https://github.com/pv-bhat/leadswizard
A revolutionary conversational AI tool that leverages advanced emotional frameworks, psychological insights, and strategic prompting to transform lead engagement and sales workflows.
https://github.com/pv-bhat/leadswizard
conversational-ai customer-engagement data-labeling-tools generative-ai gpt prompt-engineering system-design
Last synced: 2 months ago
JSON representation
A revolutionary conversational AI tool that leverages advanced emotional frameworks, psychological insights, and strategic prompting to transform lead engagement and sales workflows.
- Host: GitHub
- URL: https://github.com/pv-bhat/leadswizard
- Owner: PV-Bhat
- License: mit
- Created: 2024-12-10T11:46:42.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2024-12-14T12:12:34.000Z (6 months ago)
- Last Synced: 2025-02-13T09:37:43.800Z (4 months ago)
- Topics: conversational-ai, customer-engagement, data-labeling-tools, generative-ai, gpt, prompt-engineering, system-design
- Homepage:
- Size: 22.2 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Leads Wizard: A Cutting-Edge Conversational AI for Empathetic Lead Engagement
![]()
_Is it really possible to automate a repetetive customer-focused task like lead engagement without losing the **human touch?**_
# 🔑 Executive SummaryLeads Wizard (LW) is a groundbreaking AI system that redefines lead engagement with innovation, empathy, and measurable business impact. Developed in a fast-paced startup environment, LW is designed to bridge the gap between automation and human-centric engagement.
**What LW changed:** _Automated lead engagement and conversions where manual & templated efforts fell short._
### Key Innovations:
- **🧠Chain-of-Thought (CoT) Reasoning:** Advanced step-by-step processing for complex scenarios.
- **💡 Dynamic Emotional Scoring:** Real-time sentiment analysis for empathetic responses.
- **🔄 Filtered Few-Shot Learning (fFSL):** Cost-effective iterative improvements without traditional fine-tuning.
- **📈 Strategic Response Planning:** Aligns conversations with business outcomes.### 📊 Tangible Impact:
- **+56% engagement improvement** in the Intake stage.
- **+45.9% sentiment improvement** in the Engaged segment.
- **+17% higher lead qualification** rates than templated methods.### 📂 Explore More:
- Interactive Visualizations to see the real-world impact at a glance (Flourish Interactive Visuals):
- Key Metrics Bar Graph
- Sales Funnel Stages Slope Graph
- Chord Diagram with Empathy and Perception Comparison
- Open Dataset Visualizer w/ custom filtering for transparency
- Features and Supporting Tools showcasing technical excellence: [Jump to tools](#supporting-tools)## Table of Contents
- [Introduction](#introduction)
- [Features Summary](#features-overview)
- [Key Metrics and Visualizations](#key-metrics)
1. [Sentiment, Engagement and CES comparison](#1-sentiment-engagement-and-customer-effort-scores)
2. [Sales Funnel Stage Stats](#2-lead-qualification-retention-across-stages)
3. [Emotional and Perceptual Comparison](#3-comparative-emotional-engagement-and-perception)
- [Supporting Tools](#supporting-tools)
- [Timeline](#timeline)
- [Explore dataset, Data Handling protocols and privacy](#dataset-used)
- [License](https://github.com/PV-Bhat/LeadsWizard/blob/main/LICENSE)## Introduction
Leads Wizard (LW) is an AI-powered innovation designed to revolutionize lead engagement and qualification. LW employs advanced techniques like Chain-of-Thought (CoT) reasoning, filtered Few-Shot Learning (fFSL) dynamic emotional scoring, and strategic planning to deliver empathetic, business-driven results.
Developed and iterated in a high-pressure startup environment, LW transitioned from a custom GPT workflow to a streamlined API-integrated system, delivering tangible value to both users and businesses.---
## Features Overview
Leads Wizard (LW) incorporates cutting-edge AI techniques and systems-level innovation to deliver exceptional performance in lead engagement. Below is a high-level overview of its core features:1. **Inner Monologue and Chain-of-Thought Reasoning (CoT)**
Enhances response quality by simulating step-by-step reasoning for tailored and intelligent conversations.
2. **Filtered Few-Shot Learning (fFSL)**
Introduces a cost-effective, systems-level feedback loop that iteratively improves LW’s performance by leveraging real-world data.
3. **Dynamic Emotional Scoring and Context Analysis**
Analyzes user sentiment and contextual cues to deliver empathetic, validating, and context-aware responses.
4. **Strategic Response Planning**
Dynamically adjusts tone, framing, and goals to align lead interactions with high-level business objectives.
5. **Modular Architecture**
Enables seamless integration with APIs and external data sources, offering flexibility and scalability.
6. **Iterative Improvement Ecosystem**
Integrated workflows with open-source tools like the **meta-labeller** and **LW chrome extension** to extract, analyze, and refine responses continuously._By leveraging these advanced techniques, Leads Wizard delivers measurable business outcomes that surpass traditional methods. Below, are the tangible improvements LW achieved._
---
## Key Metrics
LW demonstrates groundbreaking improvements across critical performance metrics when compared to traditional methods (Manual and Templated). These metrics, derived from over 250+ anonymized conversation segments, underscore LW’s ability to seamlessly balance empathetic engagement with strategic business outcomes.### 1. Sentiment, Engagement, and Customer Effort Scores
This comparison highlights LW's significant impact on lead sentiment, engagement, and customer effort:
![]()
Figure 1 - Key Metrics Bar Graph |
Click for interactive visual (Flourish)#### Sentiment, Engagement, and CES Comparison:
- Leads Wizard improved engagement by 56% over templated methods in the Intake segment. This directly translates into higher user satisfaction and more meaningful lead interactions.
_This visualization emphasizes LW’s superior ability to provide empathetic and effective user interactions compared to traditional approaches._---
### 2. Lead Qualification Retention Across Stages
The slope graph below tracks lead retention as they progress through the sales funnel stages (Intake, Engaged, Qualified):
![]()
Figure.2 - Sales Funnel Stages Slope Graph |
Click for interactive visual (Flourish)#### Sales Funnel Stage Stats:
- LW retained a remarkable **95.12%** of leads, compared to Manual (**83.61%**) and Templated (**63.29%**) responses—outperforming manual approaches by over 11 percentage points, and increasing conversion rates as a result.
_Why this matters_: These metrics demonstrate LW’s strategic ability to guide leads through complex sales funnels effectively, ensuring higher lead retention, qualification and subsequently, conversion rates.---
### 3. Comparative Emotional Engagement and Perception
The innovative chord diagram below showcases LW’s superiority in composite metrics like Emotional Engagement Index (EEI) and User Perception Index (UPI) compared to traditional methods:
![]()
Figure.3 - Chord Diagram with Composite Metric Comparison |
Click for interactive visual (Flourish)#### Emotional Engagement Index (EEI):
- LW scored **57.2**, significantly outpacing Manual (**47.9**) and Templated (**47.4**) approaches.
#### User Perception Index (UPI):
- LW achieved a score of **54.7**, emphasizing its ability to deliver responses that resonate with users.
_This visualization highlights how LW’s dynamic emotional scoring and contextual analysis set it apart from traditional methods, leading to more impactful and engaging interactions._---
### Summary of Metrics
- **45.9%**Â improvement in sentiment for the Engaged segment.
- **56%**Â boost in engagement scores for the Intake segment over templated methods.
- **17% higher lead qualification rate** compared to templated methods._These metrics and visualizations illustrate Leads Wizard’s transformative potential, merging cutting-edge AI with empathetic user design to achieve superior business outcomes._
---
## Supporting Tools
- **Meta-Labeler**: An open-source Python-based tool with user-friendly UI for conversation labeling and anonymization.
_[Try it here](https://github.com/PV-Bhat/Meta-Labeler/blob/main/README.md)_
- **LW Chrome Extension**: Simplifies JSON conversation data extraction from Meta Business Suite.
_[More details here](https://github.com/PV-Bhat/LW-Chrome-Extension)_## Timeline
- **Development:** Conceptualized and prototyped in 12 days.
- **Iterative Improvements:** Added CoT reasoning and dynamic emotional scoring based on real-world data.
- **Adoption:** Collaborated with leadership for API integration and multi-team automation.
[Find the Detailed Timeline here](https://github.com/PV-Bhat/LeadsWizard/blob/main/Timeline.md)## Dataset used
(Data handling, Privacy and Bias management)
![]()
Figure 4 - Interactive Dataset Visualizer - Each circle represents a conversation with a unique ID and attributes. Feel free to interact further:
Explore the dataset on Flourish- The dataset used was from a real-world startup, with 250+ datapoints (conversations with leads).
- In light of maintaining privacy and protecting proprietary information, all data was anonymized and meta-labeled first. Each conversation maintains the unique conversation ID generated during the process of downloading using the extension, and maintains transparency.
- The dataset was downloaded with LW-Chrome-Extension and manually labelled with Meta-Labeler (Both are open-source tools). Despite following strict labelling protocols and blinded cross-testing, it's important to note that manual labeling inherently adds bias to the data. Therefore the metrics above are a pilot scale proof of concept which can easily be automated moving forward to mitigate manual biases.