LLM call-transcript analyzer
Built for an internal company AI-themed hackathon, where it placed 1st. A call/transcript analyzer that scores each engagement on several metrics — call quality, whether expectations were met, and tone — then routes the result to the right people. Later adopted into the company workflow.
What it does
Scores each engagement on call quality (how well it went), whether expectations were met, and tone — essentially sentiment analysis over the transcript.
The pipeline
Transcripts dropped into a source folder trigger an agent that orchestrates the processing, sends notifications to everyone involved internally (e.g. the senior manager / director), and writes a log of the engagement with that client.
From hackathon to production
Placed 1st at the internal AI hackathon, then moved from a one-off build into an adopted, smoother internal process that surfaces call sentiment and quality to the right stakeholders automatically.
Stack
Interested in work like this?
dhruvnirmal2111@gmail.comOpen to remote data & AI roles — Australia, India, and the Gulf / Singapore.