Federal civilian · Moraph software

Patent & Trademark AI Examiner

Find the prior art and conflicting marks sooner, and leave every determination with the examiner

Book a demonstrationRequest a technical briefingFactsheet

Overview

What you are buying

The Patent & Trademark AI Examiner searches patent documents and scientific literature for prior art relevant to each claim of an application, and searches registered and pending marks for those that may conflict with a trademark application. It ranks what it finds, shows the passages that match each claim element, and keeps the full search history. Examiners decide what is relevant and make every determination; the tool records the searches behind them.

The problem it solves

Examiners have a limited amount of time for each application, and much of it goes into building search queries across several databases, reading through long result lists and recording what was searched. Relevant prior art may sit in a foreign-language document or a journal article that a keyword search misses, and similar marks may differ in spelling or sound rather than in letters. When a search is questioned later, during quality review, appeal or litigation, the record of where the examiner looked and why can be thin.

  • Searches are built by hand, query by query, across separate patent and literature sources
  • Keyword searches miss relevant documents that use different terms or another language
  • Phonetic and visual similarity between marks is hard to search consistently
  • The search record behind a determination is incomplete when it is reviewed later

Who uses it

  • Patent examiners and supervisory patent examiners in a national intellectual property office
  • Trademark examining attorneys and their managers
  • Search and classification specialists who support examination
  • Quality assurance staff who review the completeness of searches
  • Office leadership and oversight bodies who need to see how AI is used in examination

Requirements it supports

35 U.S.C. 102 (novelty) and 35 U.S.C. 103 (obviousness)35 U.S.C. 122 (confidential status of applications)Rules of practice in patent cases (37 CFR Part 1)Manual of Patent Examining Procedure (MPEP)Trademark Act of 1946 (Lanham Act, 15 U.S.C. 1051 et seq.)Trademark Manual of Examining Procedure (TMEP)

The product supports these requirements; meeting them remains your organization’s responsibility.

See how it works

A short walkthrough

Illustrative screens with fictional sample data. They show the workflow, not any client’s data or configuration, and the layout of the product itself differs. A live demonstration uses the product with sample data.

  1. Step 1

    The examiner's docket

    Examiners start from their assigned applications, with the status of each search.

    ApplicationTypeTechnology areaClaimsSearch statusAssigned
    Application SA-118 (fictional)PatentBattery electrode materials20Results ready4 days ago
    Application SA-131 (fictional)PatentWireless scheduling14Searching2 days ago
    Application SA-097 (fictional)PatentBattery thermal management26Claims amended, reopened3 weeks ago
    Application SA-140 (fictional)PatentElectrolyte additives9Not startedToday
    Examiners start from their assigned applications, with the status of each search.

  2. Step 2

    Claim elements

    The claim is broken into elements the search will cover, and the examiner can change the breakdown before searching.

    Application SA-118 (fictional) · Claim 1

    Claim type
    Independent, composition
    Elements identified
    4
    Suggested classes
    3, from the application
    Sources selected
    Patent collections, licensed literature
    Languages
    All available

    Elements

    • A cathode comprising a layered oxide
    • A surface coating of a phosphate compound
    • Coating thickness within a stated range
    • Retained capacity after repeated cycling
    The claim is broken into elements the search will cover, and the examiner can change the breakdown before searching.

  3. Step 3

    Ranked results

    Results are ranked against each element, with literature and foreign-language documents alongside patents. The ranking is a suggestion.

    DocumentSourceLanguageElements matchedExaminer decision
    Sample Patent Doc A (fictional)Patent collectionEnglish1, 2, 3Relevant
    Sample Journal Article B (fictional)Licensed literatureEnglish2, 4Possibly relevant
    Sample Patent Doc C (fictional)Patent collectionMachine translated1, 2Not yet reviewed
    Sample Patent Doc D (fictional)Patent collectionEnglish1Not relevant
    Results are ranked against each element, with literature and foreign-language documents alongside patents. The ranking is a suggestion.

  4. Step 4

    Matching passages

    Opening a result shows the passages that match each element, so the examiner judges relevance with the evidence in view.

    Sample Patent Doc A (fictional) · against claim 1

    Element 1
    Matched, paragraph 14
    Element 2
    Matched, paragraph 22
    Element 3
    Matched, table 2
    Element 4
    Not found
    Examiner decision
    Relevant

    Examiner notes

    • Coating range overlaps the claimed range
    • Cycling performance not disclosed; consider Article B for element 4
    • Added to claim chart for elements 1 to 3
    Opening a result shows the passages that match each element, so the examiner judges relevance with the evidence in view.

  5. Step 5

    The search record

    Everything the examiner searched and decided is kept, and exported to the case system with the claim chart.

    Application SA-118 (fictional) · Search history

    1. Claim elements reviewed and one element editedPatent examiner
    2. Search run across patent and literature sourcesTool
    3. Two additional keyword queries addedPatent examiner
    4. Twelve documents reviewed, three marked relevantPatent examiner
    5. Claim chart and search history exported to case systemPatent examiner
    Everything the examiner searched and decided is kept, and exported to the case system with the claim chart.

  6. Step 6

    Similar marks

    For trademark applications, marks that look, sound or mean alike are listed with overlapping goods and services for the examining attorney to assess.

    MarkStatusSimilarityOverlapping classesAttorney decision
    SAMPLEBRITE (fictional)RegisteredSound and appearanceClass 3For further review
    SAMPLE BRIGHT (fictional)PendingSoundClass 21Not conflicting
    BRITE-SAMPEL (fictional)RegisteredAppearanceNoneNot conflicting
    For trademark applications, marks that look, sound or mean alike are listed with overlapping goods and services for the examining attorney to assess.

Workflows

The principal workflows

  1. Understand the application

    The tool reads the claims, specification and classification of a patent application, or the mark, goods and services of a trademark application, and breaks them into the elements a search needs to cover.

    • Application loaded from the office's case system when it is assigned
    • Independent and dependent claims split into elements, or the mark split into its words and design elements
    • Suggested classifications and search terms listed with their source in the application
    • Examiner reviews and edits the elements and terms before searching

  2. Search

    Each claim element or mark is searched across the patent, literature and trademark sources your office makes available, using meaning as well as keywords, and across languages where the source supports it.

    • Searches run against each source the office has connected
    • Results ranked by how closely they match each claim element or the mark
    • Foreign-language documents shown with a machine translation marked as such
    • Examiner adds their own queries, which run alongside the tool's
    • Every query, source and date recorded in the search history

  3. Review

    The examiner reviews ranked results with the matching passages highlighted against each claim element, marks what is relevant and why, and sets aside the rest.

    • Results shown with the passages that match each element
    • Examiner marks documents as relevant, possibly relevant or not relevant
    • A claim chart builds from the passages the examiner accepts
    • For trademarks, similar marks are shown with the goods and services that overlap
    • Examiner notes recorded against each document or mark

  4. Record

    The examiner's selected references, claim chart and search history are exported to the office's case system to support the action the examiner writes. The tool does not write or issue office actions.

    • Selected references and claim chart exported to the case system
    • Search history saved as the record of what was searched
    • Quality reviewers can see the search alongside the action that followed
    • Searches reopened if the applicant amends the claims

Roles and permissions

Who does what in the product

Each role below is a starting point. During implementation we set them up to match your teams, and every action anyone takes is recorded in the audit trail.

Patent examiner

Patent examiner, primary examiner, junior examiner

Searches for prior art against the claims of assigned applications and records what was searched and found.

Sees

  • Applications assigned to them, with claims, specification and classification
  • Ranked results and matching passages for each claim element
  • Their own search history, notes and claim charts
  • Earlier searches on the same application, including before amendment

Does

  • Reviews and edits claim elements and search terms
  • Runs searches and adds their own queries
  • Marks documents relevant, possibly relevant or not relevant, with notes
  • Builds claim charts from accepted passages
  • Exports references, claim charts and search history to the case system
  • Reopens searches after claim amendments

Cannot

  • See unpublished applications not assigned to them
  • Delete search history or change a search record after export
  • Change source or model configuration
Approvals
Their determinations follow your office's existing signatory and supervisory review rules, which happen in the case system.
Notified about
New assignments, searches completed, and amendments that reopen a search.

Trademark examining attorney

Trademark examining attorney, senior attorney

Searches for marks that may conflict with assigned trademark applications and records the search behind each determination.

Sees

  • Trademark applications assigned to them, with the mark, goods and services
  • Similar registered and pending marks, with overlapping goods and services
  • Their own search history and notes

Does

  • Reviews the words and design elements identified in the mark
  • Runs similar-mark searches and adds their own queries
  • Marks results as conflicting, for further review or not conflicting, with notes
  • Exports the selected marks and search history to the case system

Cannot

  • See patent applications
  • Delete search history
  • Change source or model configuration
Approvals
Their determinations follow your office's existing review rules in the case system.
Notified about
New assignments, searches completed, and amended applications.

Supervisory examiner

Supervisory patent examiner, managing attorney

Oversees the examiners in their unit, reviews searches and manages workload.

Sees

  • Applications and searches for their art unit or law office
  • Search histories, claim charts and notes for their examiners
  • Workload and search status across the unit

Does

  • Reviews examiners' searches and adds comments
  • Requests a supporting search from a search specialist
  • Reassigns applications within the unit
  • Reviews AI use records for their unit

Cannot

  • Change an examiner's relevance decisions or notes
  • Change source or model configuration
  • Edit or delete entries in the audit trail
Approvals
Approves requests for supporting searches and reassignments in their unit.
Notified about
Searches reopened after amendment, supporting searches completed, and quality findings for their unit.

Search specialist

Search specialist, classification specialist, technical information specialist

Runs supporting searches for examiners and maintains search configurations and source mappings.

Sees

  • Applications they are asked to search
  • Source coverage and indexing status
  • Search configurations and classification mappings

Does

  • Runs supporting searches and returns results to the requesting examiner
  • Maintains classification mappings and saved search templates
  • Reports gaps in source coverage
  • Tests search configuration changes on past applications

Cannot

  • Mark documents as relevant on an examiner's behalf
  • Put a configuration change into effect without approval
  • See applications they have not been asked to search
Approvals
Configuration changes they propose are approved by the office's designated program owner.
Notified about
New search requests, indexing failures, and decisions on proposed changes.

Quality reviewer

Quality assurance specialist, review quality assurance staff

Reviews samples of searches so the office can show its searches are complete and consistent.

Sees

  • Sampled applications with their search history, references and notes
  • Quality findings and trends by unit and technology area

Does

  • Draws samples by unit, technology area or examiner
  • Records whether each search was adequate, with comments
  • Tracks findings until they are resolved

Cannot

  • Change the examiner's search record or decisions
  • Review their own work
  • Change configuration
Approvals
Their findings go to the supervisory examiner and quality management, who decide on follow-up.
Notified about
New review samples and responses to their findings.

Auditor (read-only)

Inspector general staff, internal auditor, oversight reviewer (under temporary access)

Reviews how searches were carried out and how AI was used, without being able to change anything.

Sees

  • Search records and AI use records within the granted scope
  • Model and configuration change history
  • Quality review results
  • The audit trail

Does

  • Searches and reads records within their scope
  • Exports records and reports, with each export logged
  • Leaves review notes where the office enables them

Cannot

  • Change, approve or delete anything
  • See records outside the scope and dates granted
  • Keep access after it expires
Approvals
Their access is approved by the program owner or an administrator, with a scope and an end date.
Notified about
Nothing by default; access granted and expiring is confirmed to the person who approved it.

Administrator

Application administrator, IT systems administrator

Manages users, roles and units on behalf of the office, without access to application content.

Sees

  • Users, roles, art units and law offices
  • Integration and indexing status
  • The record of permission changes

Does

  • Adds and removes users, or maps them from single sign-on groups
  • Assigns roles and units
  • Monitors integration and indexing jobs
  • Runs access review reports

Cannot

  • Open applications or search results
  • Grant themselves an examining role without a second administrator
  • Change model configuration
Approvals
Role changes that grant access to unpublished applications are approved by the program owner.
Notified about
Access reviews coming due, unused accounts, and failed integration jobs.

Permissions at a glance

ActionPatent exam.TM attorneySupervisorSearch spec.QA reviewerAuditorAdmin
View unpublished applicationsOwn work onlyOwn work onlyFullOwn work onlyView onlyView onlyNo access
Run prior-art searchesOwn work onlyNo accessFullOwn work onlyNo accessNo accessNo access
Run similar-mark searchesNo accessOwn work onlyFullOwn work onlyNo accessNo accessNo access
Mark relevance and add notesOwn work onlyOwn work onlyNo accessNo accessNo accessNo accessNo access
Build and export claim chartsOwn work onlyNo accessNo accessNo accessNo accessNo accessNo access
Request supporting searchesOwn work onlyOwn work onlyApprovesNo accessNo accessNo accessNo access
Reassign applicationsNo accessNo accessFullNo accessNo accessNo accessNo access
Record quality findingsNo accessNo accessView onlyNo accessFullView onlyNo access
Propose search configuration changesNo accessNo accessNo accessFullNo accessNo accessNo access
View AI use recordsOwn work onlyOwn work onlyView onlyView onlyView onlyView onlyNo access
View audit trailNo accessNo accessView onlyNo accessView onlyView onlyView only
Manage users and rolesNo accessNo accessNo accessNo accessNo accessNo accessFull
  • Full
  • Own work only
  • Approves
  • View only
  • No access

How access is controlled

  • Only examiners and examining attorneys mark relevance. Supervisors, specialists and reviewers comment and request, but do not change an examiner's decisions or search record.
  • Configuration and model changes are approved by your office's designated program owner, who sits outside the examining roles, and every change is recorded with the test behind it.
  • Roles are configured with you during implementation. You can rename them, create custom roles, and limit them by art unit, law office or technology area.
  • Staff sign in through your identity provider, every permission change is recorded in the audit trail, and auditors get temporary read-only access with a defined scope and an end date.

Features

What it does

Claim element breakdown

Claims are split into elements so each one can be searched and charted separately; the examiner can edit the breakdown.

Meaning-based search

Documents are found by what they describe as well as the words they use, alongside conventional keyword and classification searches.

Cross-language search

Documents in other languages are searched and shown with machine translations, clearly marked, for the examiner to check against the original.

Non-patent literature

Scientific and technical literature from sources your office licenses is searched in the same step as patent documents.

Highlighted passages

Each result shows the passages that match each claim element, so the examiner can judge relevance without reading the whole document first.

Claim charts

Passages the examiner accepts are assembled into a claim chart by element, ready to export to the case system.

Similar-mark search

Trademark applications are searched for registered and pending marks that look, sound or mean alike, with overlapping goods and services shown.

Design element search

Marks with design elements are searched by the design codes your office uses, alongside the words in the mark.

Complete search history

Every query, source, date and result the examiner reviewed is kept as the record of the search.

Examiner-controlled relevance

Only the examiner marks documents as relevant; the tool's ranking is a suggestion and is labeled as one.

Quality review view

Reviewers see the search history and selected references beside the action that followed, and record their findings.

AI use record

Each application records which AI functions were used, which model version produced the results and what the examiner accepted or rejected.

Integrations

How it connects to your systems

Connects toHowWhat flows
Case management systemApplications, claims, classifications and assignments from your office's examination case system, by API or scheduled transfer.In: application text, claims, classification and assignment. Out: selected references, claim charts and search history.
Patent document collectionsPublished patent documents from the collections your office holds or receives under its data exchange arrangements, indexed during implementation.In: patent documents, bibliographic data and classifications.
Non-patent literature sourcesScientific and technical literature from the databases your office licenses, searched under the terms of those licenses.In: abstracts, full text where licensed, and bibliographic data.
Trademark registerRegistered and pending marks, goods and services, and design codes from your office's trademark records.In: marks, status, goods and services, and design codes.
Single sign-onStaff sign in through your identity provider (SAML or OpenID Connect), including PIV-backed authentication where your office uses it.In: user identity and group membership for role assignment.
Work APISearch activity, AI use records and quality review results available to your data warehouse and reporting tools through the Moraph Work API.Out: search records, review outcomes and usage data.

Each integration is confirmed in discovery and specified in the design. See how an engagement progresses.

Security and privacy

How your data is protected

Confidential applications

Unpublished application content is visible only to the people assigned to it and their supervisors, supporting the confidentiality the law requires.

No training on your applications

Application content and examiner decisions are not used to train models shared with other clients.

United States hosting

Data is hosted in Moraph's United States region only, and support tickets from federal clients are handled only by US citizens with active security clearances.

Encryption and keys

Client data is encrypted, with keys Moraph staff cannot use without explicit, time-bound authorization.

Complete audit trail

Every search, view, relevance decision and export is logged with the person and time, and cannot be edited.

Tested releases

Every release passes security testing gates before it ships, and a software bill of materials is maintained for the product. Moraph is SOC 2 Type II and ISO/IEC 27001 audited.

Company-wide controls, independent audits (SOC 2 Type II and ISO/IEC 27001) and data residency are described in our Trust Center, where you can request the evidence pack.

Reporting

What you can report on

11 standard reports, grouped by who uses them. Each shows who it is for, how it can be broken down, how it is delivered and what it is used for. The data behind them is also available to your own reporting tools.

Operational

Search status by unit

For supervisory examiners

Assigned applications in each unit and the status of their searches, including searches reopened after amendment.

Break down by
Art unit or law office, Examiner, Search status, Application type
Delivered as
Live dashboard; CSV export
Used for
Seeing where searches are waiting and balancing work across the unit.

Supporting search requests

For supervisors and search specialists

Requests for supporting searches, who made them, who is working them and their status.

Break down by
Requesting unit, Specialist, Status, Technology area
Delivered as
Live view
Used for
Managing specialist workload and response.

Source coverage and indexing

For search specialists and administrators

Each connected source, when it was last updated, and any indexing failures.

Break down by
Source, Language, Update date, Status
Delivered as
Live view; scheduled email
Used for
Making sure examiners are searching current and complete sources.

Effectiveness

Suggestions accepted and rejected

For program owner, supervisors and quality staff

How often examiners marked tool-ranked documents and marks as relevant, by rank and source.

Break down by
Technology area, Source, Rank band, Period
Delivered as
Live dashboard; CSV export
Used for
Judging where the tool helps and where its ranking needs attention.

References cited by source

For program owner and leadership

References examiners cited, by source type, language and whether the tool or the examiner's own query found them.

Break down by
Source type, Language, Found by, Technology area
Delivered as
Live dashboard; PDF; CSV export
Used for
Understanding which sources and search methods contribute to examination.

Past-case comparison

For program owner and quality staff

For a set of already-examined applications, how the tool's results compared with the references examiners cited.

Break down by
Technology area, Model version, Test date
Delivered as
PDF and CSV export
Used for
Evaluating a model or configuration change before it is approved.

Quality

Quality review results

For quality reviewers and supervisors

Sampled searches, the reviewer's finding and how findings were resolved.

Break down by
Unit, Technology area, Finding type, Period
Delivered as
Live dashboard; CSV export
Used for
Targeting training and showing that searches are checked.

Reopened searches

For supervisors and quality staff

Searches reopened after claim amendments and the references added afterwards.

Break down by
Unit, Technology area, Period
Delivered as
Live view; CSV export
Used for
Understanding how amendments affect search effort.

Governance and audit

AI use record

For program owner, oversight bodies and auditors

Which AI functions were used on which applications, the model version, and what examiners accepted or rejected.

Break down by
Function, Model version, Unit, Period
Delivered as
Live view; PDF and CSV export
Used for
Answering questions about how AI is used in examination.

Model and configuration change history

For program owner and auditors

Every model or configuration change, the test behind it, who proposed and approved it, and when it took effect.

Break down by
Change type, Approver, Change date
Delivered as
Live view; PDF and CSV export
Used for
Evidencing that changes were tested and approved.

Audit trail extract

For auditors and inspector general staff

Who searched, viewed, decided and exported what, and when, for a selected application or period.

Break down by
Application, User, Action, Date range
Delivered as
On request in the product; CSV and PDF export
Used for
Answering audit requests and confirming that confidential applications were accessed only by those assigned.

Exports, access and evidence

  • Every report can be exported to CSV, and summary and evidence reports to PDF. Reports can be scheduled to arrive by email for the people entitled to see them.
  • Filters can be saved, so a supervisor or program owner keeps their own views by unit or technology area.
  • Search activity and AI use data are available through the Moraph Work API for your data warehouse or business intelligence tools.
  • Reports respect each viewer's role and the confidentiality of unpublished applications; aggregate reports do not reveal application content.
  • Governance and audit reports can be run as of a past date and give the same result each time. Running and exporting a report is itself recorded in the audit trail.

Deployment

Where and how it runs

Moraph cloud, United States

Hosted and operated by Moraph in the United States region, with data kept in the US.

Dedicated environment

A single-tenant environment for offices that require isolation, including isolated model hosting, scoped in the proposal.

With a managed service

Optionally run alongside a Moraph managed service for administration, source updates and integration support.

Security controls, independent audits and data residency are set out in our Trust Center. Engagement models and what drives a quotation are on Working with Moraph.

Implementation

What a rollout involves

The general phases are on Working with Moraph. For this product, they involve the following.

Source onboarding

We index the patent collections, literature sources and trademark records your office makes available, within the terms of each source's license.

Case system integration

Applications, assignments and exports are connected to your examination case system. We need interface documentation and a contact from the system's owners.

Evaluation against past cases

The search is run on a set of already-examined applications and the results compared with the references examiners cited, so your office can judge its usefulness before go-live.

Roles and workflow

Roles, art units or law offices, quality review sampling and export formats are configured to match your procedures.

AI governance documentation

We document the models used, their intended use, their known limitations and the human review steps, for your office's AI inventory and governance process.

Pilot and training

A pilot group of examiners uses the tool in selected areas for a period you choose, and examiners, supervisors and reviewers are trained on their own workflows.

Limitations

What it does not do

Worth knowing before you evaluate it.

  • It does not decide patentability or registrability. Examiners decide what is relevant and make every determination, and the office's procedures apply.
  • It can miss relevant prior art or conflicting marks. Its results supplement, and do not replace, the examiner's own search.
  • It searches only the sources your office makes available and licenses. Coverage of any source depends on what that source contains.
  • Machine translations can be wrong; examiners should check relevant passages against the original or an official translation.
  • It does not write or issue office actions; it exports references, claim charts and search history to your case system.
  • Moraph holds no FedRAMP authorization for this product. We provide control documentation to support your office's own authorization decision.
  • It is not designed for classified information, including applications under secrecy orders, which must be handled outside it.
  • Ranking quality varies by technology area and should be reviewed periodically with quality assurance staff.

Evaluation checklist

What to test in a demonstration or pilot

Questions worth putting to us, and to any other vendor you are considering.

  1. Run the search on already-examined applications and compare its results with the references examiners cited
  2. Ask examiners from different technology areas to work an application and note where results helped or misled
  3. Check machine-translated passages against originals for a sample of foreign-language documents
  4. Test similar-mark search on marks that differ by sound or spelling rather than letters
  5. Review the exported search history and claim chart against what your quality reviewers need
  6. Confirm that unpublished applications are visible only to the people assigned to them

Questions

Frequently asked questions

Does the tool decide whether a claim is patentable or a mark can be registered?

No. It finds and ranks documents and marks. Examiners decide what is relevant and make every determination under your office's procedures.

Can examiners still run their own searches?

Yes. Examiners add their own keyword, classification and other queries, which run alongside the tool's and are kept in the same search history.

Are our applications used to train models for others?

No. Application content and examiner decisions are not used to train models shared with other clients.

Which databases does it search?

The patent collections, literature sources and trademark records your office makes available and licenses. Sources are agreed and indexed during implementation.

Is it FedRAMP authorized?

No. Moraph holds no FedRAMP authorization for this product. We provide control documentation to support your office's own authorization decision.

How do we judge whether it helps?

During implementation the search is run on applications your examiners have already examined, and the results are compared with the references they cited, so your office can judge it on its own cases.

Next steps

Evaluate Patent & Trademark AI Examiner

Book a demonstration

See the product working with sample data, focused on your workflows.

Request a demonstration

Request a technical briefing

Architecture, integrations, security and hosting, with our engineers and your technical team.

Request a briefing

Factsheet

This page on two sides, to share with colleagues or add to your evaluation file.

Open the factsheet

Buying through a formal procurement? See How to buy for purchasing routes, accessibility conformance reports and company information. Documentation: Patent & Trademark AI Examiner guides on docs.moraph.com (getting started and security guides are public; setup, administration and integration guides are for client accounts). Support: Patent & Trademark AI Examiner support guide.

Related products