RingCentral calling uses the firm's existing RingCentral plan with no added licensing from Case Compass. Some features are described as available on all plans, but no plan is named. Case Compass's 2026 intake guide quotes general market ranges for intake software, from $50 a month for simple tools to $500 to $2,000 or more for full platforms, without placing IntakeOS in either. Dwellex, the company's landlord and tenant product, carries public per case pricing that does not apply to IntakeOS.
Prices are public and the unit is the call. A free Solo plan costs $0 and includes 30 calls a month with transfers and scheduling. Base is $500 a month for 250 calls, with multilingual support and routing through the firm's CMS or CRM. Growth is $1,000 a month for 500 calls and adds outbound lead follow up, payments taken by phone and referral network help. Calls above the allowance cost $2 each. A yearly commitment takes 10% off Base and Growth, which brings them to $5,400 and $10,800 a year. Enterprise adds long interviews, complex qualification logic, multistep intake, outbound calling and dedicated onboarding, with terms set in a quote. There are no setup fees and no long term contract, and every tier is available month to month. Inbound service can go live in a day and outbound in two to five days after business verification. Payments made by card are final, with no refunds for partial months. A comparison page sets Reflekt Legal's flat monthly plans against per minute and per call answering services.
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.
IntakeOS is built for high volume plaintiff firms. Personal injury, mass torts and MDL campaigns, mass arbitration, class actions, workers' compensation and consumer litigation are the named practices, and the intake guide adds social security disability. Waypoint ships with prebuilt criteria for active torts and supports custom rubrics for any plaintiff case type. Mass tort firms group claimants into named MDL portfolios with lead counts, score distributions, status breakdowns, deadline tracking and plaintiff fact sheet mapping. Referral partners, including cocounsel and marketing partners, get their own portal. The product sits between marketing and case management and replaces neither, so firms are expected to keep a CMS such as Litify, Filevine or Clio. Every named market is plaintiff work, and defense, transactional and in house use are not mentioned. No jurisdiction limits are given. Landlord and tenant practices are served by a separate Case Compass product, Dwellex, and specialty medical practices by Torvana.
The product is sold only to law firms, of any size, that miss calls after hours, during hearings or at peak volume. The named fit is high intake practices such as personal injury, family law, criminal defense and immigration. Defense firms taking assignments from carriers, administrators and employers are named too, as are firms serving clients who need intake in their own language. Practice pages cover 22 areas, among them mass tort, medical malpractice, social security disability, workers' compensation on both sides, insurance defense, subrogation, employment, bankruptcy, estate planning, elder law, real estate, intellectual property and business law. Mass tort pages describe screening claimants on product, exposure dates, injury type and prior settlements during campaign spikes. The limits are stated. The company does not serve consumers looking for a lawyer, anyone seeking legal advice, firms that want human answering, businesses outside law, or buyers of a general chatbot or drafting tool. Service is limited to the United States and Canada.
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 says claimant data sent for Waypoint scoring goes to OpenAI under the firm's own account and never trains a shared or third party model. The February 2026 Waypoint launch post repeats the point: no pooling with other customers' data, and no use by Case Compass for training or model improvement. The commitment sits in policy pages, since no customer agreement is public. The privacy policy separately keeps a right to build aggregated, anonymized insights to improve the platform.
Nothing covers chatbot conversations handled on Microsoft's Azure services. A firm can see what data is sent for evaluation, audit usage directly with OpenAI and revoke the key at any time. The Claude connector is read only, and Case Compass says connector credentials are authenticated by Case Compass and never shared with Anthropic.
The security policy says OpenAI processes customer data transiently during intake conversations and does not use it to train or fine tune models, under Reflekt Legal's enterprise API agreements. Its FAQ answers that firm and client data does not train public models. The Terms of Service limit use of customer data to providing, operating and improving the services and bar its sale, without mentioning training either way.
The no training position therefore sits in policy pages. AI inputs and outputs are logged for quality assurance, and nothing says whether those logs are used to tune Reflekt Legal's own dialogue engine. Personal data sent to OpenAI is limited to names, contact details and conversation content.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
Retention is acknowledged without a period. The privacy policy keeps information only as long as needed to run the service, meet legal duties and resolve disputes, and a firm can ask for its client intake data to be deleted. Backups are kept for 30 days. Transcripts, call recordings and Waypoint summaries stay on the lead record, and audit logs are kept for compliance review, with no period for either. Prompts sent to OpenAI under the firm's key follow the firm's own OpenAI settings.
Signed retainers attach to notification emails and stay downloadable from the client portal. Individuals can ask for access, correction, deletion or portability of their data under the privacy policy, and minors' data can be reviewed or deleted at a parent's request.
Retention follows each firm's policy, with no default period stated. The privacy policy keeps personal information only as long as the service needs it or the law requires, then deletes or anonymizes it, and answers verified deletion requests within 30 days. Google tokens are deleted within 30 days of disconnecting. Transcripts, recordings and AI inputs and outputs are kept for quality assurance and audit, and logs go to Google Cloud Logging for retention, with no period given for any of them.
Copies written into the firm's CMS follow the firm's own retention. Card payment data is handled by Stripe under its own terms, and calendar data created through Reflekt Legal is kept for the life of the account.
Ethical Walls and Matter Segregation
Does retrieval respect the firm’s ethical walls, or can the model read across them?
Role based access controls limit each user to what their role needs, and the Claude connector returns only the data a staff member's own account can reach. Referral partners see only the leads they sent. Waypoint requests are isolated to each customer account. No matter level wall, conflict screen or hold on a new intake until a conflicts check runs is described, and live transfer sends prospects to any available intake agent with the transcript attached.
Agent scripts are assigned per intake form, and supervisors see every agent's queue and callbacks. Each staff member who connects Claude signs in with their own credentials, so connector answers follow that person's access.
Reflekt Legal keeps its own permission model and describes how it is enforced. Users hold roles such as Manager or Support scoped to specific projects, routes check those roles, and every database query joins against project membership before returning data. Within a firm, matter level walls are not described, and the agent can look up existing Clio matters and Filevine projects during a call. A conflict and jurisdiction step captures parties and adverse parties and flags matters for attorney review before booking.
Clio connects through OAuth 2.0 with PKCE, and tokens are stored and refreshed by the platform. Non fit callers are introduced to the firm's referral partners automatically.
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 lists legal compliance as a ground for sharing information when law, regulation or valid legal process requires it. The information it covers includes the case and client data firms enter, such as intake forms, signed retainers and case notes. No commitment to tell the firm before or after a disclosure appears, and there is no transparency report. Waypoint data held in the firm's own OpenAI account falls under the firm's agreement with OpenAI.
The same section allows transfer of information in a merger, acquisition or asset sale and sharing with hosting, payment and analytics providers under confidentiality agreements, and says Case Compass does not sell personal information.
The privacy policy uses information to respond to subpoenas and court orders, to cooperate with law enforcement and government investigations and in legal proceedings, and allows sharing in response to legal process. It applies the same exception to customer data, and the Terms of Service except uses required by law from the limit on customer data. No commitment to notify the firm appears, and there is no transparency report.
The policy also warns that data stored in the United States may be reachable by United States agencies, courts or law enforcement. The Terms of Service and privacy policy are governed by Texas law. Canadian data sits in a separate Canadian deployment, and no position on cross border requests is stated. The policy names no step for the firm to object before data is produced.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
IntakeOS does not answer legal questions from a body of law. Its legal content is the firm's own intake questions and Waypoint criteria. Prebuilt criteria for active mass torts come from Case Compass, and one set screens for uterine cancer and fibroids against NIH benchmarks, with no source or update schedule given for the others. Plaintiff fact sheet templates are loaded from the court filed document for each MDL. Statute of limitations, exposure window and diagnosis rules inside Waypoint carry no citation to the law or study behind each rule, whether the firm writes them or they come from a Case Compass tort set.
Reflekt Legal's agents do not answer legal questions from a body of law. They run the firm's own intake script and qualification rules, with practice area templates such as mass tort criteria on product, exposure dates, injury type and prior settlements. No source is given for the practice area templates, and nothing describes how jurisdiction rules used in screening are kept current. Treatment tracking for personal injury clients records appointment outcomes reported by the client, not medical records. Nothing describes who writes or reviews the practice area scripts before a firm adopts them.
Good Law Verification
Does the product tell you when the authority it just cited has been overruled?
IntakeOS produces no citations to case law or statutes, so no citator is involved. Waypoint criteria can include statute of limitations rules that the firm writes, and nothing describes how those rules are kept current when limitation periods or tolling rules change. Plaintiff fact sheet exports follow the field order of the court filed form for each MDL, which Case Compass loads from the docket. MDL portfolios track discovery cutoffs, expert disclosure dates, bellwether trials and fact sheet deadlines that the firm records.
The agents cite no case law or statutes, so no citator is involved. Jurisdiction screening checks where an incident happened and where the caller lives against the areas the firm serves, using rules the firm supplies, and nothing describes a check of limitation periods against current law. Matters outside the firm's territory are sent to its referral process rather than assessed on the merits. The agent writes intake facts to the CMS for attorney review without legal analysis.
Refusal and Uncertainty Behavior
What does the product do when the answer is not in the corpus?
Nothing describes what the chatbot says when a question falls outside its script or when it cannot answer. A prospect can ask for a live agent by phone, chat or form, the request lands in the transfer queue with the transcript attached, and an agent can take over a bot conversation. Waypoint raises the red flags a firm defines, and claimants see a status message while their case is being evaluated. Case Compass's AI principles name novel situations and nuance as weak spots for AI without tying them to a product behavior.
When no agent is free, the firm's configured workflow decides the next step, such as an electronic retainer or a scheduled callback. Leads that do not clear the firm's rules move into SMS and email nurture sequences rather than a closing message.
Reflekt Legal describes several points where the agent hands off instead of deciding. Urgent calls are escalated to the firm's team, and matters that need an attorney's eyes are flagged for review before a consultation is booked. Out of jurisdiction matters go to referral, and disputes on collection calls go to staff. The firm's routing rules decide when a caller is live transferred, and a whisper message briefs the staff member first.
No published evaluation shows how reliably the agent recognizes when it should hand off, and nothing describes what it says when a caller asks a question the script does not cover. Callers can be served in their own language, and the agent hands the call to staff whenever the firm's rules require it.
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 maintained by Damien Charlotin, which records court decisions worldwide that address hallucinated AI content and the tool involved where known, has no entry naming IntakeOS, Case Compass, Waypoint or Gideon Legal. IntakeOS writes intake conversations and case scores for a firm's own staff rather than court filings.
The AI Hallucination Cases database maintained by Damien Charlotin, which records court decisions worldwide that address hallucinated AI content and the tool involved where known, has no entry naming Reflekt Legal or Lead Autopilot. Reflekt Legal's agents talk with callers and write intake records rather than court filings.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions its buyers are bound by?
Case Compass refers to law firms' ethical and regulatory obligations around client data, and says Waypoint was built so that using AI adds no new compliance exposure for a firm. Agent scripts can carry the compliance disclosures a firm writes for each practice area. No ABA opinion, state bar opinion or advertising rule is named, including the solicitation and prospective client rules that apply to live transfer and chatbot intake.
Referral fees to cocounsel and other referral partners are tracked in the product, and no fee sharing rule is mentioned beside them.
Reflekt Legal refers to professional responsibility in general terms. Its reference page states that it is software, not a law firm, and gives no legal advice, and that it does not refer members of the public to counsel. The conflict check and jurisdiction step reflects conflict rules without citing them. No ABA opinion, state bar opinion or rule on AI, solicitation, prospective clients or nonlawyer assistance is named.
The one American Bar Association link on the site concerns client intake and retention rather than ethics guidance. Firm branded collection calls and caller disclosure of AI are not tied to any conduct rule.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
IntakeOS works before an engagement exists. It closes intake with a prefilled retainer for electronic signature, and the fee terms in that retainer are the firm's own. Referral fees owed to referral partners are tracked as pending or paid in the referrals module. Savings claims face the firm's own costs, such as a 90% cut in case acquisition cost at a mass tort firm and higher chat to client conversion, and no client bill is involved.
Retainers are prefilled from intake answers and can bundle several documents in one signing step. Unsigned retainers trigger SMS reminders, and signed copies download from the client portal.
Most of the product works before an engagement exists, but two features reach the lawyer and client fee relationship. AI collection calls, branded as the firm, call clients on past due invoices and retainers, route disputes to firm staff and put every call on the file. The Growth plan also takes payments by phone through LawPay. Nothing addresses how those calls should describe fees, what clients are told about the AI making them, or any rule on fee collection.
The marketing claims face the firm's own intake costs rather than a client's bill. Intake itself sits before any engagement, and the firm's own retainer terms govern fees.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
No subprocessor list, data processing addendum or disclosure pack is public. The security page names AWS for hosting, Microsoft Bot Framework and Azure Cognitive Services for chatbot conversations and OpenAI for Waypoint. It invites a firm's IT team or compliance counsel to contact Case Compass for a walkthrough of its security posture. The privacy policy refers to hosting, payment processing and analytics providers bound by confidentiality agreements without naming them. No security questionnaire, insurance certificate or audit report is offered in advance.
The public security policy lists each subprocessor with its purpose. Google Cloud hosts, stores and logs, OpenAI processes language, Twilio carries calls and texts and SendGrid sends email. ElevenLabs supplies voices, Stripe takes payments, Sentry monitors errors, Cloudflare runs DNS and CDN, DocuSign handles signatures and Clio is the practice management integration. The same policy describes encryption, access control, tenant isolation, incident response and remediation timelines.
No data processing addendum, audit report or questionnaire is offered publicly. Security questions and vulnerability reports go to a published security contact.
Court Disclosure Support
If a judge’s standing order requires an AI disclosure, can the product produce one?
Each lead keeps its chatbot transcript, intake answers, call recordings and Waypoint score with its written reasoning, and the platform logs lead access, submissions and user changes. Leads export to CSV with scores and individual intake answers as columns. Mass tort firms can export plaintiff fact sheet data in the court's field order from a mapped intake. Nothing records which model produced a score, and no export is tied to a court's AI disclosure rule.
MDL portfolio dashboards show AI scored lead counts, average scores and score distributions for each litigation. Call recordings and optional Whisper transcripts attach to the lead profile beside the agent's notes and disposition.
Every call leaves a transcript, a recording and a structured summary with the qualification outcome and what happened next, written to the firm's CMS or CRM. AI inputs and outputs are logged, and lead lifecycle events go to audit tables with timestamps. Nothing records which model version handled a call, and nothing ties these records to a court's AI disclosure requirements. Summaries record the caller's details, the matter type, the practice area answers, whether the matter met the screening criteria and the outcome of the call, in the same fields for every call. Recordings and transcripts can be played back and read from the firm's records, as one customer's COO describes.
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.
- Security Certifications and Trust Center
- Primary Law Corpus Provenance
- Good Law Verification
Which one fits
Choose IntakeOS if
- Most of your leads arrive through your website and paid campaigns. IntakeOS captures them with chat and branching forms and scores each one before staff open it.
- You keep a human intake team and want it fed in order. The live transfer queue, RingCentral softphone, scripts and speed to lead dashboards are built for agents.
- You run mass tort campaigns. Tort specific criteria, MDL portfolios and plaintiff fact sheet exports are part of the platform.
Choose Reflekt Legal if
- Your missed calls are the problem. Reflekt Legal's AI receptionist answers every call, day and night, and transfers or books under your rules.
- Your callers speak many languages. The agents run intake in English and more than 15 other languages, including Spanish, Arabic and Cantonese.
- You want the price before the demo. Plans are published by the call, with a free tier, no setup fees and month to month terms.
In summary
IntakeOS
IntakeOS is Case Compass's intake platform for high volume plaintiff firms, formerly sold as Gideon. Chatbots, webforms and live transfer capture each prospect, and Waypoint returns a score, a category breakdown, a written summary and red flags against criteria the firm writes, running on the firm's own OpenAI key. According to the AI Legal Index, retainers are signed in the same session, mass tort claimants can be grouped into MDL portfolios, and the platform runs on AWS in the United States. Case Compass says intake data never trains a shared model. Pricing is quoted after a demo.
Reflekt Legal
Reflekt Legal, formerly Lead Autopilot, sells AI employees that answer a law firm's phones and run intake around the clock in English and more than 15 other languages. Each call ends in a live transfer, a booked consultation, a referral or a message under the firm's rules, with a transcript, recording and summary written into the CMS. According to the AI Legal Index, prices are public: a free plan for 30 calls a month, Base at $500 for 250 calls and Growth at $1,000 for 500. It runs on OpenAI and ElevenLabs, hosted on Google Cloud in separate United States and Canadian deployments.
Questions buyers ask
IntakeOS vs Reflekt Legal: chat or phone?
IntakeOS is built around website chat, webforms and live transfer to the firm's own agents. Reflekt Legal is built around an AI that answers the phone, and it also follows up by text, voicemail, WhatsApp and email. Many firms take leads both ways, and both products write to the same case management systems. From the AI Legal Index, based on each vendor's own published materials as of October 12, 2026. No vendor pays for placement.
How much do IntakeOS and Reflekt Legal cost?
Reflekt Legal publishes its plans. The free plan covers 30 calls a month, Base costs $500 a month for 250 calls and Growth $1,000 for 500 calls. Each extra call is $2, and a yearly commitment takes 10% off. Enterprise is quoted. Case Compass quotes IntakeOS after a demo, with onboarding included. From the AI Legal Index, based on each vendor's own published materials as of October 12, 2026. No vendor pays for placement.
Who decides which cases the firm takes?
Both leave the decision with the firm. Waypoint scores each intake for staff review, and Case Compass says AI should never decide case acceptance alone. Reflekt Legal applies the firm's qualification rules, flags matters for attorney review before booking and sends out of area matters to referral. From the AI Legal Index, based on each vendor's own published materials as of October 12, 2026. No vendor pays for placement.
Where does the data sit?
IntakeOS runs on AWS in United States data centers, with chatbot conversations on Microsoft Azure services and Waypoint calls going to OpenAI under the firm's own key. Reflekt Legal runs on Google Cloud in separate United States and Canadian deployments and lists its subprocessors, including OpenAI, ElevenLabs and Twilio. From the AI Legal Index, based on each vendor's own published materials as of October 12, 2026. No vendor pays for placement.
Is IntakeOS the same product as Gideon?
Yes. Gideon Legal became Case Compass, which later renamed its intake platform IntakeOS without changing logins, data or contracts. The old gideonlegal.com address now carries unrelated content. From the AI Legal Index, based on each vendor's own published materials as of October 12, 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.
Both products talk with prospective clients before a lawyer does, and neither describes telling them they are speaking with AI. Neither names a bar rule on solicitation, prospective clients or AI use. Reflekt Legal's AI collection calls also reach clients about unpaid fees. IntakeOS was sold as Gideon before its company became Case Compass, and Reflekt Legal was called Lead Autopilot. Neither vendor reviewed this page.