{"id":23318885,"url":"https://github.com/pv-bhat/leadswizard","last_synced_at":"2026-01-21T16:04:05.532Z","repository":{"id":267595348,"uuid":"901291586","full_name":"PV-Bhat/LeadsWizard","owner":"PV-Bhat","description":"A revolutionary conversational AI tool that leverages advanced emotional frameworks, psychological insights, and strategic prompting to transform lead engagement and sales workflows.","archived":false,"fork":false,"pushed_at":"2024-12-14T12:12:34.000Z","size":23312,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-07T05:20:40.568Z","etag":null,"topics":["conversational-ai","customer-engagement","data-labeling-tools","generative-ai","gpt","prompt-engineering","system-design"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/PV-Bhat.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-12-10T11:46:42.000Z","updated_at":"2025-02-10T16:48:11.000Z","dependencies_parsed_at":null,"dependency_job_id":"f048a814-1813-416b-9517-39677781ebe9","html_url":"https://github.com/PV-Bhat/LeadsWizard","commit_stats":null,"previous_names":["pv-bhat/leadswizard"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/PV-Bhat/LeadsWizard","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PV-Bhat%2FLeadsWizard","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PV-Bhat%2FLeadsWizard/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PV-Bhat%2FLeadsWizard/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PV-Bhat%2FLeadsWizard/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/PV-Bhat","download_url":"https://codeload.github.com/PV-Bhat/LeadsWizard/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PV-Bhat%2FLeadsWizard/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28635926,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-21T15:01:31.228Z","status":"ssl_error","status_checked_at":"2026-01-21T14:42:58.942Z","response_time":86,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["conversational-ai","customer-engagement","data-labeling-tools","generative-ai","gpt","prompt-engineering","system-design"],"created_at":"2024-12-20T17:20:08.853Z","updated_at":"2026-01-21T16:04:05.510Z","avatar_url":"https://github.com/PV-Bhat.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Leads Wizard: A Cutting-Edge Conversational AI for Empathetic Lead Engagement\n\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"https://github.com/PV-Bhat/LeadsWizard/blob/main/Assets/L2.png\" align=\"center\" alt=\"Logo\" width=\"200\"/\u003e\n\u003c/div\u003e \u003cbr\u003e\n\n_Is it really possible to automate a repetetive customer-focused task like lead engagement \u003cins\u003ewithout losing the **human touch?**\u003cins/\u003e_\n# 🔑 Executive Summary\n\nLeads 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.\n\n**What LW changed:** _Automated lead engagement and conversions where manual \u0026 templated efforts fell short._\n\n### Key Innovations:\n- **🧠 Chain-of-Thought (CoT) Reasoning:** Advanced step-by-step processing for complex scenarios.\n- **💡 Dynamic Emotional Scoring:** Real-time sentiment analysis for empathetic responses.\n- **🔄 Filtered Few-Shot Learning (fFSL):** Cost-effective iterative improvements without traditional fine-tuning.\n- **📈 Strategic Response Planning:** Aligns conversations with business outcomes.\n\n### 📊 Tangible Impact:\n- **+56% engagement improvement** in the Intake stage.\n- **+45.9% sentiment improvement** in the Engaged segment.\n- **+17% higher lead qualification** rates than templated methods.\n\n### 📂 Explore More:\n- Interactive Visualizations to see the real-world impact at a glance (Flourish Interactive Visuals):\n\t- \u003ca href=\"https://public.flourish.studio/visualisation/20669562/\" target=\"_blank\" title=\"Click to View Interactive Visualization on Flourish\"\u003e Key Metrics Bar Graph \u003c/a\u003e \u003cbr\u003e\n\t- \u003ca href=\"https://public.flourish.studio/visualisation/20671670/\" target=\"_blank\" title=\"Click to View Interactive Visualization on Flourish\"\u003e Sales Funnel Stages Slope Graph \u003c/a\u003e \u003cbr\u003e\n\t- \u003ca href=\"https://public.flourish.studio/visualisation/20673018/\" target=\"_blank\" title=\"Click to View Interactive Visualization on Flourish\"\u003e Chord Diagram with Empathy and Perception Comparison \u003c/a\u003e \u003cbr\u003e\n \t- \u003ca href=\"https://public.flourish.studio/story/2765196/\" target=\"_blank\" title=\"Click to View Interactive Visualization on Flourish\"\u003e Open Dataset Visualizer w/ custom filtering for transparency \u003c/a\u003e \n- Features and Supporting Tools showcasing technical excellence: [Jump to tools](#supporting-tools)\n\n## Table of Contents\n- [Introduction](#introduction)\n- [Features Summary](#features-overview)\n- [Key Metrics and Visualizations](#key-metrics)\n\t1. [Sentiment, Engagement and CES comparison](#1-sentiment-engagement-and-customer-effort-scores)\n\t2. [Sales Funnel Stage Stats](#2-lead-qualification-retention-across-stages)\n\t3. [Emotional and Perceptual Comparison](#3-comparative-emotional-engagement-and-perception)\n- [Supporting Tools](#supporting-tools)\n- [Timeline](#timeline)\n- [Explore dataset, Data Handling protocols and privacy](#dataset-used)\n- [License](https://github.com/PV-Bhat/LeadsWizard/blob/main/LICENSE)\n\n## Introduction\nLeads 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. \nDeveloped 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.\n\n---\n\n## Features Overview\nLeads 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:\n\n1. **Inner Monologue and Chain-of-Thought Reasoning (CoT)**  \n\t   Enhances response quality by simulating step-by-step reasoning for tailored and intelligent conversations.\n2. **Filtered Few-Shot Learning (fFSL)**  \n\t   Introduces a cost-effective, systems-level feedback loop that iteratively improves LW’s performance by leveraging real-world data.\n3. **Dynamic Emotional Scoring and Context Analysis**  \n\t   Analyzes user sentiment and contextual cues to deliver empathetic, validating, and context-aware responses.\n4. **Strategic Response Planning**  \n\t   Dynamically adjusts tone, framing, and goals to align lead interactions with high-level business objectives.\n5. **Modular Architecture**  \n\t   Enables seamless integration with APIs and external data sources, offering flexibility and scalability.\n6. **Iterative Improvement Ecosystem**  \n\t   Integrated workflows with open-source tools like the **meta-labeller** and **LW chrome extension** to extract, analyze, and refine responses continuously.\n\n\u003ca href=\"https://github.com/PV-Bhat/LeadsWizard/blob/main/Features\" target=\"_blank\" title=\"Detailed features\"\u003e More feature details \u003c/a\u003e\n\n_By leveraging these advanced techniques, Leads Wizard delivers measurable business outcomes that surpass traditional methods. Below, are the tangible improvements LW achieved._\n\n---\n\n## Key Metrics\nLW 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.\n\n### 1. Sentiment, Engagement, and Customer Effort Scores\nThis comparison highlights LW's significant impact on lead sentiment, engagement, and customer effort:\n\n\u003cimg src=\"https://github.com/PV-Bhat/LeadsWizard/blob/main/Assets/Bar_Graph.gif\" alt=\"Bar Graph\" height=\"350\"/\u003e\n\u003cp\u003e \u003ci\u003e\n  Figure 1 - Key Metrics Bar Graph | \n  \u003ca href=\"https://public.flourish.studio/visualisation/20669562/\" target=\"_blank\" title=\"View Interactive Visualization on Flourish\"\u003e Click for interactive visual (Flourish) \u003c/a\u003e\n\u003c/p\u003e \u003c/i\u003e\n\n\n#### Sentiment, Engagement, and CES Comparison:\n- 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.\n    \n_This visualization emphasizes LW’s superior ability to provide empathetic and effective user interactions compared to traditional approaches._\n\n---\n\n### 2. Lead Qualification Retention Across Stages\nThe slope graph below tracks lead retention as they progress through the sales funnel stages (Intake, Engaged, Qualified):\n\n\u003cimg src=\"https://github.com/PV-Bhat/LeadsWizard/blob/main/Assets/Slope_Chart.gif\" alt=\"Slope Graph\" height=\"350\"/\u003e\n\u003cp\u003e \u003ci\u003e\n  Figure.2 - Sales Funnel Stages Slope Graph | \n  \u003ca href=\"https://public.flourish.studio/visualisation/20671670/\" target=\"_blank\" title=\"View Interactive Visualization on Flourish\"\u003e Click for interactive visual (Flourish) \u003c/a\u003e\n\u003c/p\u003e \u003c/i\u003e\n\n#### Sales Funnel Stage Stats:\n- 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.\n    \n_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.\n\n---\n\n### 3. Comparative Emotional Engagement and Perception\nThe 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:\n\n\u003cimg src=\"https://github.com/PV-Bhat/LeadsWizard/blob/main/Assets/Chord.gif\" alt=\"Chord Diagram\" height=\"350\"/\u003e\n\u003cp\u003e \u003ci\u003e\n  Figure.3 - Chord Diagram with Composite Metric Comparison | \n  \u003ca href=\"https://public.flourish.studio/visualisation/20673018/\" target=\"_blank\" title=\"View Interactive Visualization on Flourish\"\u003e Click for interactive visual (Flourish) \u003c/a\u003e\n\u003c/p\u003e \u003c/i\u003e\n\n#### Emotional Engagement Index (EEI):\n- LW scored **57.2**, significantly outpacing Manual (**47.9**) and Templated (**47.4**) approaches.\n    \n#### User Perception Index (UPI):  \n  - LW achieved a score of **54.7**, emphasizing its ability to deliver responses that resonate with users.\n    \n_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._\n\n---\n\n### Summary of Metrics\n\n- **45.9%** improvement in sentiment for the Engaged segment.\n- **56%** boost in engagement scores for the Intake segment over templated methods.\n- **17% higher lead qualification rate** compared to templated methods.\n\n_These metrics and visualizations illustrate Leads Wizard’s transformative potential, merging cutting-edge AI with empathetic user design to achieve superior business outcomes._\n\n---\n\n## Supporting Tools\n- **Meta-Labeler**: An open-source Python-based tool with user-friendly UI for conversation labeling and anonymization.\n  _[Try it here](https://github.com/PV-Bhat/Meta-Labeler/blob/main/README.md)_\n- **LW Chrome Extension**: Simplifies JSON conversation data extraction from Meta Business Suite. \n_[More details here](https://github.com/PV-Bhat/LW-Chrome-Extension)_\n\n## Timeline\n- **Development:** Conceptualized and prototyped in 12 days.\n- **Iterative Improvements:** Added CoT reasoning and dynamic emotional scoring based on real-world data.\n- **Adoption:** Collaborated with leadership for API integration and multi-team automation.\n[Find the Detailed Timeline here](https://github.com/PV-Bhat/LeadsWizard/blob/main/Timeline.md)\n\n## Dataset used\n(Data handling, Privacy and Bias management)\n\n\u003cimg src=\"https://github.com/PV-Bhat/LeadsWizard/blob/main/Assets/Dataset.gif\" alt=\"Bar Graph\" height=\"350\"/\u003e\n\u003cp\u003e \u003ci\u003e\n  Figure 4 - Interactive Dataset Visualizer - Each circle represents a conversation with a unique ID and attributes. Feel free to interact further:\n  \u003ca href=\"https://public.flourish.studio/story/2765196/\" target=\"_blank\" title=\"Explore the dataset on Flourish\"\u003e Explore the dataset on Flourish \u003c/a\u003e\n\u003c/p\u003e \u003c/i\u003e\n\n - The dataset used was from a real-world startup, with 250+ datapoints (conversations with leads).\n - 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.\n - 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.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpv-bhat%2Fleadswizard","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpv-bhat%2Fleadswizard","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpv-bhat%2Fleadswizard/lists"}