Q
Qanooni
Qanooni is a legal AI platform for law firms from Qanooni AI Ltd, a company registered in Dubai's DIFC free zone and sold mainly to firms in the United Kingdom and the UAE. It runs inside Microsoft Word, Outlook and Teams rather than as a separate application. QMatters is the foundation. It reads the emails, documents and files connected to a matter, builds a graph of the parties, facts and timeline, and sets more than 5,000 live legal authorities beside them.
Three modules work on that foundation. QCounsel takes a plain English request and runs multistep work across the file, such as chronologies, bundle summaries, party maps and tables of dates and obligations. QDraft writes agreements and client emails in the firm's own style from its precedents. QRedline reviews counterparty paper against the firm's playbook and marks it up in track changes with fallback wording. Every answer cites the document or authority behind it.
An Actionstep integration brings matter context into Word and saves finished work back to the matter. More than 150 firms in 11 countries use Qanooni by its own count, and prices are quoted after a demo.
Qanooni, head to head
Side by side on the same 15 capability axes and 12 legal signals: where the two part company, and what neither one publishes.
Alternatives to Qanooni
Vendors in the same categories as Qanooni 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.
- CCORTOCORTO is an AI workspace for law firms from CORTO Pty Ltd in Sydney, which also runs a US company, CORTO AI Inc., and an office in San Francisco.
- CCoCounsel LegalCoCounsel Legal is Thomson Reuters' flagship legal AI product, grounded in Westlaw and Practical Law content.
- RRuliRuli is an AI legal platform from Ruli, Inc. of Austin, Texas, built for in house legal teams.
- SSagaSaga is a legal AI platform from Saga International B.V. in Amsterdam, with Norwegian roots, used by more than 500 legal teams and law firms in over 25 countries.
- OOrbitalOrbital is an AI platform for commercial real estate legal work, sold to the real estate practices of law firms, to real estate businesses such as investors, developers and REITs, and to…
- WWordsmithWordsmith is a legal platform built only for in house teams.
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.
Every module is model work. QMatters reads the documents, emails and files on a matter and builds a graph of its parties, facts and timeline with no manual entry, then keeps it current as new material arrives. QCounsel turns a plain English request into a plan of steps and runs it across the whole file, producing chronologies, a two page brief from a 300 page bundle, party maps and tables of dates and obligations. QDraft writes agreements, notices and client emails in the firm's tone from its precedents.
QRedline reviews counterparty paper against the firm's playbook in track changes. Retrieval from more than 5,000 legal authority sources sits under all four. The product keeps no conventional workflow layer of its own. Matter records, billing and documents stay in the firm's existing systems, such as Actionstep and Microsoft 365.
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.
Answers are built by retrieval rather than from the model's memory. Qanooni pulls statutes, cases and regulations from more than 5,000 legal authority sources at the moment of the request, attaches a citation to each line, and a click opens the original. The sources sit in a legal data graph hosted in Azure that maps how laws amend one another, which cases interpret a provision and how earlier versions changed. Official databases feed it, among them the UK's legislation service, the EU's official law database, the UAE Ministry of Justice and the Saudi Bureau of Experts.
Matter answers cite the document on the file they came from. Qanooni states that the product cannot invent case law, and no measured accuracy rate, test set or failure analysis is published beside that statement. The source count stood at 1,000 in October 2025 and is given as more than 5,000 today.
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.
Lawyers stay in the loop at set points. QRedline proposes its markup as track changes in Word, so each edit is accepted or rejected by the lawyer, and QDraft returns a first draft rather than a sent document. QCounsel plans and runs multistep work end to end, then hands back the chronology, table or analysis with every point cited to the file or the law. Qanooni's position is that nothing goes to a client without a lawyer's sign off.
In its UAE case study the product flags risk, and the lawyers verify compliance, interpret what the risk means and advise the client. On Actionstep, each draft, review and change is logged to the matter. Which QCounsel steps run without approval, the point at which the product stops and hands back, and what happens after a step goes wrong are not 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.
Inspired Thinking Group, a UK marketing and content technology company, piloted Qanooni with its in house commercial legal team, and the results were published in January 2026. Comparable review tasks were timed against the team's earlier baselines using its standard time keeping. Review time fell by 60%, and personal productivity rose 21%. The team expects 25 to 30% once SharePoint and OneDrive files connect, a projection rather than a measurement.
Inspire Legal Group became the first UK firm to run Qanooni inside Actionstep, and partners or founders at Legal Circle, Lecote and Primecase are quoted by name. Qanooni puts its base at more than 150 law firms across 11 countries. A UAE case study with the firm unnamed describes more than 200 contracts reviewed in seven days instead of two weeks, and figures on the Actionstep page carry no unit or customer.
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.
Client documents are referenced through retrieval at the moment of use and are never used to train a model, Qanooni's or any provider's. Each firm's data is logically isolated from every other firm and reachable only by that firm, behind role based access, single sign on and audit logging. The firm owns its matter graph as intellectual property and can export or permanently delete it at any time. Document contents stay in Qanooni's own Azure environment, with no third party document repository added.
These commitments are made on Qanooni's website and in its articles. The user agreement that governs the product is not published, and nothing addresses privilege, work product or what the model provider keeps.
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.
Sold to law firms and in house legal teams, the product is framed two ways in its own material. The Actionstep page calls it the legal AI that does the practice of law, covering research, review and drafting. Elsewhere the line runs the other way. Lawyers verify compliance, interpret exposure and advise clients while the product flags risk, and nothing goes out without a lawyer's sign off. Articles on UK practice tie its use to the SRA duties of confidentiality, competence and supervision.
The published terms cover the website only. The user agreement for the product is not public, so no advice disclaimer, user restriction or jurisdiction limit appears in writing.
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.
Accuracy, auditability and alignment are the three principles Qanooni names for trust in legal AI, and grounding in cited law is presented as its main control on output. Client data is excluded from model training, and a change of model is designed to happen without moving a firm's data. No governance framework, release testing regime, accountable owner or analysis of how output varies across practice areas, jurisdictions or languages is published.
Articles on UK regulation describe how the SRA, the ICO, the FCA and the CMA approach AI in law firms, and the Equality Act 2010 for algorithmic screening, as background for buyers rather than as Qanooni's own controls.
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.
Data is encrypted in transit and at rest on Microsoft Azure, with role based access, single sign on, multifactor authentication and audit logging across the platform. Each firm's data is logically isolated, and the firm can export or permanently delete its matter graph whenever it chooses. The privacy policy lists the service providers that may process personal data, each with its purpose, hosting region and transfer safeguard.
They are Stripe for payments, HubSpot for CRM, PostHog for product analytics, Microsoft for productivity and documents hosted in the UAE, and Langfuse in Germany for LLM monitoring. Personal data is kept for a reasonable time with no fixed period, and no retention period is given for documents, prompts or outputs. No incident or breach notice practice 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 only published terms are the website terms effective 5 August 2025, under UAE law with the Dubai courts as forum. They provide the website as is, exclude Qanooni's liability for the website and its content, and have visitors indemnify Qanooni. Use of the product itself falls under a separate user agreement that is not published. Caps, indemnities, warranties and recourse for wrong output therefore cannot be read before signing.
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.
Installed from Microsoft AppSource as a ribbon tab in Word, the product also works in Outlook and Teams, so drafting, review and research happen in the documents and email the firm already uses. The Actionstep integration goes deepest. When a lawyer starts drafting in Word or Outlook, Qanooni pulls the matter details, client information, deadlines and related documents from Actionstep. Finished work saves back to the matter with version control, audit logs and matter linking.
It switches on inside an existing Actionstep with no data migration. A Docusign partnership announced in April 2026 connects drafting and review to signature and agreement management. Document management systems are supported without being named, and the SharePoint and OneDrive file connection was still described as coming in January 2026.
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.
Microsoft Azure hosts the platform as cloud software, with each firm's data logically isolated from other firms. Document contents stay in Qanooni's own Azure environment while the lawyer works in the firm's Microsoft 365 tenant. For UK firms Qanooni describes data held in Microsoft's UK and EU data centers. For UAE and wider GCC work it states that local data is stored and processed in Microsoft's UAE data centers to meet DIFC and ADGM rules.
The privacy policy allows personal data to be stored in the United States and the UAE. No private cloud or on premises option, tier difference or separate processing location for the language model is described.
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.
ISO/IEC 27001:2022 certification and a SOC 2 Type II attestation cover the operating environment for the platform, which runs on Azure infrastructure that carries its own certifications. The auditor, the report period and the controls in scope are not published. Security documentation is sent on request through the demo and contact route, and there is no trust center or self serve portal. Personal data falls under the DIFC Data Protection Law of 2020, with complaints going to the DIFC Commissioner of Data Protection, and the company states GDPR compliance.
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.
The platform is model agnostic. The model underneath can be swapped without moving a firm's data, since the firm's precedents, voice and accumulated judgment live in its matter graph rather than in a trained model. Neither the model in production nor its provider is named. Hosting on Microsoft Azure is stated, and the privacy policy lists Langfuse, based in Germany, for LLM observability and monitoring. No commitment to tell customers when the model changes is published.
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.
No price, plan, unit of charge or contract term is published. Every route leads to a 30 minute demo, and the Actionstep page sends firms to a phone number or their Actionstep representative. An ROI calculator estimates the hours and value a team could recover from its own rates and weekly hours, in pounds, dollars, euros or dirhams, and asks for contact details before it shows the report. It says nothing about what Qanooni costs.
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.
Law firms are the main buyer, from boutiques to full service practices, with more than 150 using the product across 11 countries. In house teams such as Inspired Thinking Group's commercial legal team use it too. Jurisdictions are named. The legal data graph covers the UK, the EU, the UAE, Saudi Arabia, Qatar and other GCC states, with Arabic and English drafting for UAE contracts and checks against UAE Labour Law and DIFC and ADGM rules.
Published work spans commercial contracts, M&A due diligence, employment contracts under UK law, conveyancing and litigation chronologies. The ROI calculator lists practice settings from corporate and litigation to family, immigration, criminal and private client work. Practice areas or jurisdictions the product does not support are not stated.
7 public documents
The public pages on file for Qanooni, 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.
-
qanooni.ai/security3 signals
Client Data in Training, Prompt and Output Retention, Ethical Walls and Matter Segregation
Read Oct 13, 2026
-
qanooni.ai/actionstep2 signals
Billing and Fee Posture, Court Disclosure Support
Read Oct 13, 2026
-
qanooni.ai/privacy2 signals
Third Party Request and Subpoena Notice, Outside Counsel Guideline Readiness
Read Oct 13, 2026
-
Fabricated Citation Record
Read Oct 13, 2026
-
Bar Guidance Alignment
Read Oct 13, 2026
-
Primary Law Corpus Provenance
Read Oct 13, 2026
-
qanooni.ai/grounded1 signal
Refusal and Uncertainty Behavior
Read Oct 13, 2026
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.
A firm's documents are referenced through retrieval when a lawyer asks and are never used to train a model, Qanooni's own or any provider's. The same commitment appears on its security, home and Actionstep pages, and the firm's matter graph stays its own intellectual property. Because the model sits outside the firm's data, a change of model leaves the firm's knowledge where it is. No customer agreement is published, so no matching contract term can be read.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
Retention is acknowledged in public materials with no stated period.
A firm can export or permanently delete its matter graph and documents whenever it chooses, and work saved through Actionstep stays on the matter with its version history. Personal data is kept for a reasonable length of time with no period given, and Langfuse monitors LLM activity from Germany. No retention window is stated for prompts, outputs or the logs of model calls, and no zero retention setting is described.
Ethical Walls and Matter Segregation
Does retrieval respect the firm’s ethical walls, or can the model read across them?
Segregation is asserted in public materials with no published detail on how it is enforced.
Each firm's matters, precedents and knowledge are logically isolated and reachable only by that firm, and nothing is pooled across firms. Inside the firm, role based access, single sign on and audit logging control who sees which matter, and the matter graph organizes every document and email by the matter it belongs to. How matter permissions are set, and whether they follow the access rules in the firm's document management system or in Actionstep, is not described.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
Published terms or policy address disclosure to authorities or in response to legal process, and no commitment or reservation regarding customer notice is located anywhere. The vendor has told the customer that data can leave and has said nothing about whether the customer hears of it.
Under its privacy policy, Qanooni may have to share information with public authorities or law enforcement, for example under a court order, after satisfying itself that a lawful basis exists and documenting the decision. It makes no commitment to tell the firm about a request or to resist one, and no transparency report is published. Product terms that might add a notice duty are not public.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
Sources are identified without stating the license or rights basis.
The legal data graph connects statutes, case law, regulations, circulars and gazettes for the UK, the EU, the UAE, Saudi Arabia, Qatar and other jurisdictions. Named sources include the UK's legislation service, the EU's official law database, the UAE Ministry of Justice and the Saudi Bureau of Experts, and connections are described as permissioned, timestamped and refreshed routinely. The rights basis for each source and a fixed update schedule are not given.
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.
Each line of an answer cites the statute, case or regulation it rests on, and the legal data graph maps how laws amend one another, which cases interpret a provision and how versions have changed over time. Sources are read live at the time of the request, so a statute appears in its current form rather than as a training snapshot. No flag on a cited case that has been overruled, reversed or distinguished is described.
Refusal and Uncertainty Behavior
What does the product do when the answer is not in the corpus?
The vendor describes refusal or abstention behavior in public materials.
Answers come only from retrieved sources. Where no authority supports a point, the product says so and leaves the claim out rather than inventing support, and Qanooni invites firms to test this in a demo on their own matters. No published evaluation shows how often it declines to answer.
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 Qanooni. Every answer the product gives carries a citation that opens the source behind it.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions its buyers are bound by?
Public materials refer to professional responsibility in general terms without naming guidance.
Articles for UK firms tie AI use to UK GDPR and to the SRA's duties on confidentiality, competence and supervision. They also summarize how the SRA, the Law Society of England and Wales and the Law Society of Scotland approach AI, and a pilot plan template for UK firms sets out governance controls and roles. UAE material covers DIFC and ADGM data rules. No specific ethics opinion or practice note is discussed, and no mapping of the product to guidance in either market is published.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
A usable record of AI assisted work exists with no published fee guidance.
On Actionstep, every draft, review and change Qanooni makes is logged back to the matter with the cited authorities behind it, a per matter record of AI assisted work. Elsewhere the platform keeps an audit log. Qanooni claims drafting 50% faster, six to eight hours saved per lawyer each week and fewer non billable hours, and offers an ROI calculator. It publishes no guidance on billing or disclosing AI assisted work to clients.
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.
The privacy policy lists five service providers with their purpose, hosting region and transfer safeguard. They are Stripe, HubSpot, PostHog, Microsoft and Langfuse, and copies of the standard contractual clauses are offered by email. No model provider is named. Security documentation and certification detail are sent on request, and no client facing disclosure pack is published.
Court Disclosure Support
If a judge’s standing order requires an AI disclosure, can the product produce one?
Some elements of the record are available, short of a document level export.
Every line of output cites its source, and on Actionstep each draft, review and change is logged to the matter with the authorities behind it. QRedline's edits arrive as track changes, so the document itself shows what the product proposed and what the lawyer accepted. The platform keeps audit logs of access. No export ties a document to the model used, the sources retrieved and the lawyer who verified it, and no court disclosure template is published.