Q
Querious
Querious is an AI notetaker for lawyers from Querious, Inc., a Delaware company, sold under the name Legal Conversational Intelligence. It joins client conversations on Zoom, Microsoft Teams and Google Meet, and handles phone calls and in person meetings through a desktop app. During the conversation, patented real time features surface legal issues, follow up questions and relevant statutes, regulations or guidance, capture planned questions and track follow up tasks.
Afterward it produces structured notes, a summary email and a drafted time entry with a billing narrative, which the lawyer reviews and sends to the matter in Clio, 8am MyCase or Smokeball. Audio is processed as it streams and never stored, no verbatim transcript is kept unless a user turns that on, personal details are removed before analysis, and voiceprints are destroyed within a minute of each meeting. Models from OpenAI and Anthropic run in private instances inside Querious's Microsoft Azure environment. Plans start at $59.99 a member a month, with the real time features at $99.99 and enterprise pricing on request.
Alternatives to Querious
Vendors in the same categories as Querious whose graded profiles look most alike, with a line on what each product does.
Similar is not the same, so check that each one does the job you need. No vendor pays for placement.
- WWordsmithWordsmith is a legal platform built only for in house teams.
- OOrdalieOrdalie is a French legal AI platform for lawyers in private practice, in house legal teams and notaries.
- PPhilips SpeechLivePhilips SpeechLive is a cloud dictation, speech recognition and transcription platform sold by Speech Processing Solutions, with a legal edition, SpeechLive Legal, for solicitors…
- JJimini AIJimini AI is a legal AI assistant built for continental civil law, sold to French law firms, individual avocats and corporate legal departments.
- LLucioLucio is a legal AI workspace built by lawyers at Zenlegal Technology Private Limited in Bengaluru, which contracts outside India through Lucio Inc and has users in 13 jurisdictions.
- MMagnarMagnar is a legal AI agent for lawyers in Latin America, built by Magnar SpA in Santiago, Chile.
Ordered by how closely the graded profiles match across the 15 capability axes, inside the same categories. See how each axis is graded in the methodology.
Capability grades
All 15 axes, graded from public sources on the date shown. 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.
The product is the model listening to a client conversation. Audio streams in from Zoom, Microsoft Teams, Google Meet, a phone call or a meeting in the room, and speakers are told apart. From that the AI produces notes, a summary email, follow up tasks and a drafted time entry with a billing narrative. The Intelligent plan adds patented real time features that surface legal issues, follow up questions and statutes, regulations or guidance as the conversation runs, and capture the questions a lawyer planned to ask.
Personal details are removed before the conversation is analyzed, and past notes on a matter prepare the lawyer for the next conversation. Without the models there is no product to sell.
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.
Real time research prompts surface statutes, regulations and guidance tied to what is being discussed, and Enterprise customers can set custom sources for those prompts. The standard sources, how a prompt is matched to the conversation and whether a cited provision links to its text are not described.
An AI accuracy disclaimer states that outputs may contain errors, inaccuracies, omissions, hallucinations or misattributions, including factual errors in research prompts and issue spotting suggestions. No accuracy figure, test set or error rate is published for notes, speaker attribution or research prompts.
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.
Nothing leaves Querious on its own. When a conversation ends, the lawyer gets notes, a summary and a drafted time entry. Where Querious cannot identify the Clio matter with certainty, the lawyer confirms it, then sends the reviewed notes and billing entry to the matter. Real time prompts appear as suggestions during the conversation.
Under the disclaimer, the authorized user is solely responsible for reviewing, verifying and correcting every output before relying on it for client advice, court filings, legal strategy or settlement negotiations. No confidence signal or threshold at which the system holds back a prompt is described.
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.
Customers are quoted by name and firm without figures. Jennifer Stanley, managing partner of Stanley Kup Legal & Compliance in Texas, says she cannot afford to be without it. Wayne Hassay, managing partner of Maguire, Schneider, Hassay LLP in Ohio, calls it a real time legal assistant. Keely Beemer of Bird, Scheske, Reed, Beemer & George in Michigan and Princess Uchekwe of The Chief Counsel in New York are quoted too, along with Matt Beier, a senior vice president at Wisconsin Lawyers Mutual Insurance Company.
The ROI calculator estimates hours saved and revenue from a firm's own inputs, marked as representative results. Querious has delivered CLE sessions for state bars and malpractice insurers. No dated deployment with measured results is published.
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.
Confidentiality is built into how audio is handled. Streaming audio is processed and never written to storage, no verbatim transcript is kept unless a user enables one, personal details are stripped before analysis, and voiceprints are destroyed within 60 seconds of a meeting ending. Meeting content and outputs are never used to train, fine tune, evaluate or improve any model, a separation Querious enforces by keeping production and training systems apart at the network level. The model providers run in private instances, delete inputs after processing and are barred by contract from training.
Staff cannot read privileged content in decrypted form without the user's consent, and legal demands follow a protocol of notifying the user, asserting privilege and declining to produce without a court order. These commitments sit in the privacy policy. The platform's terms of service are shown only at registration and not published, and nothing describes separation between matters or users inside a firm.
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 disclaimer states that Querious is a technology company, not a law firm, that neither the website nor the platform gives legal advice, and that no attorney client relationship forms with Querious. The relationship stays between the authorized user, the attorney, and the client, and Querious describes its own role as a technology provider working in a capacity like a paralegal or court reporter so that privilege is preserved.
The attorney must review, verify and correct every output before relying on it for advice, filings, strategy or settlement. Security is mapped to ABA Formal Opinion 477R, and Querious delivers CLE sessions on AI notetakers. It also sets out how recording consent and Illinois biometric rules apply when participants sit in different states or abroad, with consent features for Illinois meetings.
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.
Querious publishes no AI policy, governance framework, named owner or testing program. It says the product was designed by attorneys, and the model separation and deletion rules are data protections rather than governance of output quality. Nothing addresses whether notes, speaker attribution or issue spotting work less well for some accents, languages or practice areas.
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.
Retention is set out item by item. Nothing from the audio itself is stored, and voiceprints last no more than 60 seconds after a meeting. Notes, outputs and optional transcripts stay for 60 days unless the user sets a shorter period, and users can delete them at any time. Account data is kept for 60 days after the account closes, then deleted or anonymized.
Data is encrypted with TLS 1.2 or higher in transit and AES 256 at rest, staff access is limited to automated systems except for consented support, and breaches are reported within 24 hours. The AI providers named are OpenAI and Anthropic, with Microsoft Azure as the cloud. Other service providers are described only by role, such as payments, analytics and support, and no full list is published.
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.
The platform's terms of service, which govern the product, are presented only at registration and are not published, so no liability cap, indemnity, warranty on output or insurance position can be read before signing. The published terms of use cover the website alone, cap Querious's liability for website use at $100, and require visitors to indemnify Querious. The disclaimer places full responsibility for relying on AI output on the authorized user.
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.
The Clio integration is documented step by step. Where it can, Querious identifies the Clio matter for a conversation and asks the lawyer to confirm it. Reviewed notes and the billing entry then go to that matter, and past notes on the matter come back to prepare the lawyer for the next conversation. 8am MyCase and Smokeball connections are included on every plan.
On the meeting side, Querious joins Zoom, Microsoft Teams and Google Meet, with a custom meeting bot on the Intelligent plan, and a desktop app covers phone calls and in person meetings. Summaries can go out by email, after which the email provider's retention applies. Enterprise customers get custom integrations through an API.
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.
All platform operations run in Microsoft Azure, and the AI models run in private, isolated instances that are not shared with other customers. The Azure region and where the model providers process data are not stated, and no on premises or regional option is offered. Querious notes that meetings with participants outside the United States may bring in the GDPR and similar laws, without describing a separate deployment for them.
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.
SOC 2 Type II certification is held, with an annual independent audit of the security controls. The auditor, the report period and the scope are not named, and no trust center or route to the report is published. Security measures are mapped to ABA Formal Opinion 477R on reasonable efforts to protect client confidentiality.
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.
Meeting audio is processed by models from OpenAI and Anthropic, described as current providers, running in private instances inside Querious's Azure environment. Each provider must delete inputs once processing ends, may not train on the data and owes confidentiality at least as strict as Querious's terms.
Which models and versions handle transcription, notes and research prompts is not named, the region they run in is not stated, and no notice of a change in provider is promised.
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 published in USD per member a month, with monthly and annual billing. Essential costs $59.99 and includes unlimited meetings, notes, summary emails, billing entries, Zoom, Teams and Meet support, the Clio, 8am MyCase and Smokeball integrations, and the desktop app. Intelligent costs $99.99 and adds custom conversation types, a custom meeting bot, capture of planned questions, real time issue, question and research prompts, and follow up tracking.
Enterprise, with API integrations, custom research sources and enterprise configuration, is priced on contact. A free trial starts from the site without a sales call. No setup fee is mentioned for the self serve plans.
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.
Solo practitioners, boutique firms and multipractice law firms use the product. Practice areas named include business and corporate law, employment and labor, estate planning, real estate, healthcare compliance, intellectual property and general litigation, and highly specialized practices are asked to get in touch about configuration.
Recording consent and biometric rules are handled for meetings across states and for participants outside the United States. Which practice areas the real time research prompts cover in depth, and which jurisdictions' law they draw on, is not stated.
2 public documents
The public pages on file for Querious, with the recorded signals each one supports and the date it was last read. Open any of them and check the reading against the record.
-
querious.ai/privacy-policy5 signals
Client Data in Training, Prompt and Output Retention, Third Party Request and Subpoena Notice and 2 more
Read Oct 13, 2026
-
Fabricated Citation Record
Read Oct 13, 2026
From $59.99 per member/month
- Querious costs $59.99 a month for each person on the Essential plan.
- The Intelligent plan costs $99.99 a month and gives tips during the call.
- You can pay monthly or yearly.
- Big firms ask Querious for a custom price.
- You can try it free first.
Per member per month in USD, billed monthly or annually. Essential at $59.99 includes unlimited meetings, AI notes, summary emails, billing entries, Zoom, Microsoft Teams and Google Meet support, Clio, 8am MyCase and Smokeball integrations and the desktop app. Intelligent at $99.99 adds custom conversation types, a custom virtual meeting bot, automatic capture of planned questions, real time question, issue and research prompts, and real time follow up tracking.
Enterprise adds custom API integrations, custom research sources and enterprise configuration and support, priced on contact.
Implementation: None stated for Essential or Intelligent. Enterprise configuration and support are part of the custom Enterprise price.
Note: A free trial starts from the site. The pricing page toggles between monthly and annual billing without showing the annual rate.
Legal Signals
What each signal meansA signal records what public sources say on the date shown. It is not a grade and it is not a recommendation. Where a signal reads Not addressed, it means the index did not locate the material in public sources on that date, which is a statement about disclosure rather than about the product.
Client Data in Training
Can material a lawyer puts into this product be used to train a model?
A public policy or trust page states no training on customer content, with no matching term located in the published agreement.
Section 3.2 of the privacy policy rules out using meeting audio, AI outputs, voiceprints or any other meeting content to train, fine tune, evaluate or improve any model. Production and training systems are kept apart at the network level. The AI providers, OpenAI and Anthropic, are barred by contract from training on the data. The platform terms of service that would carry the promise as an agreement are shown only at registration.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
The customer controls the retention window, by product configuration or by contractual instruction, but zero retention is not stated as available.
Notes, outputs and any transcripts a user chooses to keep are held for 60 days by default. The user can set a shorter period in profile settings or delete them at any time, and they are then deleted automatically. No audio is ever stored, voiceprints are destroyed within 60 seconds of a meeting, and AI providers delete inputs once processing ends.
Ethical Walls and Matter Segregation
Does retrieval respect the firm’s ethical walls, or can the model read across them?
No located public material addresses walls or matter level segregation.
Outputs belong to the authorized user who recorded the conversation, and Clio matter association keeps notes with the right matter. Nothing describes permissions or walls that limit which colleagues inside a firm can see a matter's conversations.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
Terms commit to notice where lawfully permitted. No transparency report located.
Because meeting content may be privileged, Querious follows a subpoena protocol before disclosing it: it notifies the affected user, asserts privilege and declines to produce without a court order. 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?
No located public material identifies the corpus behind the product’s answers.
Real time prompts surface statutes, regulations and guidance during a conversation, and Enterprise customers can add custom sources. The standard sources behind those prompts, their rights basis, jurisdictions and update cadence are not named.
Good Law Verification
Does the product tell you when the authority it just cited has been overruled?
No located public material addresses whether authority is checked for subsequent history.
Research prompts name statutes and regulations as suggestions during a call, with no check of whether an authority is current or has been amended. Such prompts may contain factual errors, the disclaimer warns.
Refusal and Uncertainty Behavior
What does the product do when the answer is not in the corpus?
No located public material addresses what the product does when it cannot ground an answer.
Nothing describes how Querious behaves when it cannot attribute speech, misses a passage or finds no relevant authority, and no confidence signal is shown. Hallucinations and misattributions are among the possible output errors listed in the disclaimer.
Fabricated Citation Record
Does a public court record exist addressing fabricated or hallucinated legal citations in output from this product?
No court order, opinion or disciplinary record addressing fabricated or hallucinated legal citations produced by this product has been located as of the date shown. This is a statement about the public record on that one subject, not a finding about the product, and this signal is not a litigation history.
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 Querious. Its outputs are meeting notes, billing entries and research suggestions that the attorney must verify before use.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions its buyers are bound by?
Public materials engage with at least one named ethics opinion.
Security measures are mapped to ABA Formal Opinion 477R (2017) on reasonable efforts to protect client confidentiality. Querious argues that the product can be used without waiving privilege by analogy to email and cloud storage, delivers CLE sessions for state bars and malpractice insurers, and asks lawyers to review the guidance in their own jurisdiction.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
Public materials claim time savings without addressing billing or disclosure, and the product sits inside a fee relationship between a lawyer and a client where those savings would change the bill.
Each conversation yields a drafted time entry and billing narrative, which the lawyer reviews and sends to Clio, MyCase or Smokeball, and an ROI calculator estimates hours saved and revenue. The entry records the lawyer's conversation, not the AI's work. No guidance addresses whether or how a firm should disclose AI notetaking or bill for it.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
A current subprocessor or model provider list is published.
OpenAI and Anthropic are named as the AI providers, running in private instances inside Microsoft Azure, with deletion, no training and confidentiality duties set out. Other service providers are described by role only. The privacy, disclaimer and BIPA policies give a firm material to explain the tool to clients and to Illinois participants.
Court Disclosure Support
If a judge’s standing order requires an AI disclosure, can the product produce one?
No located public material addresses court disclosure or verification certification.
The outputs are notes and billing entries from client conversations rather than court filings. Nothing addresses disclosure of AI use to a court, and no export records the model behind an output.