T
TriNotar

TriNotar is practice management software for German notarial offices from Wolters Kluwer Legal Software Deutschland in Hürth, sold as a monthly subscription priced by users and modules. It keeps the electronic side file under section 43 NotAktVV, records parties and contacts, imports company and representative details from commercial register extracts, checks parties against the EU sanctions list and manages tasks, document versions and collections, with Outlook import and sending.

Optional modules add digital document processing with OCR, PDF merging and compression for large original deeds, and Posteingang PLUS, which assigns scanned originals to files by barcode or file name and routes incoming mail to the clerk or notary. A DATEV interface serves lawyer notaries, and filings pass to XNotar for the trade register.

Expert AI, a per user add on, brings generative AI into the workspace: chat over one document, a whole matter or, in Plus, the office's collection, with clause extraction, summaries, drafting and plain language explanations for clients. It runs on a legal knowledge graph and models from OpenAI, Anthropic, Meta and Google hosted in the EU, and documents can be anonymized first.

Further modules cover client onboarding questionnaires, KYC checks and knowledge management. Dr. Alexander Völzmann uses TriNotar in his Wuppertal notarial practice.

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.

CC on AI CentralityArtificial intelligence is present but peripheral: a feature layer on a product whose value stands without it.

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 practice system runs the notarial office without any model: the electronic side file, party and contact records, commercial register import, sanctions list checks, deed preparation, Outlook mail, versioned documents and, with Posteingang PLUS, barcode routing of scanned originals. Expert AI is a separately licensed user add on that summarizes, extracts clauses, drafts and answers questions over a document, a matter or the office collection.

Remove the models and every notarial workflow, register filing and accounting step still runs, so the AI is a feature layer on top.

Source: Vendor Published
BB on Citation Accuracy and Hallucination DisclosureGrounding is real and documented, with linked primary sources and a described retrieval method, short of published accuracy figures an outsider can test.

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 draw on the documents the office selects and, for tasks such as clause review, on outside legal databases, with a legal knowledge graph built from about 900 million tokens of legal material structuring the source before the model writes. References let the notary compare the output with the underlying documents. The 85% time saving offered for drafting, research and document review has no method behind it, and no test reports how often a cited source or extracted clause is wrong.

Source: Vendor Published
AA on Autonomy and Oversight ModelWhat the system runs alone, what constrains it, and how a lawyer checks it are all published: modes, thresholds, review surfaces, and the route a matter takes back to human judgment. A categorical limit on a named mode or tier, stating what its output may not be used for, meets the threshold limb without a number.

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.

Expert AI works in three scopes the office chooses: Document Chat on a single file, Matter Chat on the documents of the selected matter, and Plus across the office's collection with outside legal sources. Staff can anonymize material before it reaches a model, and every result comes back for review and correction inside TriNotar rather than going into a deed on its own. The product conditions set a categorical limit: no automated decision with legal or similarly significant effect on a person without appropriate human review.

Source: Vendor Published
BB on Operational and Outcome EvidenceReal deployment evidence with substance, short of full attribution or measurement: a named customer without figures, or figures without the named customer.

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.

Dr. Alexander Völzmann, a notary in Wuppertal, is named as a user and praises the interface and its fit for modern notarial work, which speaks to the practice system rather than the AI. Expert AI's own evidence is a claim that it speeds drafting, research, document review and client communication by up to 85%, with no office, sample or period behind it.

Source: Vendor Published
BB on Privilege and Confidentiality PostureSubstantive published commitments on confidentiality and training use, short of the full picture: commonly silence on segregation between users or matters, or on what the underlying model provider may retain.

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.

Documents for Expert AI sit in a vector collection kept separate for each customer and reachable only by that customer's AI services, and data passed to the models is expressly excluded from training and fine tuning. The office chooses the scope, one document, one matter or the office collection, and can anonymize material in the cloud or on its own server first. The service addresses secrecy under section 203 StGB and section 43e BRAO. Plus retrieves across the office collection without a stated check against matter permissions.

Source: Vendor Published
AA on UPL and Professional Responsibility PostureThe vendor states plainly what the product is and is not, who may use it, and how it supports a lawyer’s competence and supervision duties. Jurisdiction limits are named and any consumer facing surface carries a clear disclosure.

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.

Notaries use Expert AI for clause review, drafting and explanations in plain language, and the office keeps the legal review. The conditions put verification of every output on the licensed office, bar automated decisions with significant effect on a person without human review, and state that Wolters Kluwer does not assess an individual case under Germany's Legal Services Act. The audience is notaries and their staff, and the service is built around secrecy duties under section 203 StGB and section 43e BRAO.

Source: Vendor Published
BB on AI Governance and Bias DisclosureA published governance framework with real substance, short of testing results or a named owner.

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.

Expert AI is built from three parts, a legal knowledge graph, task specific agents and the language models, and its prompt library holds tested legal use cases from simple to complex. The product conditions bar automated decisions with legal or similarly significant effect without appropriate human review, and Wolters Kluwer's AI principles commit to human oversight and accountable development. Aggregated or anonymized operating metrics and voluntary feedback on result quality feed product work. No named owner, release test results or comparison of output quality across notarial matter types is offered.

Source: Vendor Published
BB on AI Safety and Data StewardshipSubstantive published policy covering most of the ground, short of the full set: commonly no named subprocessor list or no stated incident practice.

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.

Each customer's documents sit in a separate vector database that only the customer and its AI services can reach, the office can have it deleted at any time, and it is deleted when the relationship ends. QNC GmbH in Hannover runs the Expert AI backend with data in Germany, Microsoft in Germany, AWS in Ireland and Google in Belgium host the models, and Digital Ocean in the Netherlands runs cloud anonymization, all inside the EU or EEA.

Backups run daily and weekly, encrypted and offsite, and a documented process handles security incidents through the data protection officer. Prompts, outputs, logs and backups carry no retention period, and incident notice has no deadline.

Source: Vendor Published
CC on AI Liability and RecourseLiability is addressed only through a standard limitation clause that disclaims the exposure the product creates.

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.

Wolters Kluwer's general terms for its legal software govern the subscription and allocate liability for the contracted services under German law. The Expert AI conditions exclude any warranty for the accuracy or completeness of output and put review and correction on the office. Software faults go through product support tickets. No remedy or indemnity attaches to a wrong summary, a missed clause or a flawed draft, so the office carries that loss.

Source: Vendor Published
AA on Practice Systems Integration DepthDocumented, verifiable integrations into the systems legal work already lives in, with the depth described: what syncs, in which direction, and what a firm must configure.

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 optional DATEV interface sends parties and matter data from TriNotar to the firm's DATEV installation, returns the DATEV matter number to the TriNotar file, and posts notarial invoices to that matter as receivables, while payments stay in DATEV and updated open items return to the invoice header. The firm installs a transfer database from Advoservice to link the two. Trade register filing data passes to an installed XNotar, Outlook mail imports and sends from the file, and the TriNotar ribbon in Word saves a new version into the chosen folder.

Source: Vendor Published
AA on Deployment Model and Data ResidencyDeployment options and data residency are published, including the regions available, what changes between tiers, and where processing happens as distinct from where data is stored.

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.

TriNotar is offered installed in the office, where the office keeps its SQL database when the contract ends, or hosted. Expert AI always runs in the cloud. Its processing description places the QNC backend and vector store in Germany, OpenAI models with Microsoft in Germany, Anthropic and Llama models with AWS in Ireland, Gemini with Google in Belgium and cloud anonymization with Digital Ocean in the Netherlands, all inside the EU or EEA. An optional on premises anonymization server keeps that step in the office at extra cost.

Source: Vendor Published
CC on Security Certifications and Trust CenterBadges appear on the site with no scope, no date, and no report available.

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.

An ISO 27001 badge sits on the Expert AI offer, and the processing description cites ISO 27001 and BSI baseline protection beside measures such as a 20 character minimum password, intrusion detection, disk encryption, RFID data center access and TLS 1.2 or higher. No certificate shows the certified entity, auditor, scope or date, so it is unclear whether it belongs to Wolters Kluwer, QNC or a host. There is no trust center or audit report.

Source: Vendor Published
BB on Model Supply Chain DisclosureThe supply chain is partly disclosed: providers named without change notification, or architecture described without the providers.

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.

Expert AI combines a legal knowledge graph, task specific agents and a choice of language models. The processing description names OpenAI models stored with Microsoft in Germany, Anthropic Claude and Meta Llama with AWS in Ireland and Google Gemini in Belgium, run through QNC GmbH's Prime Legal AI backend in Hannover. Customer data is expressly excluded from training and fine tuning. Which model handles a given task, and what notice precedes a change of provider or version, are not committed.

Source: Vendor Published
BB on Commercial TransparencyReal pricing is published for part of the range, with enterprise tiers withheld, or the unit and structure are stated without the figure.

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.

The subscription is priced per user per month by the modules chosen, with support and software maintenance included, from Basis alone to Basis with digital document processing, Posteingang PLUS or both. Each add on has its own unit, with Expert AI licensed per user, Client Onboarding and Compliance Check per notary with a volume package, Wissensmanagement per office and SMART Beleg per VAT number. Every figure comes in an individual quote after a consultation, and open training sessions and webinars are included.

Source: Vendor Published
BB on Firm and Practice CoverageSegment and practice coverage is described with substance, short of the boundaries: what is supported is clear, what is not is left open.

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.

German notarial offices, including lawyer notaries, are the market, and the product follows German registers and professional rules from the side file under section 43 NotAktVV to trade register filings through XNotar. It covers party intake, KYC and sanctions checks, deed preparation, mail and document handling, and billing, with a DATEV interface for lawyer notaries who keep their attorney files there. Expert AI scopes run from one document to the whole office collection. Nothing in the product serves offices outside Germany.

Source: Vendor Published
Sources on file

5 public documents

The public pages on file for TriNotar, 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.

Pricing

No published figure

  • TriNotar is priced per user per month by package.
  • Choose Basis, Basis with digital document processing, Basis with Posteingang PLUS or both modules.
  • Support and maintenance are included.
  • Expert AI is a separate per user license.

The monthly price depends on the number of users and the modules chosen, and each office receives an individual quote after a consultation. Each add on has its own unit, with Expert AI licensed per user, Client Onboarding and Compliance Check per notary with a volume package, Wissensmanagement per office and SMART Beleg per VAT number.

Implementation: Open training sessions and webinars are included. Tailored training is booked and priced separately.

Legal Signals

What each signal means

A 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.

Confidentiality and Privilege

Client Data in Training

Can material a lawyer puts into this product be used to train a model?

Never, in the contract

The published terms prohibit training on customer content. Not a policy page, the agreement.

Data passed to Expert AI is expressly excluded from training and fine tuning of the language models, processing is limited to performing the contract, and each customer's collection is kept separate.

Source: Vendor Publishednicht zu Trainingszwecken bzw. zum Finetuning der LLM’s genutztAs of Nov 21, 2026Evidence

Prompt and Output Retention

How long does the product keep what a lawyer typed, and can that be set to zero?

Customer controlled, no zero option

The customer controls the retention window, by product configuration or by contractual instruction, but zero retention is not stated as available.

The office can have its vector collection deleted at any time, and it is deleted when the relationship ends. Backups run daily and weekly, encrypted and offsite, but prompts, outputs and backups carry no stated period.

Source: Vendor PublishedDie Vektordatenbank kann jederzeit auf Wunsch des Kunden gelöscht werden.As of Nov 21, 2026Evidence

Ethical Walls and Matter Segregation

Does retrieval respect the firm’s ethical walls, or can the model read across them?

Own model, documented

The product maintains its own permission model, documented, requiring the firm to keep it aligned.

Each customer's vector collection is kept apart, and Matter Chat reads only the selected matter. Plus widens retrieval to the whole office collection.

Source: Vendor Publishedgetrennt nach Kunden verwaltetAs of Nov 21, 2026Evidence

Third Party Request and Subpoena Notice

If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?

Not addressed

No located term or policy addresses third party requests for customer data.

Processing follows the customer's instructions under the processing agreement. No commitment covers notice to the office before its data is produced to a third party.

Source: Vendor Publishedin seinem Auftrag und nach seiner AnweisungAs of Nov 21, 2026Evidence
Accuracy and Authority

Primary Law Corpus Provenance

Where does the law in this product come from, and does the vendor have the right to use it?

Not addressed

No located public material identifies the corpus behind the product’s answers.

The knowledge graph rests on a legal collection of about 900 million tokens, and answers also read office documents and optional outside sources. No source list or license for that collection is given.

Source: Vendor Publishedumfangreiche juristische Datenbank mit 900 Millionen TokensAs of Nov 21, 2026Evidence

Good Law Verification

Does the product tell you when the authority it just cited has been overruled?

Prompts the user to verify

The product instructs the reader to check the citation without performing the check.

The office must review and correct AI output before relying on it. Clause review and research run without a citator showing the current status of an authority.

Source: Vendor Publisheddurch menschliche Überprüfung und Korrektur des OutputsAs of Nov 21, 2026Evidence

Refusal and Uncertainty Behavior

What does the product do when the answer is not in the corpus?

Not addressed

No located public material addresses what the product does when it cannot ground an answer.

Expert AI returns research and drafts for review, and the office answers for their accuracy. No rule covers what the assistant does when the sources do not support an answer.

Source: Vendor PublishedGenauigkeit oder Vollständigkeit des OutputsAs of Nov 21, 2026Evidence

Fabricated Citation Record

Does a public court record exist addressing fabricated or hallucinated legal citations in output from this product?

None located

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.

Expert AI drafts and reviews material inside the notarial office, and no court decision in the AI Hallucination Cases database names TriNotar.

Source: Bar Guidance or Court RecordAs of Nov 21, 2026Evidence
Professional Responsibility

Bar Guidance Alignment

Has the vendor engaged in public with the ethics opinions its buyers are bound by?

Named guidance addressed

Public materials engage with at least one named ethics opinion.

The service is built around German secrecy duties under section 203 StGB and section 43e BRAO, and the conditions leave the legal review to the office. No chamber guidance on AI use is mapped to the workflow.

Source: Vendor Published§ 203 StGB, § 43e BRAOAs of Nov 21, 2026Evidence

Billing and Fee Posture

Does the vendor address what happens to the bill when the work takes an hour instead of six?

Fee record is the product

The buyer is the payer, not the biller. The product exists to review, author or benchmark legal fees, so the record of fees is the product itself rather than a byproduct of AI assisted lawyering. Typically sold to in-house teams paying outside counsel.

Notarial invoices are prepared in TriNotar and can be posted to the matching DATEV matter as receivables, with updated open items returned to the invoice header.

Source: Vendor Publisheddie aktualisierten offenen PostenAs of Nov 21, 2026Evidence

Outside Counsel Guideline Readiness

Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?

Subprocessors listed

A current subprocessor or model provider list is published.

The processing description names QNC GmbH, Microsoft, AWS, Google and Digital Ocean with the country where each holds data, all inside the EU or EEA, and the Expert AI terms come with the license. Anonymization can also run on the office's own server.

Source: Vendor PublishedQNC GmbHAs of Nov 21, 2026Evidence

Court Disclosure Support

If a judge’s standing order requires an AI disclosure, can the product produce one?

Partial record

Some elements of the record are available, short of a document level export.

The electronic file keeps document versions and feeds the register workflow. Any statement of AI use to a court or register stays with the office.

Source: Vendor Publishedeine neue Version anlegenAs of Nov 21, 2026Evidence
Contact

Correct a record, or ask how something was graded

Every grade and every signal on this index is drawn from public sources and dated. If a record is wrong, out of date, or missing an artifact the index did not locate, send the source and it will be reviewed and the record redated. Vendors are welcome to submit documentation. Nothing on this index is for sale, including a listing, a placement, or a grade.

AI Legal Index

The AI Legal Index is an independent index that tracks changes to AI vendors in legal. It holds 670 vendors across 9 categories, each graded on the same 15 capability axes and recorded against 12 legal signals, from public sources. No vendor pays for inclusion, placement, or rating.

Index Status
Last index update
November 21, 2026
The AI Legal Index is an editorial reference. It is not a regulatory body, not a law firm, and nothing published here is legal advice or a recommendation to retain or avoid a vendor. Records are verified against published sources, bar guidance and public court records. Where a record reads not addressed, the material was not located in public sources on the date shown. See the Methodology page for evaluation standards and limitations.
© 2026 AI Legal Index
3801 N Capital of Texas Hwy, Ste E240 · Austin, TX 78746