Speed of development using AI

At Rocket^®, we're constantly exploring ways to enhance our technological capabilities and improve team productivity. Today, I'm excited to share insights into our groundbreaking project, where we’re accelerating the speed of development using AI.

The challenge of meeting productivity

Meetings have long been acritical yet inefficient part of our work ecosystem. Traditionally, converting discussion points into actionable items was a time-consuming, manual process that could take days to complete. This project has beenour revolutionary solution to this universal challenge.

What is the speed of development using AI Project?

This is an initiative designed to be the ultimate post-meeting efficiency tool. 

By leveraging conversational AI, we've created a system that captures every spoken word during calls and transforms them into:

Real-world impact: From concept to code

The original vision was to transform spoken code changes into executable reality. 

During our initial trials, we discovered a high level of efficiency in software development and additional efficiencies, including Code Prompt Generation, ADO Work Item Creation, and many expanded use cases, including integrations with Rocket Navigator.

Once these prompts are created, we consume them into the Meeting Summaries UI and allow users to send them to Git as a Git Issue and assign Copilot to the change. Steps outlined below:

[1:Post-meeting Zoom-generated code prompt.]

Creating stories is as easy as one, two, three!

1. Sign in to your meeting dashboard.

2. Analyze meetings for relevant content.

3. Create work items, code prompts, and other post-meeting content.

 

1. Expanded use cases

Beyond code changes,we've successfully applied this to:

• Project updates
• Meeting recaps
• Post-incident reviews (PIR)
• Generating knowledge articles
• Creating and tracking tasks post-meeting

2. Zoom integration: A game-changing partnership

A key breakthrough in the project has been our integration with Zoom.

The Zoom SDK andAI admin interfaces provide flexibility and organization level configurability, allowing us to:

• Configure prompts at the organizational level so they can be made available to everyone at Rocket.

By leveraging Zoom's configurable components, we've created a system that ensures every meeting is documented in a consistent, easily understood format, drawing from as well as creating a central knowledge base.

3. Human in the Loop: Putting users in control

At the core of this project is our commitment to human-centered AI. We've designed the system with a fundamental principle: technology should empower, not replace, human decision-making.

Key User-Centric Features:

1. Meeting privacy and control

• All meeting content is initially available only to the meeting organizer.

• Organizers have complete discretion over sharing meeting notes, code prompts, and stories.

• Users choose which insights to act upon or distribute.

Below is the Zoom interface where you can see your meetings for the day, and meetings that have been shared with you, ensuring you are in the driver’s seat of where your information will go.

2. Intuitive post-meeting interface

• Efficiently presents captured meeting information
• Allows granular control over knowledge sharing
• Enables users to: 

• Update knowledge bases
• Create project updates
• Generate code prompts
• Decide what content moves to different channels 

This approach ensures that AI serves as a powerful assistant, with humans always makingthe final decisions about how information is used and shared.

Technical innovation