Tech Stack
Python, Workflows, Vertex AI, Dialog Flow, LLM, BigQuery, Looker, LookML
Global Technology Leader saves 50 % processing cost with Next Gen support automation powered by LLM
Using Intent Feedback Loop Automation, Multi-turn conversation coherence, and NLG-based on-demand conversational analytics
Objectives
- To transform customer experience using LLM-based hyper-automation solutions
- The current conversational AI solution deployed is trained on limited intents and phrases and is unable to map 50% of the conversations
- A lot of manual effort goes into extracting missed utterances from the bot and mapping them with the right intent to re-train the bot
- Key business insights difficult to retrieve from current dashboard
Challenges
- Distributed / unstructured data environment
- Data accuracy and performance is of high importance
- Integrated customer internal enterprise applications
- 200+ complex conversational multilingual bots
Solutions
Automate feedback loop with the help of LLMs and existing data science models for classification of missed utterances. Summarization of Dashboards/Charts powered by Generative AI (NLG). Adding Generative AI features to the existing conversational bots
Embedding Large Language Model – Classification logic within LLM using embedded data, entities, and utterances to calculate a mapping score gets calculated.
ML Model – Created based on LLM data and once trained saved in the client’s cloud for further reference.
Python Notebook – ML and embedding logic will be executed in python notebooks in a scheduled manner.
BOT Training API – Re-training of the bot with new classified data (intent-utterances mapping).
On-demand dashboard framework created to track metrics as sentiment analysis, context management metrics, AI recommendation for new workflows
Using NLG to generate summary of the dashboard which will help in drawing required business insights customised to stakeholder persona
Added Generative AI inbuilt features to the current bots : Generators, Generative fallback, and answer feedback
Outcome
~90% Automation achieved for conversations
Improve End customer experience enabling contextual conversation with 94% confidence score
Custom business insights summary as per stakeholders using generative conversational analytics
Integration with Enterprise Application to automation feedback loop
Agile Methodology for acceleration of development
Proprietary Technology for quick adoption of customer environment to deliver in secured environment
Self Service Ability across all enterprise layers
