Newcode
Newcode is a workspace that sits across the systems a legal team already runs and puts AI on top of all of them at once. Rather than holding documents itself, it connects to them, claiming reach into more than 750 Model Context Protocol servers and naming Outlook, iManage, SharePoint, OneDrive, Teams and the Microsoft Office applications among them, so a lawyer can ask for an engagement letter drafted from a matter in Outlook using historical letters in SharePoint as fee benchmarks and have the work run end to end. Two products sit on that connective layer. Nova is the assistant: it searches the firm's own material and external sources, returns referenced answers grounded in what it retrieved, and carries tools for matrix review across many documents, jurisdictional comparison, deep research, document management search and audio transcription. Aurora is the engine underneath, a visual builder in which a firm assembles its own agentic workflows from components including agents, prompt templates and model selection, then deploys them. Retrieval is agentic rather than a single lookup, with the system planning, searching, evaluating and iterating until it has the right context, bounded by the taxonomy, labels and walls the firm defines. Control is the other half of the pitch: matter-level configuration, granular permissions, audit, a choice of language model, and cloud or local deployment. It is sold to law firms, in-house teams, insurers, banks and government bodies, and its customer list names Kirkland & Ellis, DLA Piper, Reed Smith, Wolters Kluwer, The Bar of Ireland and several Norwegian public agencies. Newcode.ai AS is headquartered in Oslo with offices in Stockholm, Dublin, New York and Palo Alto.
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.
Remove the models and the product has no reason to exist. Newcode holds no documents of its own; it connects to the systems a firm already runs and everything it adds on top is model-driven. Nova retrieves, analyses and drafts with referenced answers. Aurora is described as the AI-native intelligence engine at the heart of the platform, a builder in which a firm assembles agentic workflows from agent nodes, prompt templates and a language model selector. Retrieval itself is agentic rather than a lookup, the vendor describing an agent that plans, searches, evaluates and iterates until the context is right. The published capability list is the same picture in one line: workflow orchestration, contract review, case-law analysis, knowledge ingestion, data structuring, document analysis, structured outputs, legal reasoning and governed execution. Strip out the models and what remains is a permissions and connector layer with nothing to run, which is why the vendor calls the product an AI harness rather than a workspace with AI in it. Checked 5 September 2026.
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.
The retrieval method is described rather than asserted, and nothing about accuracy is measured. Nova is stated to return referenced answers grounded in the firm's own data or external verified sources, with grounded referenced responses given as a product bullet in its own right. More usefully, the retrieval architecture behind that is set out: the retrieval agent plans, searches, evaluates and iterates until the context is right, guided by firm-defined taxonomy, labels and walls. That is a described method with a stated stopping condition and a stated constraint, which is more than most records in this lane publish and is what the band asks for. The sources are the firm's own documents and named external sources, so a reader can open what an answer rests on. What is absent is any test of it: no accuracy figure, evaluation, test set, error rate or statement of failure modes appears anywhere on the readable estate, and no accuracy or benchmark page exists. Nothing addresses hallucination in either direction, and no published agreement exists in which an accuracy position might otherwise sit.
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.
Control is offered as configuration the firm sets, and the boundary of autonomous action is never stated. What is published is real and is about capability rather than restraint: matter-level configuration, granular permissions, audit, firm-defined taxonomy, labels and walls, the ability to choose the model and set the guardrails without waiting on a release, and governed execution named among the platform capabilities. A reasoning trace is visible in the interface, shown as an expandable thought process against each output, which is a genuine review surface. What is missing is the account of what the system does alone. Aurora is sold on deploying agentic workflows at scale to automate complex processes, and the interface shows an Auto toggle on a running task, so the question of when the system acts without a person is raised by the product's own material and answered nowhere. Nothing states which outputs require review, what happens when an agent is wrong, whether generated work is marked as generated, or what guardrails can actually be set to. The band above requires a written commitment that the models work alongside a supervising lawyer, and no such commitment was located.
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.
The strongest named customer list in this pull, with no figure attached to any of it. The home page names, in text as well as logos, Kirkland and Ellis, DLA Piper, Reed Smith, Dickinson Wright, Wolters Kluwer, Robinson and Cole, The Bar of Ireland, Wiersholm, Haavind, Awilhelmsen, Ræder Bing, Simonsen Vogt Wiig, Ekko Advokatfirma and Helton, together with Norwegian public bodies including Helsetilsynet, Meteorologisk institutt and the Statsforvalteren offices, closing with a claim of more than one hundred law firms and enterprises. That is attribution a reader can check against real organisations. One testimonial carries a name and a role, Preben Brecke, Managing Partner at Haavind, describing the product as helping structure transactions, sharpen analysis and reach better decisions in private equity, M&A and complex disputes. What is entirely absent is measurement: no figure, no date and no described outcome accompanies any customer, and no case study was located on the readable estate. A customers page exists in the navigation and was not opened in this pass; it is named here as the limit.
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.
Walls are named as a product concept and no commitment about them can be read before signing. The home page states that retrieval is guided by firm-defined taxonomy, labels and walls, and that a firm gets governed, auditable, matter-level configuration with granular permissions over what each team can reach. Naming walls at all is unusual and it is why this is not the floor band. Everything else is unavailable. No customer agreement, master services agreement or data processing addendum exists on the estate, confirmed by a full footer inventory that carries only a cookie policy and a privacy policy. The privacy policy states in its own first line that it covers personal data collected when a visitor uses the website or the contact form, so it does not reach matter data. No statement on training use, no privilege or work product treatment, and nothing about what any model provider retains was located. The Vanta-hosted trust centre linked as the site's Security entry returned page metadata with no body on 5 September 2026 and is the rebuttal route; nothing is inferred from it in either direction.
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.
Nothing published addresses the advice line. No statement that Newcode is not a law firm, no disclaimer that output is not legal advice, no description of the professional judgement required before generated work is used, no jurisdiction limit and nothing on supervision or competence was located. There is no terms of service on the estate in which such a clause could sit, and the privacy policy is scoped to the website. The exposure is broad on this product because the published use cases are the work itself: drafting engagement letters, extracting court dates and deadlines from a scheduling order, conducting discovery, preparing trial submissions, providing strategic advice, and handling government applications, complaints and administrative proceedings. The band above does not fit, because it describes a boilerplate disclaimer sitting in the terms and no terms exist. Searched the home page in full, the legal page and the site footer inventory on 5 September 2026; the trust centre would not render and is the rebuttal route.
AI Governance and Bias Disclosure
Published governance over model behaviour: who owns it inside the vendor, what is tested before release, and what is disclosed about disparate output across matter types, parties, or populations.
No governance position was located. There is no responsible AI page, no principles statement, no accountable owner or function named for model behaviour, no pre-release evaluation regime, no management system and no certification such as ISO 42001. The vocabulary of governance is present in the product and means something different: governed execution, guardrails and matter-level configuration are controls a customer sets over its own deployment, not disclosure of how the vendor governs the models it ships. The privacy policy's automated decision-making clause addresses only website data and states that no solely automated decisions with legal effect are made there. The gap has a specific shape given the buyer list, which includes national public bodies and a bar association, and given a model-agnostic architecture in which the firm chooses the model: nothing published describes who is accountable for behaviour when the firm has selected the model and built the workflow. Home page, legal page and footer inventoried 5 September 2026; the trust centre would not render.
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.
Access control is published at product level and everything downstream of processing is unavailable. What is stated: granular permissions, matter-level configuration, firm-defined labels and walls governing what retrieval can reach, audit described as a platform property, and a choice of cloud or local deployment. That is a real access story. What is absent for customer data is retention, deletion, incident practice and any subprocessor list, none of which appears anywhere readable. The privacy policy is thorough and covers the wrong subject: it states retention periods of twelve months for contact-form correspondence and ninety days for technical logs, tabulates GDPR legal bases, names transfer mechanisms and lists three website providers, Vercel, Resend and Cloudflare Turnstile, while confining itself by its own first line to data collected through the website. No agreement exists on the estate to carry the rest. The Vanta trust centre linked as the site's Security entry returned metadata with no body on 5 September 2026, so its contents are neither credited nor held against the vendor, and it is the rebuttal route on this row.
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.
Nothing published addresses who bears the loss when the system is wrong. The site footer was inventoried in full on 5 September 2026 and carries two legal documents, a cookie policy and a privacy policy, both reached through anchors on a single legal page. There is no terms of service, no master services agreement, no customer agreement and no data processing addendum anywhere on the estate, so no indemnity, liability cap, warranty position, disclaimer of warranties, service level commitment or insurance statement can be read before entering a sales process. The privacy policy is scoped to website visitors and allocates nothing. The band above does not fit, because it requires a standard limitation clause disclaiming the exposure the product creates and there is no clause of any kind. The exposure is not theoretical on a platform that drafts filings, extracts court deadlines and runs agentic workflows for government bodies and international firms. The trust centre would not render and is the rebuttal route.
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 most substantial integration story in this pull, short of documentation an implementer could work from. Newcode's premise is that it connects rather than replaces, and the named counterparties are the systems legal work actually lives in: iManage for document management, Outlook, SharePoint, OneDrive, Teams, and Word, Excel and PowerPoint, delivered through what the vendor describes as seamless reach into more than 750 Model Context Protocol servers. What moves is described at workflow level rather than left as logos, with a published example of drafting an engagement letter from a matter in Outlook using historical letters in SharePoint as fee benchmarks, a DMS search tool inside the assistant, and review, redlining and feedback carried out directly in Word. The vendor's own framing, that context follows the matter rather than the tool, is the correct description of what this axis measures. What is missing is depth a buyer could plan against: no field mapping, sync direction, trigger condition or permission model is documented, no developer or configuration documentation was located, and the 750 figure is a count rather than a list.
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.
The deployment limb is answered with a real option and the region limb is not addressed at all. The home page states that a firm gets cloud or local deployment options, which offers a self-hosted route rather than the single multi-tenant cloud most records in this lane assume, and pairs it with matter-level configuration and granular permissions over what each team can reach. A local deployment option is the strongest form the tenancy question can take, since it puts the customer in control of the environment entirely. Against that, no region is named anywhere for the hosted option, no cloud provider is identified for it, and no residency commitment appears in any readable material. The only geographic facts published are corporate, offices in Oslo, Stockholm, Dublin, New York and Palo Alto, which locate the company rather than the data, and the privacy policy's transfer section concerns website personal data by its own scope. This is the documented band gap where one limb is answered cleanly and the other not at all.
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.
A real trust portal on a recognised compliance platform, and nothing verifiable from outside it. The site footer links Security to a dedicated trust subdomain hosted on Vanta, which is the artifact this axis asks about and is materially more than a badge image; several records in this pull display certification marks with no portal behind them at all. What could not be established is anything inside it. The page returned title and metadata with no body on 5 September 2026, so no standard, certifying body, examination period, scope statement or report is establishable, and whether the portal fulfils on an email address or requires a sales conversation is unknown. No certification is claimed anywhere in the readable text of the estate, and no badge appears on any page. Under the convention for gated artifacts, where the access tier cannot be established the lower tier is graded and the reason stated, which is what this note does. This is the cheapest available upgrade on the record.
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.
Model choice is sold as a feature and no model or provider is named. The vendor offers the flexibility to use the language model that works best for a firm, tells buyers to choose the models and set the guardrails without waiting on a release, and shows a language model selector inside an agent node in its workflow builder, so a model layer is not merely acknowledged but made configurable. Naming which models are on offer is the next sentence and it is never written: no provider, no model family, no version and no hosting arrangement for any of them appears in the readable estate, and no commitment to notify customers when the available set changes was located. A model name appears in one interface illustration and is treated here as artwork rather than disclosure, since nothing corroborates it. The question carries weight in proportion to the architecture: a platform whose selling point is model flexibility across a firm's whole document estate is precisely where a buyer needs the list. The trust centre would not render and is the rebuttal route.
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 pricing information is published at any level, including the unit of charge. There is no pricing page in the site navigation, which carries solutions, academy, customers, security, about, news, careers and contact, and none in the footer, which carries only the cookie and privacy policies. Every commercial route on the estate is the same single call to action, book a demo. Nothing states whether the platform is licensed per user, per firm, per workflow, per agent run or on consumption, which is a live question on a product sold on agentic execution at scale where usage and cost would ordinarily be linked. No tier names, minimum commitment, term length or implementation cost appears, and because no terms of service or master agreement is published either, the payment provisions that would ordinarily disclose a charging structure are also unavailable. A buyer can learn nothing about cost without entering a sales process. No pricing row is owed on this record.
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.
Five buyer segments are described with distinct substance, and the boundary is never drawn. Law firms are addressed on billable capacity and firm-wide standards; in-house teams on standardising routine work, traceability and turnaround; insurance on matching claim facts to policy wordings and endorsements and surfacing coverage grants, exclusions and conditions precedent; banking and financial institutions on analysing facility agreements, loan agreements and master agreements at volume with review and redlining in Word; and government on case handling across applications, complaints, investigations and administrative proceedings. Each names the instruments and the work of that sector rather than restating a generic pitch, and the customer list corroborates the spread, running from international firms to a bar association to national public agencies. Practice depth is evidenced by named capabilities including fund formation, case-law analysis and jurisdictional comparison. What is absent is the limit: no jurisdiction is stated despite a Nordic base and US offices, no firm size band is given, nothing identifies a practice area or matter type the product does not suit, and nothing addresses the languages supported.
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?
No customer agreement, terms of service or equivalent contract is published on any surface located, and no policy page states a position on training. Nothing is granted and nothing is withheld, so a client has no term to hold the firm to. Where a policy page does state a position, the row takes the matching policy value instead and the summary records that no agreement exists.
No located term or policy addresses the question either way. The agreement search this value requires was run against a full footer inventory on 5 September 2026: the estate publishes a cookie policy and a privacy policy, both reached through anchors on one legal page, and no terms of service, master services agreement or data processing addendum exists. The privacy policy states in its first line that it explains how personal data is collected when a visitor uses the website or the contact form, so it does not reach customer matter data and says nothing about model training in either direction. No product page states that customer content does or does not train models, and no opt-out or configuration setting is described, on a platform whose own architecture invites the question by letting a firm select the model. The Vanta-hosted trust centre linked as the site's Security entry returned page metadata with no body on the same date; it is the rebuttal route and nothing is inferred from it.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
No located public material states how long prompts and outputs are retained.
No located material states how long anything the platform handles is kept. The privacy policy does state retention periods, and they are precise and unusually well drafted, ordinarily twelve months for contact-form submissions and related correspondence and ninety days for technical and security logs, with longer retention where required by law. None of that reaches this signal, because the same policy confines itself to personal data collected through the website and the contact form. Nothing addresses retention of documents retrieved from a firm's connected systems, of the context assembled by the retrieval agent, of prompts, or of the outputs and workflow runs Aurora produces. No deletion or return-of-data commitment for customer material was located and no agreement exists on the estate to carry one. Searched the home page, the legal page and the footer inventory on 5 September 2026; the trust centre would not render.
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.
Walls are named as a control the firm defines, and no mechanism behind them is published. The home page states that the retrieval agent plans, searches, evaluates and iterates guided by firm-defined taxonomy, labels and walls, and separately offers governed, auditable, matter-level configuration with granular permissions determining what each team can reach. Naming ethical walls as a first-class concept, and tying them to what the retrieval agent may see rather than only to what a user may open, is the right shape for this signal and rare in this corpus. What is absent is any account of how the boundary is enforced: nothing states whether the platform is single or multi-tenant, how a wall is configured or audited, what happens when an agent traverses connected systems that carry their own permissions, or whether walls survive the more than 750 external connections the product claims. No administrator documentation was located, and the trust centre would not render.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
No located term or policy addresses third party requests for customer data.
No located term or policy addresses third party requests for customer data. The confidentiality section of a master agreement is where this evidence normally sits and no such agreement is published on the estate. The privacy policy does address the subject for the data it covers, listing public authorities, courts and regulators among recipients where required by law, and it commits to no notice, reserves no discretion over notice and publishes no transparency report; that provision governs website and contact-form personal data by the policy's own stated scope and does not reach a firm's matter content. Nothing published states what happens when material held or reachable through the platform is demanded by subpoena, court order or regulatory process, which is a live question for a vendor whose customers include a bar association and national public bodies. Searched the home page, the legal page and the footer inventory on 5 September 2026; the trust centre would not render and is the rebuttal route.
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.
The corpus is the firm's own estate and the external half is named only as a category. Newcode's design point is that it retrieves from the systems a firm already runs rather than from a database of its own, and the vendor describes the result as firm-owned intelligence, so the primary material behind an answer is the customer's. Nova is also described as searching legal and external sources and returning answers grounded in the firm's data or external verified sources, and case-law analysis and legal research appear among the published capabilities, so primary law does enter the product. What is missing is any identification of it: no publisher, database, jurisdiction set or licensing position is stated for the external legal material, and verified is asserted without saying verified by whom or against what. A jurisdictional comparison tool is offered without naming the jurisdictions it covers. Searched the home page in full, the legal page and the footer inventory on 5 September 2026.
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.
Nothing addresses checking authority for subsequent history, on a product that does reach primary law. Case-law analysis and legal research are both named among the published capabilities, Nova carries a legal research tool and a jurisdictional comparison tool, and answers are described as grounded in external verified sources. No citator, treatment signal, currency check or good-law verification is described anywhere, and nothing states what verified means or who performs it. That gap sits differently here than on a contract or investigations product, because this platform is sold to litigation practices and public bodies for research and analysis, so an authority that has been overturned is a live failure mode rather than an inapplicable limb. Searched the home page, the legal page and the footer inventory on 5 September 2026; the product pages for Nova and Aurora were not opened and are the rebuttal route.
Refusal and Uncertainty Behaviour
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.
No located material describes what the system does when it cannot ground an output. One adjacent mechanism is published and is recorded because it comes closer than most: the retrieval agent is described as planning, searching, evaluating and iterating until the context is right, which implies an internal sufficiency test on retrieved context. Nothing states what happens when that test never passes, whether the agent stops, reports the gap, or answers anyway, and no confidence indicator, abstention path or no-answer state is described. A reasoning trace is visible in the interface as an expandable thought process, which shows what the system did rather than how certain it was. Nothing addresses behaviour when a connected system is unreachable or a firm's walls exclude the material an answer would need, which on this architecture is the ordinary case rather than an edge one. Searched the home page, the legal page and the footer inventory on 5 September 2026.
Fabricated Citation Record
Does a public court record exist involving output from this product?
No court order, opinion or disciplinary record naming this product has been located as of the date shown. This is a statement about the public record, not a finding about the product.
The AI Hallucination Cases database maintained by Damien Charlotin was searched on 5 September 2026 on the product names Newcode, Nova and Aurora and on the corporate name Newcode.ai AS. No court order, opinion or disciplinary record naming the product or the company was located. One limitation is recorded rather than glossed: Nova and Aurora are common product names across the software industry and are less discriminating search terms than a distinctive one, so a negative result on those two carries less weight than the negative result on Newcode itself. This records the state of the public record on that date and is not a finding about the product.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions its buyers are bound by?
No located public material engages with bar or ethics guidance.
No located material engages with bar or ethics guidance at any level. No bar association, law society, rule of professional conduct, ethics opinion or regulator guidance is named or referred to in general terms, and nothing maps what a firm must do to discharge its own supervision and competence duties when agentic workflows it has built are running across its document estate. No advice disclaimer or statement that the company is not a law firm exists either, so there is no adjacent material of the kind that usually accompanies such a reference. The absence is conspicuous on this record for one reason worth stating: The Bar of Ireland appears in the vendor's own published customer list, so a professional body is a named customer while professional obligations are addressed nowhere. Searched the home page in full, the legal page and the footer inventory on 5 September 2026; the trust centre would not render.
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.
The billing consequence is named as a benefit and never addressed as a disclosure question. The law firm proposition is published as reducing repetitive administrative work and expanding firm-wide billable capacity, alongside compressing turnaround times, protecting quality at volume and expanding capacity so teams can deliver more. Expanding billable capacity is a direct claim about the economics of the work, and it is the closest thing on the estate to a statement about fees. Nothing follows from it. No per-matter record of AI-assisted work is described as available, no guidance on fee or disclosure treatment is published, and nothing addresses what a client is told when research, drafting or due diligence on their matter was produced by an agentic workflow the firm configured. The platform does capture the underlying material, since matters are described as traceable and execution as auditable, so the record exists and is offered for governance rather than for disclosure.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
No located public material supports a client side disclosure obligation.
No located material would let a firm answer a client's AI clause. No subprocessor register for the platform is published, no model or model provider is named anywhere, no cloud provider is identified for the hosted option, and no data processing addendum, consent pack or notification material exists on the estate. The only subprocessors published are three website providers named in the privacy policy, Vercel, Resend and Cloudflare Turnstile, which serve the marketing site rather than the product and do not touch client content. The gap is structural rather than incidental on this architecture: the platform is sold on model choice and on reaching more than 750 external systems, so the set of parties that may see client content is both larger and more variable than on a single-model product, and none of it is disclosed. The Vanta-hosted trust centre linked as the site's Security entry returned metadata with no body on 5 September 2026 and is the rebuttal route; nothing is credited from it.
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.
Elements of a record exist as a governance property, short of anything built for disclosure. The platform is described as keeping every matter traceable, as offering governed, auditable, matter-level configuration, and as exposing a thought process against outputs, so a firm can see what a workflow did and under what configuration it ran. Nova's answers carry references to the sources retrieved, which is the sources-retrieved element this signal contemplates and is the strongest part of it here. What is missing is the model and the artifact. No model or version is identified against any output, on a platform where the model is selectable and may differ between workflows and over time, so the record cannot say which system produced what. Nothing marks generated work as generated once it leaves the platform into a document, no record of human verification is captured, and no export is described for producing any of it to a court, a client or a regulator. No disclosure template or guidance is published.