| 7.5.2 | 11-DEC-2024 | - we have introduced Follow-up Questions feature which will enhance Skypoint AI's capability to handle incomplete or unclear queries by prompting users with targeted follow-up questions. This will ensure more accurate and relevant responses to users, with the flexibility to skip follow-up questions.
- Our newly deployed API integration with the Reftab data source enables seamless regular data synchronization, point-in-time reporting, and support for both automated and manual triggers.
- The new SharePoint Excel Master Data Management Connector enables seamless import of master data from Excel datasets from SharePoint to the Skypoint Platform, streamlining workflows, ensuring data consistency, and enhancing collaboration in a unified environment.
|
| 7.5.1 | 27-NOV-2024 | - We have introduced distributed Azure subscription support for storage accounts, which enabled flexible data storage architectures alongside our Bring Your Own (BYO) feature for storage accounts, offering greater scalability and control for Skypoint users.
- Skypoint AI Copilot now utilizes chat history to provide accurate, contextually relevant responses, distinguishing between grounded and ungrounded inputs while adapting to context changes. It retrieves past responses, handles unrelated prompts independently, and combines relevant history to form complete queries, ensuring precise and efficient interactions.
- The newly deployed DrChrono API connector automates secure data retrieval for patients, appointments, and custom demographics, featuring automatic token refresh, cursor-based pagination, and flexible support for both incremental & full data loads to ensure efficient daily updates.
|
| 7.5.0 | 13-NOV-2024 | - We have enhanced Skypoint AI’s capability to ask follow-up questions for incomplete or unclear queries, ensuring it gathers all necessary information for accurate responses. This improvement elevates the user experience and supports scalable interactions across various use cases. In addition to that, We've enhanced search functionality by implementing parallel calls to both Hybrid Search and the Unstructured Search Agent, providing more accurate results and ensuring reliable access to relevant information.
- B2B Copilot for Medicare now offers advanced filtering options, allowing users to refine query and plan searches by state, county, zip code, drugs, and preferred providers for more accurate and personalized results. This enhancement minimizes data processing, enabling quicker access to specific information for faster response times.
|
| 7.4.9 | 30-OCT-2024 | - The Skypoint AI Copilot now supports French, allowing users to switch from English to French with a single click in the settings. This feature enhances accessibility and provides a more inclusive experience for French-speaking users.
- We've introduced enhanced flexibility for brand image uploads in Skypoint Studio, now allowing users to upload images of any dimension without restrictions, empowering users to freely personalize their brand images to better align with their unique brand identity.
|
| 7.4.8 | 16-OCT-2024 | - We've introduced multi-lingual support on Skypoint AI Copilot which will allow users to switch from English to Spanish with a single click in the settings.This enhances accessibility and provides inclusive experience for spanish speakers. Also we have enhanced provenance feature for unstructured data, which will display page numbers and provide direct link to the source. This improves traceability and transparency, allowing users to easily verify the origin of information within their data.
- Users can now enable or disable Bing Search for Skypoint AI Copilot via a simple interface in Skypoint AI Studio, enabling web data access to enhance response accuracy, user engagement, and satisfaction.
- We have deployed new Sitetelligence Connector, which will streamline data collection and long-term analysis, with daily updates and scalable storage.
|
| 7.4.7 | 03-OCT-2024 | - The agent architecture has been upgraded with a new DAG-based planner for more efficient execution of combination prompts, improving task management, processing speed, and reliability.
- We are excited to introduce the new Paycom Connector for Infinity Rehab which automates employee data transfers, provides real-time updates on payroll, attendance, and benefits, streamlining HR processes and reducing errors. In addition to this, we’ve also enhanced MRINexCore to support a broader range of data sources, including SQL databases and APIs, improving data integration flexibility, streamlining workflows, and providing more comprehensive insights from diverse sources.
|
| 7.4.6 | 18-SEP-2024 | - We have revamped the agent architecture by integrating an LLM within a structured framework, delivering faster execution, stricter rule adherence, and fewer errors. Enhanced error handling and comprehensive logging has improved system monitoring, boosting overall efficiency, accuracy, and reliability. Additionally, the Schema Caching Service for Skypoint AI has been deployed, reducing Structured Agent latency and enabling real-time schema updates via the Databricks REST API. This service will ensure scalable, reliable data management, with automated email alerts for quick resolution of caching failures.
- We've introduced two key features to improve user experience: the ability to edit the last question in a conversation, allowing users to refine details or rephrase for better responses, and a new search functionality in History Copilot, enabling quick access to past conversations using keywords. These updates enhance flexibility, boost efficiency, and improve overall user satisfaction.
- We've enhanced the iSolved incremental load to improve data accuracy by ensuring proper record visibility and eliminating duplicates. Additionally, the UKG WFM connector now supports incremental loads and multiple parallel calls, resulting in faster data updates and significantly reduced load times, delivering quicker access to information and a more efficient workflow.
|
| 7.4.5 | 04-SEP-2024 | - We’re excited to launch Skypoint AI Copilot on Microsoft Teams! This integration offers quick and convenient access to chat with your data anytime, anywhere, boosting productivity and enhancing the user experience. We have also enhanced the Custom Digital Library, which now features Metadata Enriched Search, improving search accuracy by ranking documents based on relevant metadata. Additionally, a new Chat Tool has been integrated, offering answers from the library's resources, further enhancing efficiency and user experience.
- Users can now edit the last question in a conversation, offering the opportunity to add missed details, rephrase, or provide additional context. This feature enables the generation of new responses and allows users to view all edits, enhancing flexibility, refining interactions, and ensuring better context in conversations.
- We have launched the Spanish version of IC Planfinder, allowing users to search for healthcare plans using customizable filters and view detailed plans in Spanish. This update provides a personalized experience for Spanish-speaking users, with the option to toggle between English and Spanish modes at the click of a button.
- Nginx Ingress has been deployed in the Kubernetes cluster, enabling the use of domain names for accessing endpoints via HTTP and HTTPS. This simplifies service management, enhances security and reliability.
|
| 7.4.4 | 21-AUG-2024 | - Users can now effortlessly connect an unlimited number of diverse structured and unstructured retrievers to their copilots, by enabling API Retriever support. This enhancement streamlines the integration process and offers customizable configurations, allowing your copilot to adapt to the evolving needs of your business with ease.
- A refined approach to accessing source information for responses is now integrated into our upgraded interface. Users can swiftly review and confirm details with a single click, enhancing overall efficiency.
- We have restructured our Kubernetes services to optimize infrastructure, resulting in improved computing, memory efficiency and better resource management. Also we have revamped the Helm and ArgoCD pipeline to streamline the deployment process for developers, enabling easier management across multiple Kubernetes clusters. Additionally, new security policies have been deployed to endpoint devices to strengthen our overall security posture.
|
| 7.4.3 | 07-AUG-2024 | - We’re excited to unveil an enhanced edition of the Skypoint AI Copilot, featuring a streamlined interface designed to elevate user experience while maintaining our high standards of performance and accessibility. This update introduces a simple retry button for users to instantly retry prompts in case of system failures, minimizing downtime and ensuring a smooth, uninterrupted workflow. Additionally, users will now see a welcome message and suggested questions upon logging in, which can be configured by admins through the prompt library on Skypoint AI Studio to further streamline interactions and enhance the overall experience.
- The Private Copilot configuration UI has undergone a complete revamp to significantly enhance the user experience. Users can now easily configure and customize their settings, including URL customization, theme selection, page title setting, brand logo uploads, and more. Additionally, the update introduces the ability to add multiple API Retrievers via the AI Tuning tab in Skypoint AI Studio. Simply enter API details and a description to integrate. This enhancement not only boosts functionality but also streamlines workflows and enhances overall versatility.
- Introduced Nethealth Connector which will integrate clinical data using Databricks Delta Share. It will support both a data warehouse star schema and a production OLTP database for improved reporting.
- Architectural changes implemented aiming at enhancing the overall performance, efficiency, and security of our systems. These updates include cost-effective measures, improved security patching, and refined Data Loss Prevention (DLP) policies.
|
| 7.4.2 | 24-JULY-2024 | - Introduced API based UKG HCM connector, which will seamlessly transfer data to the Skypoint AI Platform. It is equipped with enhanced data integration capabilities, allowing users to generate reports, chat with their data, and more. In addition to this, enabled August Health Connector to automate data extraction from August Health Assessments and Incidents, which will streamline data management and analysis.
|
| 7.4.1 | 10-JULY-2024 | - Introduced a feature to extract data from PDFs into a structured lakehouse. This update allows configurable field extraction, modeling data as tables for advanced and analytical querying. The phased release starts with Fat Table extraction and ingestion, followed by star schema support. The user-friendly interface ensures efficient data handling and high performance, enhancing accuracy and customer satisfaction. We have successfully implemented a proof of concept (POC) for Medicare. Also, enhanced Sherloq with reflection support, that allows models to learn from past experiences (manually injected), ensure consistent error handling,improve problem-solving abilities and thinking process, forming highly accurate queries to data sources.
- Introduced Domain Grounding for the private copilot in Skypoint AI Studio, allowing users to enable or disable 'Domain Context' and 'Terminology' for improved domain-specific accuracy & relevance, and integrated Bing search as a fallback, enhancing response accuracy and user satisfaction by retrieving additional information when internal data is insufficient.
- Added MRI PMX Connector, which will seamlessly complement user BAK backup file, provide nightly updates to maintain 'live' data within the Skypoint AI platform. In addition to this we have deployed enhanced PayNW Connector for importing employee timesheet data onto the platform, that will lead to streamlining data integration and improve overall efficiency.
|
| 7.4.0 | 19-JUNE-2024 | - Skypoint AI introduces significant updates to streamline user workflows and enhance capabilities. The new API Retriever support allows seamless integration and management of API retrievers in Skypoint AI Copilot. Users can now add, modify, or remove API endpoints with strict specifications, enabling advanced data retrieval techniques like semantic search and specific filtering. This enhancement boosts operational efficiency by improving the quality and relevance of retrieved data.
- Domain Grounding enhances the contextual accuracy of responses in Private Copilot by integrating industry-specific terminologies and domain contexts. This update ensures responses are precise and tailored to industry requirements, enhancing user satisfaction and decision-making processes.
- Updates in unstructured data management empower users with greater control over their data workflows. Users can now delete and modify existing connections, manage files, and adjust folder locations, optimizing data management strategies and enhancing overall efficiency. These enhancements underscore Skypoint AI's commitment to providing a versatile platform that meets diverse user needs while upholding high standards of performance and usability.
|
| 7.3.9 | 29-MAY-2024 | - Our latest update introduces structured support for Combo Prompting, empowering users to access and leverage structured Lakehouse data seamlessly. Additionally, we've implemented enhanced error messaging for our Private Copilot, providing clear guidance during system failures or technical errors, enhancing user experience.
- We've upgraded our data retrieval mechanism with Levenshtein distance-based matching, improving accuracy and latency. Moreover, users now have the flexibility to toggle AI features for Copilot directly within Skypoint AI Studio, enhancing usability and efficiency.
- With support for Blueprint SFTP integration, users can automate data extraction, transformations, and loading processes, including folder level entity ingestion. This addition streamlines data management, providing users with enhanced capabilities for efficient data handling.
|
| 7.3.8 | 8-MAY-2024 | - Improved markdown formatting capabilities and enhanced configurator features empower users to create polished and personalized Copilots effortlessly, elevating user experience and interaction.
- The import enhancement feature enables users to remove unwanted entities from imports and Lakehouse, enhancing data organization and cleanliness for improved data management efficiency.
- SherloQ, our advanced Text2SQL model, brings unparalleled accuracy and customization to SQL conversions, providing users with enhanced query understanding and data extraction capabilities.
- With the addition of Broadspire and InfuseFlow connectors, we're expanding our platform's compatibility, enabling seamless integration with diverse data sources, enhancing data accessibility and flexibility for users.
|
| 7.3.7 | 17-APR-2024 | - Significant enhancements are coming to the Skypoint AI platform, providing users with more control and efficiency. Admins can now tailor Private Copilots with self-serve customization options, including access endpoints and branding elements. Enhanced conversational question grounding ensures smoother interactions, while improved retrieval accuracy for unstructured data with ease.
- Two new updates and integrations streamline data processes. The PostgreSQL Connector enables seamless data ingestion from PostgreSQL databases, with effortless configuration and incremental ingestion support. Additionally, integration with PayNW's services via the PayNW Connector allows users to integrate online payroll and HR management platforms into their workflows.
- Exciting updates to the Skypoint AI Developer Portal empower users to integrate Skypoint AI APIs into their interfaces, facilitating custom Copilot creation. By providing a more intuitive experience, developers can efficiently leverage the platform's capabilities to achieve their goals.
|
| 7.3.6 | 27-MAR-2024 | - Enhancing the login process for Private Copilot and introducing combo prompt sources support exemplifies our commitment to enhancing user experience and transparency. These updates streamline access and provide users with clear, credible information, fostering trust and ease of use across the platform.
- From the introduction of the SharePoint Connector for Self-Serve AI Config to enhancements in data import processes and improved connectors like QuickBooks Online - General Ledger, our platform is geared towards seamless data integration and efficiency. These enhancements empower users with streamlined workflows and deeper insights, driving productivity and success in data management endeavors
|
| 7.3.5 | 06-MAR-2024 | - Skypoint AI introduces Enhanced problem-solving capability with a divide-and-conquer tactic, segmenting large complex queries into multiple small unstructured queries, boosting the efficiency of generated answers.
- The studio now supports new connectors of Yardi and PointClickCare.
|
| 7.3.4 | 14-FEB-2024 | - Skypoint AI introduces significant advancements including enhanced Short-Term Memory for improved conversational coherence, superior tabular data extraction capabilities for accuracy in unstructured data analysis, and the option for longer conversation names for better organization.
- The platform now offers a Self-Service AI Configuration feature, allowing users to easily and intuitively configure unstructured data sources for AI model training, simplifying the process of enhancing AI capabilities.
|
| 7.3.3 | 24-JAN-2024 | - For Skypoint Copilot, We've upgraded our response formatting for even clearer and more structured answers to your unstructured prompts.
- Our Copilot has refreshed color palette which not only enhances the visual appeal but also provides a more comfortable and eye-friendly interface, making your interactions more enjoyable.
|
| 7.3.2 | 04-JAN-2024 | - Skypoint Copilot's latest update revolutionizes user engagement with direct feedback options, seamless conversation sharing, precise timestamped conversation histories, and enhanced interaction during wait times.
- Paragraph Formatting in Unstructured Responses .
- Embrace the power of our new Usage Report Implementation, a comprehensive system for in-depth monitoring and analysis of your structured and unstructured data usage.
|
| 7.3.1 | 13-DEC-2023 | - Unveiled the Skypoint CoPilot, a substantial upgrade aimed at refining user experience. This release features a more sophisticated response presentation, enhanced chat functionalities, and a comprehensive conversation history management system.
- Revamped 'New Support Request' Section: An upgrade to the 'New Support Request' section within the Studio App focuses on making the feature more intuitive and user-friendly, streamlining the process for our users.
- We've reengineered our system architecture using AstraTunnel, ensuring a more robust and efficient performance tailored to each client's unique needs.
- Each tenant now benefits from a dedicated Astra DB provisioning, offering enhanced data management and security.
|
| 7.3.0 | 22-NOV-2023 | - SQL Query Support has been provided for Skypoint AI responses for structured data. Structural Decomposition has been enabled for more context in Constructing SQL Queries. A tool has been built, which efficiently validate SQL queries from LLM.
- Skypoint AI has been added in the product listings dropdown of "Help + Support" Section .
- Chat model has been upgraded from 8k to 16k Token Limit to support more extensive reasoning traces.
|
| 7.2.9 | 03-NOV-2023 | - Citation Support - Enhances reference inclusion within unstructured responses, improving content reliability and research integrity.
- Optimized data model for select customers, thereby, improving the accuracy and performance of AI responses from structured sources.
- Enhanced AI Performance - Model tuning for selected customers' data improves overall system performance.
|
| 7.2.8 | 12-OCT-2023 | - Introduced support for data model context that enhances text2SQL precision.
- Automated provisioning of key spaces in Skypoint AI's enablement workflow.
- Using the MultiQuery retriever for unstructured querying, We can now produce a variety of queries based on different viewpoints for a single user input query. By creating diverse angles on the same query, we are able to surpass some constraints of distance-based retrieval, yielding a more comprehensive set of outcomes
|
| 7.2.7 | 20-SEP-2023 | - The ADLS Gen2 V2 connector has been improved to facilitate incremental data ingestion with CSV files.
- Enhancements to the user interface have been implemented in the Granular Scheduler, simplifying the configuration of Pipeline Schedules.
- When reviewing records within the data unification process, we now have the capability to view the details of both matched and unmatched records, not just their respective counts.
|
| 7.2.6 | 30-AUG-2023 | - The OS Langchain was forked, a toolkit developed to extract table schemas and annotations from Unity Catalog Tables using Databricks RestApi, then integrated into the Skypoint project, resulting in a substantial 40% improvement in structured data response precision.
- Users can now adjust email verification time and send DSR verification reminder emails in Skypoint Studio, with the default time previously set at 24 hours.
|
| 7.2.5 | 09-AUG-2023 | - Enabled the use of Service Principal for Databricks Lakehouse Provisioning.
- Enhancing coding standards and implementing changes to enhance efficiency.
- The Scheduler enhancements enable automated and orchestrated task execution in the pipeline.
|
| 7.2.4 | 19-JUL-2023 | - WelcomeHome connector activities load to be support incremental run
- DSR to support email for verification, and additional settings for expiry.
- Beta version of Skypoint AI plugin released
- Databricks runtime is upgraded to 12.2 LTS
- dbt Core is upgraded to version v1.5
- The Python version for all Azure functions is upgraded to version 3.10
|
| 7.2.3 | 28-JUN-2023 | - Previous 3 versions of map now available for users to compare
- Run history now displays Master Data type.
- Run history option is now available for timelines.
|
| 7.2.2 | 07-JUN-2023 | - Folder based entity ingestion using Azure Data Lake Storage Gen2 Connector
- DBT Transformations
- Type of refresh in resolve
- Rule Match accuracy improvements
- Higlight of Map attribute
- Usage based report
- MDM support for predictions
- Improvements in CLV model
|
| 7.2.1 | 17-MAY-2023 | - UKG import connector
- Warning to user in map screen when import is updated/
- Invitation email updates
- Displaying datatypes on map screen and enabling entity wise run
- SkyPointGPT can be enabled for usage on instance data
|
| 7.2.0 | 25-APR-2023 | - WelcomeHome import connector
- External tables in Lakehouse accessible in all downstream processes/
|
| 7.1.1 | 05-APR-2023 | - View different master data on Dashboard.
- Usage of the Lakehouse SQL-created tables.
- Deidentification of PII and PHI data.
|
| 7.0.0 | 22-FEB-2023 | - Added SkyPointGPT.
- Domain selection in instance.
- Allow the same priority for multiple attributes in ML match.
- Added exceptions in the ML match.
|
| 6.3.0 | 01-FEB-2023 | - Added Snowflake DLT integration.
- Added Type in master data.
- Autosuggestion in a SQL editor for Audience creation.
|
| 6.2.1 | 18-JAN-2023 | - Data is available to the user for newly ingested tables or inherited tables.
- Deletion of the instance/tenant will delete respective storage, Cosmos, Unity Catalog/Schema/Tables, and SQL warehouse.
|
| 6.2.0 | 11-JAN-2023 | - Create audience from the prediction models.
- Added topic modeling and filter on sentiment model view page.
- View multiple master profiles.
|
| 6.1.0 | 06-JAN-2023 | - Migration of hive_metastore to Unity Catalog.
- Merge execution per master data.
|
| 6.0.0 | 02-JAN-2023 | - Added Transformations.
- Multiple Master data creation per instance.
|
| 5.1.0 | 21-DEC-2022 | - Added RFM model view page.
- Added SQL query editor in Audience.
- Added DateTime option in Metrics.
- External table creation in Lakehouse with the user-defined name.
|
| 5.0.0 | 29-NOV-2022 | - RFM (Recency, Frequency, Monetary value) model is added under Predict > Built-In.
- Added search field in the dropdown to select the desired value.
- Added multiple timeline journeys per instance.
- Setup instructions for import connectors.
|
| 4.4.0 | 08-NOV-2022 | - Added profile filter ("Email approachable" or "Phone approachable") to create a quick audience.
- Real-time status update on Audience page.
- Usage of tables across all downstream processes.
|
| 4.3.0 | 18-OCT-2022 | - Real-time status updates for Exports, Audience, and Prediction models.
- Bulk Processing of Data Subject Request (DSR).
- Data ingestion through Delta Live Tables (DLT).
- Convert Pandas data frame into Spark data frames.
|
| 4.2.0 | 27-SEP-2022 | - Import connectors redesign.
- Segregating data in Bronze, Silver, and Gold.
- Prediction model is migrated from Azure ML to Databricks using ML flow.
- Net Promoter Score (NPS) calculation in Business Metrics.
|
| 4.1.0 | 06-SEP-2022 | - Auto provisioning of Lakehouse SQL during the instance creation.
- Run history shows all stages of ingestion.
|
| 4.0.0 | 23-AUG-2022 | - Removal of CDM dependency for all downstream processes to improve pipeline performance and stability.
- View profile card from Audience.
- Timeline creation from Audience.
|
| 3.0.0 | 09-AUG-2022 | - The storage layer is restructured and organized into three layers named Bronze, Silver, and Gold.
|
| 2.2.0 | 26-JUL-2022 | - Replaced the Standard cluster with an Automated cluster to support optimized autoscaling.
- Added Refresh personal access token in SQL Access to configure the expiry time for an access token.
|
| 2.1.0 | 12-JUL-2022 | - Support Change Data Capture (CDC) in Lakehouse SQL.
- Added reason for the discarded entities in map tables under lakehouse.
|
| 2.0.0 | 28-JUN-2022 | - Added access token to integrate with Visualization tools through Lakehouse SQL.
- Refresh Hive metastore is added for syncing new entities in Lakehouse SQL.
|
| 1.0.0 | 14-JUN-2022 | - Skypoint Lakehouse made available for bidirectional integration with third party tools like Fivetran, Dbt, Power BI, Tableau, etc.
|