Last week Thursday (March 12, 2024), we unveiled the latest in our product direction to our users: a fusion of SmartChat™ and Workstreams™ aimed at empowering knowledge workers to unlock their full potential with the help of AI.

Here's what to expect in the near future:

• Intuitive UI: Navigate multiple sources of data, query data, and gain insights
• Collaboration: Enable real-time interaction with colleagues
• Data Visualization: Generate charts and tables
• Versatile UX: Access multiple data sources, including private notes, and shared team data
• Automation: Streamline repetitive tasks, which saves you time & can make work more enjoyable

We welcome your feedback! Please let us know what you think

‍Want to learn more? Watch this demo:

‍

Storytell New MVP: UI Design and Features

(This update was shared on March 20, 2024)

Walk through a sneak peek of Storytell's latest product roadmap, focusing on the UI design and the cool new features they've got lined up. If you're a fan of intuitive design and collaborative tools, you're going to love what Storytell has in store.

Summary of product features users should look forward to:

• User Profile and Settings Sync: Personalize your experience with settings that remain consistent across all devices.
• Collaborative Environment: Work alongside colleagues who can join the chat to read, comment, or contribute their own insights.
• Workspace Organization: Navigate through a hierarchical structure of folders and directories within a workspace tailored for specific projects or themes.
• Rich Media Representations: Enjoy insights presented through various formats like tables, charts, and imagery for easier data digestion.
• Rewrite Options: Modify the tone, length, or style of responses with a fly-out menu offering various rewriting choices.
• Version Control: Easily revert to previous versions of content or adjust parameters to refine answers without changing the original prompt.
• Bookmarking Prompts: Star or save important prompts for quick access in future sessions.
• Commenting on Insights: Discuss and connect conversations directly to the data that inspired the insights.
• Export Options: Utilize macros and templates that adhere to brand guidelines for exporting content to PowerPoint, CSV files, and more.
• Suggested Prompts: Receive suggestions to continue the conversation with prompts that encourage deeper exploration or related questions.
• Workspace Customization: Define the voice and settings for different workspaces to suit the nature of the content or analysis being conducted.
• File Management: Upload and manage files specific to each workspace, keeping sensitive information compartmentalized.
• Ongoing Chat Prompt: Maintain an ever-present chat prompt at the bottom of the UI, creating a continuous feed of prompts and insights.

Storytell New MVP: Transforming ideas into action

(This update was shared on April 3, 2024)

This demo showcases new feature ideas for Storytell's MVP: Exploring features such as SmartChat™ mode and nsights mode, and LLM recommendations to enhance user experience and functionality

Storytell is also considering introducing:

• Rewrite button for content modification
• Using AI technology to suggest next steps and refine, for example, webinar topics
• Conversations can be turned into repeatable workflows with insights and settings modes.

Architecture Updates and Developments in Browser-Based Machine Learning

(These updates were shared on April 10, 2024)

1. Architecture and Data Model Updates

• Overview:
  • The control plane (the "brain" of the system) coordinates various tasks such as content ingestion, machine learning services, and user interactions. We're continuously improving the architecture to provide a seamless user experience.
  • The model plane will have a multi-model planner that breaks down user intents into multiple tasks for efficient and targeted content generation. An LLM router will choose the best model based on the task, ensuring optimal performance and cost-effectiveness.
• Data model improvements‍
  • We're implementing a user aggregate system that tracks user events (e.g., account creation, email verification) as a linear timeline. This allows for better auditing, data integrity, and the ability to reinterpret events without complex data migrations.
  • Every operation in the system will be represented and tracked, allowing for cost accumulation and transparency. This will enable us to optimize performance, analyze user behavior, and potentially offer flexible pricing models in the future.

2. Running Machine Learning Models in the Browser

• Proof of concept: We successfully ran BERT, a text-classifying model, directly in the browser. This groundbreaking development opens up a world of possibilities for enhancing the user experience and reducing latency.
• Implications for user experience: By running models in the browser, we can provide near-instant results, enabling features like auto-complete suggestions and real-time model selection based on user input. Imagine typing and receiving immediate, context-aware suggestions powered by machine learning models running right in your browser!‍
• Cost-saving benefits: Offloading computations and processing to the user's browser reduces the load on our systems, potentially leading to cost savings that we can pass on to our users