Submission type
Coded Agent with UiPath SDK
Name
Sushila Kumari
Industry category in which use case would best fit in (Select up to 2 industries)
Information technology and services
Complexity level
Intermediate
Summary (abstract)
The proposed solution introduces an intelligent agent that automates the process of converting meeting transcripts into actionable DevOps work items. By leveraging NLP and large language models (LLMs), the agent identifies key discussion points, extracts action items, and automatically creates corresponding DevOps user stories with well-structured titles, descriptions, and relevant tags. Once created, the agent notifies the respective stakeholders through Microsoft Teams, ensuring seamless collaboration and improved productivity across development teams.
Detailed problem statement
In most software development environments, meeting discussions often include several actionable items, task assignments, and follow-up points. However, these crucial insights are frequently lost or manually documented after the meeting, leading to inefficiency, missed deliverables, and poor traceability. Project managers or scrum masters typically spend significant time reviewing transcripts or notes, interpreting the discussed points, and manually creating DevOps user stories. This manual approach not only delays task creation but also introduces human error and inconsistency in documentation. There is a need for an automated, intelligent system that can understand natural language transcripts, identify actionable insights, and seamlessly convert them into trackable DevOps work items — reducing manual effort, ensuring no task is missed, and improving overall team agility.
Detailed solution
The developed agent addresses this challenge by combining AI-driven language understanding with process automation. The system reads meeting transcripts or voice-to-text outputs and processes them using a Large Language Model (LLM) to extract actionable insights such as assigned owners, deadlines, and task contexts. The NLP model intelligently identifies which parts of the conversation correspond to specific user stories, enhancements, or bug fixes. Once identified, the agent automatically generates DevOps user stories — complete with a meaningful title, detailed description, and relevant tags for sprint categorization. It then interacts with the DevOps API to create these work items in real time. After successful creation, the agent sends a Teams notification to the concerned team members or channels, summarizing the created story and linking it directly to the DevOps board. This end-to-end intelligent workflow eliminates manual transcription review, enhances accuracy in task tracking, and ensures that every action item from meetings is properly documented and assigned — ultimately improving team productivity, accountability, and sprint planning efficiency.
Narrated video link (sample: https://bit.ly/4pvuNEL)
Expected impact of this automation
This automation enhances team productivity by instantly converting meeting discussions into actionable DevOps user stories. It eliminates manual note-taking and task creation, ensuring no action items are missed. Automated Teams notifications keep everyone informed in real time, improving collaboration and accountability. Overall, it bridges the gap between conversations and execution, speeding up project delivery and decision-making.
UiPath products used (select up to 4 items)
UiPath Coded Agents
Automation Applications
visual studio code, Teams
Integration with external technologies
Azure Devops , MS Teams
Hi there, 
Nov 5–16: Jury evaluation by 
Nov 17: Winners announced 
.
,