IntakeOS vs LawDroid: how they compare in 2026

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.

Two products with different centrality, judged on the combination rather than the stronger half. Builder, the intake and automation product, is at heart a no code workflow and conditional logic engine. Independent review says Builder draws on the workflows, templates, questions, logic and content the firm builds into it, and is not positioned as a broad legal research database. Decision tree chatbots and document assembly on conditional logic are deterministic automation, with natural language answers added on top. Copilot is the opposite: an AI assistant with no function without the model. LawDroid has operated since 2016, when chatbot automation was rule based, and independent review describes Copilot as a new product adding large language model AI to an existing range. What buyers here get is an automation builder that now has AI in it, not a model that automation was built around.

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.

A research capability with no disclosed sources and an explicit third party warning. Copilot is stated to assist with case law research, and independent review states that the specific sources from which it retrieves case law are not explicitly detailed, that outputs should be treated as work product requiring attorney review, and that attorneys should verify results before relying on them. Unsourced case law retrieval is the highest risk configuration in legal AI and it is exactly the shape that produces fabricated citations. Nothing published by the vendor addresses grounding, citation to source, accuracy, hallucination rate, evaluation or benchmark. The Builder side compounds it differently: chatbots answer frequently asked questions using natural language over firm supplied content, and nothing states what happens when a question falls outside that content.

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.

One published feature answers this directly. The vendor offers human agent takeover, letting a person jump in and take over an automated conversation, framed as automation being good and automation plus the human touch being better. That is a named way for a person to interrupt an automated process while it runs, not just review it afterward. It is the right control for a chatbot talking to a member of the public in real time. Independent review adds that output should be treated as work product needing attorney review. Nothing is bounded, though. There is no statement of what triggers a handoff, whether escalation can happen automatically on a detected condition, or what the bot does while waiting for a person. Nor does anything say what it may say unattended at the Enterprise tier, where LawDroid builds and manages the chatbot for the firm.

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.

Independent review is the substance, and customer evidence is thin. A named legal technology publication reviewed both products separately, verified pricing and integrations, and recorded limits, including that no secondary source library was verified for Builder and that Copilot's case law sources are not detailed. Review that records what could not be verified is better evidence than a testimonial. The vendor has operated since 2016 and has a named affinity partnership with that publication. Against that, one customer quote is attributed to a named person, the CEO and Founder of LexBlog. No law firm, legal aid organization, court or government agency customer is named, though all four are stated buyers. No usage figure, case study or measured outcome is published, and a major review platform profile shows zero reviews.

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.

Nothing substantive located. The only statements found say the platform maintains confidentiality and safeguards sensitive information, phrasing that names no mechanism, and an independent review checkbox notes the product claims to keep data secure. Nothing addresses attorney client privilege or work product. The gap has a specific shape here. An intake chatbot talks to a prospective client before any engagement exists, and what it collects sits in the uncertain zone before privilege attaches. That is a professional responsibility question and a conflicts question, since a firm that learns a prospective client's confidences may be conflicted out of acting for the other side. Nothing published engages any of it.

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.

Not located, and the question is sharp here. The vendor markets Builder to firms as a way to scale legal expertise and charge for services such as self service legal documents, issue spotting and legal guidance, delivered while the lawyer sleeps. Issue spotting and legal guidance delivered automatically to a member of the public, for a fee, with no lawyer present is the unauthorized practice scenario in its most direct form, and the vendor names it as the product's purpose. Buyers include legal aid organizations and courts, where the end user is a self represented member of the public. Nothing published says output is not legal advice, addresses where legal information ends and legal advice begins, or engages any bar authority or access to justice guidance on unbundled or automated delivery.

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.

Nothing published about how the models are governed, evaluated or monitored. No AI policy, no model card, no bias or fairness testing, no evaluation methodology, no accuracy monitoring, no drift statement, no named governance body, no ISO 42001 and no EU AI Act positioning are published. The untested risk is specific to intake rather than generic: an intake chatbot performs triage, deciding which inquiries convert to leads and which are turned away, and any systematic tendency in that triage falls on prospective clients who are never told a machine assessed them and have no route to appeal. In the legal aid and court configurations the vendor names, the people being triaged are self represented and often have no alternative.

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.

No stewardship position located. Nothing states whether intake conversations, uploaded documents, firm built workflow content or Copilot prompts are used to train or improve models, no retention period is published, and no deletion right is described. The content at stake includes conversations with prospective clients about their legal problems, which is sensitive personal information collected from members of the public who are not the customer and have no relationship with the vendor at all. The only located statements are generic assurances of confidentiality and privacy.

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.

No published position located. Nothing was found on liability for AI output, warranty, service levels or remedy. Three exposures are distinctive here. An unsourced case law citation from Copilot reaching a filing is the fabricated citation risk in its classic form. A chatbot delivering issue spotting or legal guidance that is wrong reaches a member of the public directly with no lawyer in between, which is the vendor's stated use case rather than a misuse. And in the Enterprise tier LawDroid builds and manages the chatbot on the firm's behalf, so the vendor authored the conversation flow that spoke to the public, and nothing addresses who carries that.

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.

A practice management integration is named, and the difference between the products is stated precisely. Builder integrates natively with Clio Grow and Clio Manage, the intake and practice management systems the target buyer actually uses. Native integration with the intake product matters because a captured lead must become a matter. Copilot connects only through Zapier, and independent review says so plainly, noting that any practice management system connecting to Zapier could potentially work with Copilot. The vendor says one product integrates natively and the other does not, rather than claiming integration across the platform. Builder states lead capture into a firm's case management system, and API workspace integrations are mentioned. Only one practice management vendor is named, no API documentation is published, and the Zapier dependency is a real limit for Copilot.

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.

Nothing located. No hosting provider is named, no region or data residency commitment is published, and no deployment options are described beyond the products being web based and cloud hosted. Residency matters here because the vendor states buyers including courts and government agencies, which routinely carry procurement requirements about where public data is processed, and because intake conversations with members of the public are personal data subject to state and international regimes.

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 certification, attestation, trust center or security page is published. No SOC 2 of either type, ISO 27001, named auditor, penetration testing partner or encryption statement was found. The only material is a generic claim that the product keeps data secure, recorded through an independent review checkbox. That review's own framing notes that most AI products are built in ways that make them inherently insecure, which is the reviewer's caution rather than a finding about this vendor. The gap matters because the stated buyers include courts and government agencies, which usually require a named attestation before buying.

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.

Nothing located. No foundation model provider, model family or version is named, no line is drawn between proprietary and third party models, and no subprocessor list was found. Independent review describes Copilot as using large language model AI, which confirms an outside or licensed model layer exists without naming it. Copilot's case law sources are also undisclosed, so neither the model nor the data behind the research feature can be identified from public material.

Pricing comes 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.

Complete pricing is published across two products and a bundle. Published and independently verified: Copilot at $25 per user per month and Builder at $99 per user per month, both month to month with no annual contract, a 7 day free trial on Copilot, and both products together at $99 per user per month with an annual commitment. That last item matters. The bundle costs the same as Builder alone but locks the buyer in for a year, a real trade off disclosed rather than buried, which a buyer can weigh without a sales conversation. An Enterprise tier for managed delivery is unpriced, the only gap.

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.

Buyer coverage is stated broadly, and practice coverage is not stated at all. Named buyers span law firms, legal aid organizations, courts and government agencies, a wide institutional range, and pricing and independent review make clear the target is solo practitioners and small firms. What is missing is any description of substantive coverage. No practice areas or jurisdictions are named, and because Builder runs on content the firm supplies, its subject coverage is whatever the customer builds, which the vendor never says. For Copilot, independent review notes that no secondary source library was verified and that case law sources are not detailed, so research coverage cannot be assessed either.