Recent Discussions
Introducing Q Assist:Context-aware Gen AI underpinned by the Quantexa Decision Intelligence Platform
At QuanCon 2025 in March we announced that the first release of Q Assist was coming out of a pilot phase and would soon be made available to license for both existing and new customers. Q Assist is now available in Early Access and can be deployed in solutions and platform deployments on version 2.7. So, what is Q Assist? Q Assist brings Generative AI capabilities to our Decision Intelligence Platform and the solutions we offer at Quantexa. It is a modular platform component that includes a conversational UI, orchestration capabilities, configuration settings, and scalable APIs for copilots and LLMs. It embeds itself into everyday tasks and workflows for a more productive workforce and is grounded in the connected and contextual data and functionality our Decision Intelligence Platform offers. Q Assist connects a customer licensed and deployed LLM and the Quantexa Decision Intelligence Platform. It works alongside Quantexa users, embedding itself into everyday tasks and workflows and is grounded in the full set of data and functionality our Decision Intelligence Platform offers. Check out our Q Assist FAQs for more information. Who can license Q Assist? Q Assist is available in Quantexa Platform version 2.7 and is licensable as an add-on to existing Financial Crime, Fraud, Customer Intelligence, KYC, and Risk solutions. In this release, Q Assist is limited to customers in EMEA and North America for English Language deployments only. *For more information on licensing and pricing please contact your Technical Account Partner or schedule a demo here. Core components of Q Assist This Generative AI Technology Suite is made up of 3 core components. Q Assist Copilot (Available in Early Access release) An intelligent AI copilot that delivers instant, context-driven insights through natural conversation. The copilot works alongside Quantexa users revolutionizing how you work by surfacing critical data and context, streamlining repetitive and time-consuming tasks, and generating reports through a natural language interface. The Prompt Library (Available in Early Access release) A centralized repository of trusted prompts that standardizes data interactions, report writing, and investigation and research tasks across teams. The Orchestration Layer (Coming soon) Q Assist's orchestration layer is the “conductor”. A unified AI integration hub that streamlines data flow, coordinating multiple systems and workflows seamlessly. It ensures that user inputs are processed, and contextual data is incorporated from relevant platform components, and outputs are generated in a coherent, consistent, and explainable manner. The orchestration layer handles tasks like: Ensuring that the correct context is applied to each request Retrieving and integrating information from multiple sources to enrich the response Coordinating workflows and routing requests to the appropriate models and platform components, applying business rules and guardrails, using an agentic architecture Integration with existing licensed or customer-built copilots Q Assist in Action You can see Q Assist in action with our interactive demo in our Community Demo Hub and below we have highlighted some of the core features of Q Assist highlighting the benefits of each. Research Assistance: Q Assist streamlines access to a connected and contextual data foundation through an intuitive conversational interface. This functionality empowers users to instantly retrieve critical insights by talking to their data. Insights about customers, counterparties, suppliers, transactions are available through natural language queries which informs more thorough and faster investigative and research processes with rich contextual insights. By enabling self-service access to essential data, you can: Significantly reduce dependencies on dedicated data teams, Cut down manual research time while Deliver accurate and trusted information to those who need it when they need it As a result, investigation teams, relationship managers, analysts can benefit from enriched data that highlights hidden risks and identifies overlooked opportunities, allowing for quicker resolution of complex cases. This level of immediate, detailed access not only accelerates investigations but also enhances relationship management and customer service productivity, leading to a more responsive and personalized customer experience. Prompt Library The Prompt Library feature in Q Assist is designed to centralize and streamline the creation, management, and sharing of trusted prompts across teams. This tool allows you to build role-specific queries that can be easily reused across functions, ensuring that data interactions are both consistent and secure. With the Prompt Library, you can: Foster controlled, repeatable workflows for decision-making Level the playing field across your organization—making every analyst as effective as your top performers Establish consistent and secure workflows that adhere to best practices and compliance standards The Prompt Library empowers your teams to achieve optimal efficiency and alignment with organizational goals. Report Generation Q Assist’s Report Generation feature enables you to streamline the creation of a wide range of reports from SARs and EDDs to intelligence reports, risk assessments, and executive summaries, all with a single prompt. This functionality uses predefined templates to build consistency in reporting for various types of reports, such as escalations and SARs, or even customer emails and talking scripts. As a result, users can: Dramatically reduce the time it takes to create and process standardized reports Ensure data accuracy across multiple report formats Reinforce consistent and standardized reporting processes Reduce errors through predefined workflows Overall, the Report Generation feature helps reduce the time spent preparing for customer meetings, ensuring that summarized information is readily available for strategic decision-making. Contextual RAG Q Assist grounds every AI-generated response in rich, contextual data, significantly reducing the risk of hallucinations and inaccuracies. By anchoring outputs in relevant organization specific data and information, this feature Champions transparency with fully traceable and explainable responses. Increases trust and adoption internally Ensures you meet stringent regulatory requirements. Each response is not only more reliable and accurate, but it also comes with clear explanations that empower users to understand the underlying rationale and data behind every decision, ensuring that data-driven insights remain both effective and explainable. More information on Contextual RAG: Pre-recorded Webinar: Your AI Copilot is Only as Good as Your Data Foundation Blog post: Your AI Copilot is Only as Good as Your Data Foundation Underpinned by the Quantexa Decision Intelligence Platform and tailored to critical industry use cases, Q Assist empowers teams to close the gap between data and decision igniting a more productive workforce. Get in touch today to see how Q Assist can revolutionize the productivity of your frontline staff.
New and Improved Search Functionality
We’re excited to announce that our new and improved Search capability has now moved to General Availability as of 2.7.7. (this is referred to as Search 2 within our technical documentation). Let’s face it – the current Search experience came out with the first versions of the Quantexa Platform and needed a facelift. Although it did the job, and quite a good one at that, we received feedback from Quantexa users that gave us ideas on how to overhaul the functionality to both keep the UX consistent and to make it a lot more intuitive. Throughout this journey, we also found synergies in the Search setup process by coupling it up with our Data Fusion tool, and making Search a lot faster to set up. By the way, now you can explore our roadmap and give feedback on our features and functionality in our Product Roadmap & Ideas Portal! Be a part of our product development! How we brought Entities front and center From user feedback, we realized that the way users interact with the Search functionality can be improved by bringing more power to search using what Quantexa already knows about entities thereby optimizing the Search query construction. To enable this the Query Building aspects of the Search UI have been redesigned to reframe the search experience around the Entities available in the Platform. This gives the user the power to tell the system what they are looking for (which Entity Type) and then the system offers the most appropriate Data Sources and Search Fields to find the Individual, Business or other Entity the user wishes to search for. Before, the search results could sometimes be not exactly what -the user expected due to incomplete or sub-optimal search configuration. This brings us to our next update – new configuration through Data Fusion! How we simplified Search configuration If you are a Quantexa user, you might be familiar with the Search configuration process which is separate from entity resolution and tuning. What we figured is, if our users are overwhelmingly looking for entities in their searches, why not streamline the search setup up by ‘inheriting’ the settings from Data Fusion, where all the magic happens with entities. To be specific, you no longer manually have to define the search fields and groups yourself as we derive them from Fusion config. So you not only save efforts in setting up a tool, but you also get far better results from reusing the configuration that’s been tuned and tested. We have also improved some existing features: We have updated how our Results Filters work once the user has executed their query. It is now possible to filter using more than one item in the Filter list in the results screen. Additionally, we have improved the Table View of results. How we made Search faster If you are using new Search with our Entity Store then you are able to perform very fast direct Entity Searches even across massive amounts of data. The Entity Store keeps a pre-built version of your resolved entities available at hand, but also updates as soon as there are any changes or new data is introduced, so you get the speed without compromising on the content. How we made de-bugging faster Lastly, it is worth noting that this new version of Search has both re-used existing components within the Platform and is much simpler to support and de-bug than the old version of Search. Together this reduces the overall support burden on Quantexa’s R&D department – you might be thinking this is more of Quantexa benefit, but actually it means we are able to handle support requests faster and free up engineers to work on other enhancements to the Platform. What has been removed? At a fundamental level the new version of Search (known as Search 2 in our technical documentation) has feature parity with the old version of Search (Search 1) plus the new features already explained. However, there are several feature removals that are worth noting: As the Fusion configuration will now drive the search field mappings, there is no need to generate Search Fields anymore, thus we removed the feature altogether. We have removed the support for field boosting as the feature was deemed not useful by our users Facets have been replaced with Aggregations and can be easily migrated from the old Search to the new Search. We have removed the type ahead on Search Fields in the Search Bar as the query-building experience has been re-designed and this feature is no longer necessary. Deprecation and Removal of the old version of Search The old version of Search (Search 1) is deprecated at 2.8.0. We expect to remove the old version of Search from the Platform at the earliest at 2.9.0. All new customers are required to adopt the new version of Search from 2.7.7. onwards. View the New and Improved Search Demo Head over to Product Demos and launch the New Search Demo (login required) for an interactive walk-through of the new features included: Product Demos - Quantexa Community Take a self-guided tour through our interactive demos to see how the Quantexa Platform solves real-world challenges and unlocks powerful insights. How do I provide Feedback? We know this is not the end of the improvements necessary to our search capabilities, so expect to make further investments in the medium term. It would be valuable to hear feedback about the new Search results screen and the query editing experience. Please provide feedback directly to the Search initiative using the Product Roadmap & Ideas Portal. Future roadmap For the next 12 months we will not be making major changes to introduce new capabilities to our Search functionality. Our focus will be ensuring that as our existing customers upgrade and adopt this new version of Search and that the experience of migrating from old Search to new Search is as simple, fast and pain-free as possible. I encourage you to get started with the new Search functionality and let us know how you find it! Read the full release notes and Search 2 Migration Guide on the Documentation site.
2.7 Quantexa Upgrade Guide
Quantexa 2.7 Upgrade Guide The 2.7 Quantexa Upgrade introduces several important updates, and this guide provides additional guidance to support the transition. The upgrade includes: Core Product Changes: Migration to Data Lake, integrated ETL validation tools, updated Graph Script utilities, and more. Data Packs Migration: Steps for transitioning to Parsers 3 and 4, with guidance to help you decide which version to use. Feature Updates: Removal of Quantexa Incubators and changes to tools like the Transaction Viewer, with guidance available for transitioning to Data Viewer. Log in to access the full guide and learn how these changes may impact your implementation: 2.7 Quantexa Upgrade Guide - Quantexa Community Quick Upgrade Overview The 2.7 Quantexa Upgrade consists of three main parts: Core Product Changes Removal of Quantexa Incubators Data Packs Migration Most of the Core Product changes are automated migrations and minor adjustments* which can be tested in a local environment. Migration to Delta Lake is going to be the…
FinCrime Detection Pack 0.4 is now available
We are excited to announce version 0.4 of our FinCrime Detection Pack is now available in Early Access. This release introduces new features that will increase flexibility, improve score coverage and optimise score configuration to better capture desired behaviours, characteristics and events. This builds on the functionality released in version 0.3 of the FinCrime Detection Pack. Feature Highlights: You can now apply score logic on a targeted subset of transactions to help you uncover more specific underlying patterns that might otherwise be overlooked. You can now configure transaction score parameters based on the segment a score subject belongs to. This allows you to account for differences and ensure that you are capturing the behaviours and events you’re interested in. You are now enabled to select from a range of appropriate Event Windows to ensure that a score is targeting the desired behaviour or event. Target new risks with additional Score Types You can read more about the release in Detection Pack 0.4 Release (login required) For full details of the release, including compatible Quantexa Platform versions and minor enhancements, please see the Quantexa Documentation site. Release notes Migration guide
Welcome to Parsers 4.2 | Release Announcement
Alongside the release of QP2.7, we are happy to share the release of 4.2.0 of Standard Parsers. This release extends the cleansing options you can define purely in config - configurable simple generic cleansers. We have introduced new config-based cleansers that allow you to perform replacements in strings, remove and keep parts of a string based on pre-defined options, change the case of a string for different languages and to extract specific parts of input strings, all without writing any Scala. These back-end config improvements extend to the front-end. The users of QP 2.7 will have access to the extended configurability described above within the UI - more details are available in the release notes and documentation for QP2.7. The release also brings some key bug fixes and a small improvement to business parsing that should catch more edge cases of business names with odd punctuation distributions. For more information on the release features, please see the 4.2.0 release notes and for general info on Parsers, see the documentation.
Welcome to Quantexa 2.7 | 2.7.0 Release Announcement
We are pleased to announce the release of Quantexa 2.7.0. This release includes: Graph Scripting QSL (Early Access) Highlights Simplified Interface: Configuration-Based Expansions: Define Batch Graph Scripts using the Quantexa Scripting Language (QSL) with a simplified interface, reducing the need for custom Scala code. Enhanced Network Precision: Path-based Expansions: Use path-based Expansions instead of perimeter-based Expansions, resulting in tighter and more focused Networks. Efficient Data Processing: Data Pre-Filtering: Options to pre-filter data help minimize the volume of data that needs to be processed, enhancing overall efficiency. Improvements to the Entity Store Cost Efficiency and Performance: Reduced Elastic Utilization: New indexing format reduces Elastic resource usage by up to 40%, leading to significant cost savings. Smaller Index Size: Optimized Entity structure decreases index size by 60%, allowing projects to run on smaller Elasticsearch clusters. Operational Enhancements: Exclusion of Unchanged Entities: Logs can now exclude unchanged Entities, streamlining log management. Entity Version Tracking: Introduction of a version field in all Entities to track data updates, necessitating a full reload of Elasticsearch indices upon upgrade. Loading Improvements: Flexible Output Paths: Enhanced configuration accepts various path types for output locations, removing the need for file:/// prefixes. Parallel Load Execution: Specify Entity types for parallel loading, significantly reducing load times. Storage Optimization: Entities exceeding a threshold of records are stored without compounds, reducing Elastic storage requirements. REST API Enhancements: Advanced Query Capabilities: Support for the negation operator ! and wildcard queries * across all string attributes, enabling more complex and flexible searches. Pagination Support: Total hits in search responses help determine the availability of additional data, facilitating efficient data retrieval. For detailed migration steps and configuration settings, refer to the 2.6.x - 2.7.0 Migration Guide and relevant configuration references. New Global UI Configuration Service Highlights Streamlined Configuration Management: Unified Configuration Service: Global UI settings have been moved from the Explorer service to a new Global UI Configuration service, providing a centralized method for managing these settings. Dedicated REST API Endpoints: A new REST API allows programmatic access to global UI settings, enhancing integration and automation for users and Low-Code Configuration parts of the Quantexa UI. Future-Proofing and Intuitiveness: Intuitive Settings Location: This reorganization places global UI settings in a more logical location, facilitating easier management and future enhancements. Foundation for Future Improvements: While there is no immediate functional impact in the 2.7.0 release, this change lays the groundwork for future improvements in platform UI configuration. More information ➡️For more details on the release, see the 2.7.0 Release Notes on Platform Documentation. If you cannot access the Documentation site, please get in touch with your Quantexa point of contact or the Community team at community@quantexa.com. To receive updates on every release, click Subscribe in the top-right corner of the Release Announcements page (login required).
Detection Packs 0.3
What are Detection Packs? Detection Packs are a Scoring solution that enables projects to progress more quickly from resolved Entities and generated egocentric Networks to Alerts ready for investigation. Why are Detection Packs important? Using Detection Packs avoids the time and cost associated with writing the same Scores and Pipelines multiple times on different projects. This out-of-the-box Scoring solution provides a set of baseline Scores, so individual projects can focus on developing the complex Scores that match their specific needs. What is in this Detection Packs 0.3 Release? This release adds many new Scores to the FinCrime Detection Pack, and generally improves product maturity with new quality-of-life features. You can read more about the benefits of this Detection Pack release in @Greg_Jones's article (log in required): Detection Packs 0.3 Release For full details of the release, including all of the scores available, compatible Quantexa Platform versions and minor enhancements, please see the Quantexa Documentation site (log in required).Welcome to Quantexa 2.6 | 2.6.0 Release Announcement
We are pleased to announce the release of Quantexa 2.6. Highlights: Uncover insights in highly-connected data with QKnowledgeGraph [Experimental] Build and query Graphs quickly and easily with the new Graph API [Early Access] Vulnerability Management Configure Explorer through the Quantexa User Interface (UI) Reduce duplication and lighten workload with Mirror Alerting Uncover insights in highly-connected data with QKnowledgeGraph [Experimental] QKnowledgeGraph is a new capability for the analysis of data at scale. It allows the creation of Graphs from the full population of Entities and the application of Perspectives to specify important connections. It is a Python-based component that is now integrated with QPython. Fig: A graphical representation of a highly complex Graph. Why is this important? Knowledge Graph enables Data Scientists to perform Graph analytics, apply algorithms and build Machine Learning (ML) models on Graphs based on the full data which sits behind Quantexa Networks. The output of this analysis could be integrated into the Assess Scoring model as an Entity Score, that will influence Alerting and help to inform the Investigator/Analyst decision. The APIs and Python-based interface of QKnowledgeGraph make it easy for Data Scientists to master the tool. Build and query Graphs quickly and easily with the new Graph API [Early Access] The Graph API enables you to dynamically build and query graphs via a REST interface. You can define the shape of the graph that you want to generate using the Quantexa Scripting Language (QSL) and execute this without needing to define expansion logic in advance. The resulting graph can then be used to create an Investigation, or scored against the Assess scoring model. Why is this important? The new Graph API offers a quick and easy way to derive intelligence from our interconnected view of your data. It enables technical or data science user to build and query our Graphs without defining structure and expansions in advance, and without having to rebuild the application. They are now free to explore ad-hoc analysis of the Graph, enable Network Scoring in a streaming use case, or validate a Graph’s shape for batch Graph Scripting. Avoid critical threats with industry-leading Vulnerability Management From 2.6.0, we will be targeting zero vulnerabilities in every software release. To continue to address the dynamic landscape of cybersecurity threats, minor platform versions will be released on a monthly schedule, containing upgrades to dependent components that will remedy any identified vulnerabilities. In addition, major and minor open-source dependencies have been re-baselined and upgraded across almost our entire tech stack. This makes sure all releases going forward stay free from any critical or high-risk vulnerabilities. Why is this important? Nothing is more important than the security of your data. Historically, our approach to vulnerability management has been to monitor the vulnerabilities in dependencies to ensure that none pose a risk to the platform. While we are happy that this enables us to maintain a secure product, some Information Security processes may require a different approach. We now meet the stringent vulnerability management requirements outlined in NIST 800-53, an industry-leading cybersecurity standard. This grants you and your Information Security team greater control over the vulnerabilities in your IT infrastructure. It also consistently resolves all potential vulnerabilities and reduces your total cost of ownership of The Quantexa Platform by eliminating the need for manual review or lengthy exception processes. Configure Explorer through the Quantexa User Interface (UI) Explorer can now be configured directly through the UI. A user with appropriate privileges can configure the schema for a new Document or Entity Explorer type and an instance of it will be generated and auto-populated. They can then configure its display elements: aggregations, document viewer, results table and quick filters, through this instance before saving it and making the new type available to all users. Fig: UI-driven configuration of Explorer Why is this important? This enables less specialised technical users to configure their project's Explorer types, so that they can be easily set up and designed in line with specific use case and user requirements. This contributes to reducing the complexity of configuring the product, therefore reducing time to value and improving your ability to be self-sufficient. Reduce duplication and lighten workload with Mirror Alerting Mirror Alerting is an optional extension to the standard Alerting process that reduces duplicated Alerts, or Mirror Alerts, which may occur when two Alerted Subjects have a relationship and trigger the same scoring logic. Fig: Mirror Alerting Scenario Why is this important? In use cases like Correspondent Banking and Retail AML, relationship scores can cause double counting because both entities get a relationship risk trigger. The Mirror Alerting framework helps to identify the duplicated risks and reduce the volume of alerts the investigators have to process. The flexible logic allows to define the logic for matching Scores and identifying the mirrored risks. More information To receive updates on every release, be sure to click Subscribe in the top right corner of the Release Announcements page (login required to subscribe): Want to learn more? Check out the Release Notes on the Quantexa Documentation site. If you are unable to access the Documentation site, please get in touch with your Quantexa point of contact or the Community team at community@quantexa.com.
Welcome to Quantexa 2.2 | 2.2.0 Release Announcement
Welcome to Quantexa 2.2, your second major update to Quantexa 2. The highlights in this release are: Visualize geospatial path data in the Investigation Map View; New Data Viewer features; Improvements to the Investigations Timeline; A new tool, Assess Accelerate, to generate Scala code templates for Scoring. Geospatial Path Visualization You can now visualize paths over a time period in Investigation Map View, giving investigators additional context for geospatial data. Explore Geospatial Path Visualization Data Viewer Data Viewer is now more consistent with Transaction Viewer, as well as bringing in many features from Explorer directly into Investigations, including more filters, aggregations, and different types of Documents. New functionality includes: Refine filters, add a combination of filters from the Results table in the Data Viewer; A new feature enabling users to filter the Data Viewer from the Scoring Panel; Support for Significant and Shared Counterparties functionality, and graphical filtering. Explore Data Viewer Improvements to the Investigations Timeline The Timeline in Investigations has been re-designed with you in mind, giving more detailed control of timeframes and empowering you to investigate their data in a way that suits you. Explore the Investigations Timeline Assess Accelerate A new configuration-driven tool, Assess Accelerate, has been created to enable users to quickly get started with Scoring using Assess. This tool is integrated with the Repository Tool and allows you to generate code at the beginning of your Scoring setup. Explore Assess Accelerate Read the full release notes our Documentation site. You'll need to log in to access the site. Submit an access request to our support team.Welcome to Quantexa 2.3 | 2.3.0 Release Announcement
In Quantexa 2.3, you will find: Entity Store, a new component in our set of Entity Resolution capabilities; Introduction of Security Model V2, a new way to manage Role-Based Access and Control within The Quantexa Platform; Enhancements to Assess including Path Ranking, a new way to define paths; Support for Elasticsearch 8 and Spark 3.2. Entity Store In 2.3.0, we are introducing Entity Store in beta. Before 2.3.0, all interactions with the Quantexa UI and the Quantexa Mid-tier APIs depended upon resolving Entities on-the-fly (dynamically). The Entity Store allows a persisted or materialized view of Entities to be stored in the system. In this first release, the core Entity Store will load a full set of pre-resolved Entities produced by Batch Resolver, into Elasticsearch. The Entity Store can then be used by Explorer to enable querying of the underlying entities, as a Cache for Resolver to improve performance, and to support the new Entity REST API. Security Model V2 We have introduced a new framework for authentication and authorization across the platform. This gives the platform greater control over the data and features that a user can access and enables easier integration with Identity Providers (IdPs). End-users no longer need to interact directly with low-level Quantexa Roles. They are now able to share their work with Groups that are logical to their organizational structure. For example: UK Fraud Investigators. Using a new User Management Screen, you can now provision users and Groups, collections of users that can be assigned Roles and Dynamic Privileges, to The Quantexa Platform from Identity Providers simply and easily. Path Ranking It is now possible to specify the rules for defining the relative importance of paths, a chain of Documents and Entities that connect two Nodes, when writing Network Scores with Path Ranking, which make the Network easier to analyze by signaling the most significant areas to explore further. Dual Context Sources Dual Context Sources enable scoring logic to be designed that will work in both batch and dynamic, and provides a config-based tool that generates Source steps for both pipelines. This simplifies the deployment of a build with a dual architecture. Support for Elasticsearch and Spark Quantexa now supports Elasticsearch 8 across the platform, except for Offline Indexers and Spark 3.2 is now supported across the platform. Warning: Spark 3.0 is deprecated and support will be removed completely in the next release of the platform. Spring Boot upgrade Spring Boot has been upgraded to version 2.6.8. This results in faster startup times and solves a number of security vulnerabilities found in older versions of Spring Boot. Documentation Site Glossary We have completely revamped and reworked our Documentation site glossary, adding almost 100 new terms. Explore the Glossary to find out more. Other highlights For more control and flexibility when running ETL, Quantexa has has added the ability to generate Resolver Search Loader and Compound Creator scripts at the point where users define a Root Model in Data Fusion. List inputs have been introduced for Entity Attribute functions, to allow for more flexibility and customizability, granting users more ways to define Entity Attributes in Data Fusion, and cater to a wider range of data models. You are now able to collapse the Query Builder in Explorer. This is the next step in improving the user experience of Explorer, allowing users to focus on the results of the query. You will find the full set of Release Notes on the Quantexa Documentation site. If you are unable to access them, you will need to get a user with access to submit a Documentation site access request through the Quantexa Support Portal.
