Author(s): Manash Pratim

Originally published on Towards AI.

I Built an AI That Understands My Team’s Emotions From Our Commits and Messages

I built an AI that analyzes commits, PR reviews, and Slack messages to detect emotional drift and burnout in engineering teams. Using vector-drift embeddings and a fine-tuned LLaMA model, it learned to read the subtext beneath our communication and the results shocked me.

The article discusses the creation of an AI designed to analyze emotional cues from team communications, highlighting the importance of recognizing emotional drift and burnout in engineering. It explores the experiment’s findings, showcasing how the AI successfully identified patterns of emotional withdrawal in team members and emphasized the need for empathy alongside technical expertise in team management, shifting the focus from mere performance metrics to understanding human emotional dynamics in software development.

Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI