Scalytics Copilot 4.0

Scalytics Copilot

The September 2025 update for Scalytics Copilot delivers critical stability improvements to the Deep Search agent and the core API. This release focuses on resolving complex, intermittent issues related to network proxies, context window management, and API configuration, resulting in a more reliable and resilient platform for all users.

‍

Key Highlights for September 2025

Major Features

• OpenAI GPT-OSS Support. We now support OpenAI's OSS GPT models, up to 120B parameters. Build, test, and scale AI apps and agents with your enterprise data—powered by GPT-5 and managed privately with Scalytics Copilot.
• Multilingual Support for Deep Search: The Deep Search functionality has been upgraded to support multiple languages. The system now includes language detection and translation capabilities, allowing it to process queries and sources in various languages.
• Agent Reasoning Transparency: A persistent reasoning log has been implemented for the Deep Search agent. This provides a detailed, step-by-step record of the agent's decision-making process, including data retrieval, analysis, and synthesis steps. The logs are available for both real-time and historical review, increasing the transparency of the agent's operations.
  ‍

New Features

• Bot Trap Detection and Timeout Management: A new system has been implemented to detect and manage unresponsive or malicious domains during web scraping. This feature improves the reliability of data collection by temporarily blacklisting problematic domains.
• Chat History Summarization: A summarization service has been added to manage long-running conversations. When a chat history exceeds the context window, the service summarizes the conversation to maintain context.
  ‍

Improvements

• GPU Statistics: The vLLM service has been enhanced to provide more detailed GPU statistics, including a list of loaded models and the tensor parallel size.
• Model Activation: The model activation process has been refactored to improve error handling and provide clearer user feedback.
• Citation Handling: The citation generation process in report synthesis has been improved with standardized citation markers and better URL normalization.
• Reasoning Log Display: The user interface for the reasoning log has been redesigned for improved clarity and usability.
  ‍

Bug Fixes

• Language Support in Synthesis: The processing_language parameter has been added to the synthesis method to ensure correct handling of different languages.
• Hardware Information Endpoint: The getHardwareInfo function has been simplified by removing redundant code.
• Chat Title Editing: The functionality to edit chat titles has been removed.
• Reasoning Log Display: Issues with task_id propagation and conditional rendering in the reasoning log display have been resolved.
  ‍

Dependency Updates

• axios has been updated to version 1.12.0.
• mermaid has been updated to version 11.11.0.
• brace-expansion has been updated to version 1.1.12.
• form-data has been updated.

‍

Scalytics Federated AI features:

• AI-based optimizer automatically picks an optimal configuration of class data processing frameworks, such as Java Streams or Apache Spark, to run applications on.
• Scalytics Core performs the program execution. It abstracts the different platform specific APIs and coordinates inter-platform communication.
• Applications can run on multiple data processing platforms, without changing the native code of the underlying platforms.
• Federated data processing: In-situ processing in different sites without moving raw data outside their origin.
• Build and execute cross platform machine learning pipelines in a unified way.
• NEW: Federated Machine Learning
  • Federated analytics by integrating multiple platforms across silos
  • Developers: Train ML models using federated learning in a platform agnostic way
• NEW: Supporting unsupervised learning (e.g., using K-means) and Stochastic Gradient Decent optimization technique for Federated Learning across supported data platforms
• NEW: Auditing compliance (who accessed what when) and training audits (closed beta)

‍

Data sources:

• PostgresSQL
• Columnar Data Files (e.g., CSV, Iceberg, Parquet, ORC)
• SQlite (e.g. Mobiles, Embedded)
• Local file systems
• Distributed file systems (e.g., HDFS, S3)
• Apache Kafka
• NEW: Remote files over http(s)
• NEW: JDBC based data sources

‍

Data Processing Platforms:

• Java 8 Streams
• Apache Spark / DataBricks
• Postgres
• SQLite
• Apache Flink / Confluent, Decodable
• NEW: Apache Kafka
• NEW: Tensorflow
• NEW: JDBC based platforms

‍

Programming APIs

• Java
• Scala
• Basic SQL
• New: Python (limited support)

‍

Runtime

• NEW: Actor-based runtime for building federated applications

‍

This release represents our ongoing commitment to delivering a secure, efficient, and privacy-focused AI platform for enterprise environments. We continue to enhance Scalytics Connect based on customer feedback and emerging industry requirements, ensuring our solution remains at the forefront of enterprise AI technology.

‍