Inigra Software House

Tag: CRM

  • AI Conversational Coaching & Analytics Plugin for Online Meetings

    AI Conversational Coaching & Analytics Plugin for Online Meetings

    Overview

    We developed an AI-powered plugin for a global financial services company to improve client-facing conversations of their relationship managers. The solution integrates directly with Google Meet and Zoom, enabling real-time speech-to-text transcription, conversation summaries, sentiment analysis, and personalized coaching feedback.

    Client

    • Company: Confidential (Financial Services Enterprise)

    • Industry: Banking & Financial Services

    • Use Case: Training and improving performance of client-facing staff

    Challenge

    The company needed to improve the quality and compliance of client conversations while reducing the cost of manual training. Key challenges included:

    • No objective way to measure call quality or customer sentiment.

    • Manual training relied on sample reviews, leaving most calls unchecked.

    • Difficulty scaling coaching for hundreds of employees across multiple regions.

    • Compliance requirements demanded secure storage and analysis of conversations.

    Solution

    We built an AI Conversational Coaching Plugin with three main pillars:

    1. Real-Time Transcription & Avatar Assistant

    • Speech-to-Text: Real-time transcription of Google Meet and Zoom calls (multi-language support).

    • Text-to-Speech Avatar: Interactive digital avatar for role-play training sessions with employees.

    • Live Captions & Notes: Automatically displayed during calls to assist both employees and customers.

    1. Conversation Analysis & Coaching

    • Summarization: AI generates concise call summaries for CRM and compliance records.

    • Sentiment & Tone Analysis: Detects frustration, engagement, and satisfaction levels.

    • Performance Scoring: Evaluates employee responses, empathy, and adherence to scripts/policies.

    • Post-Call Feedback: Employees receive suggestions for improvement with concrete examples.

    1. Integration & Security

    • Works as a plugin for Google Meet, Zoom, and MS Teams.

    • Export of transcripts and insights into CRM (Salesforce).

    • GDPR-compliant storage with role-based access control and audit logging.

    • Encryption at rest and in transit with SOC2 alignment.

    Technology Stack

    • AI & NLP: OpenAI GPT-4, Whisper, Hugging Face Transformers

    • Speech-to-Text: Google Speech-to-Text API, AWS Transcribe (fallback)

    • Text-to-Speech & Avatar: ElevenLabs, Unreal Engine MetaHuman (training avatar)

    • Backend: Node.js, Python microservices

    • Integrations: Zoom SDK, Google Meet API, Salesforce API

    • Storage & Infrastructure: AWS S3, RDS PostgreSQL, ECS with Docker, Terraform IaC

    • Security: OAuth2 SSO, encrypted transcripts, role-based access, audit trails

    Results

    • 100% of client calls recorded & analyzed automatically.

    • 25% faster onboarding of new employees through avatar role-play training.

    • 40% improvement in customer satisfaction scores (CSAT) after 3 months.

    • Compliance-ready transcripts reduced audit preparation time by 60%.

    • Scalable solution deployed globally across 5 regions.

    Supporting Information

    • Key Features: live transcription, conversation scoring, avatar role-play, CRM export.

    • Compliance: GDPR, SOC2, industry-specific data retention policies.

    • Usage: as a live plugin during calls, and as a training simulator for employees.

    Process

    1. Discovery – workshops with HR, compliance, and customer service teams.

    2. MVP – built a Zoom plugin with transcription and summaries.

    3. Expansion – added coaching feedback, sentiment analysis, and Salesforce integration.

    4. Avatar Training Mode – deployed role-play avatar for onboarding.

    5. Rollout & Training – launched across Europe and APAC, with dashboards for HR and compliance teams.

    6. Continuous Improvement – fine-tuned NLP models based on recorded calls and real feedback.

    Client Testimonial

    “This AI solution changed how we train and monitor conversations. Every call is now an opportunity to learn, and our team is more confident and compliant than ever.”
    — Confidential due to NDA

  • AI Customer Service & Booking Assistant for Rental Venues

    AI Customer Service & Booking Assistant for Rental Venues

    Overview

    We developed an AI-powered customer service and booking platform for Salonty.com, a network of rental venues for events, workshops, and business meetings. The solution uses natural language processing (NLP), speech-to-text, and calendar integrations to automate customer interactions: answering phone calls, handling reservations, managing availability, and responding to equipment-related questions.

    Client

    • Company: Salonty.com

    • Industry: Hospitality /Short-term rental

    • Scale: 20+ locations with daily inquiries, hundreds of bookings per month

    • Client type: B2C marketplace platform

    Challenge

    Salonty.com operated a growing network of rental venues but faced significant inefficiencies in handling customer service:

    • Staff spent hours daily answering repetitive phone calls and emails about availability, pricing, and equipment.

    • Manual booking processes caused delays, double-bookings, and errors.

    • Customer expectations for 24/7 support could not be met with human staff only.

    • Scaling to new cities would have required a large and costly support team.

    Solution

    We designed and deployed an AI-driven virtual assistant that automates end-to-end customer interactions, seamlessly integrated into Salonty.com’s platform.

    1. Conversational AI & Voice Integration

    • Cloud-based speech-to-text and text-to-speech APIs to handle natural phone conversations.

    • Multilingual support for Polish and English customers.

    • NLP models trained to recognize rental-specific queries (availability, equipment, pricing).

    1. Booking & Calendar Management

    • Integration with Google Calendar & internal booking system APIs.

    • Automatic reservation creation, modifications, and cancellations.

    • Real-time availability checks across multiple venues.

    1. Customer Service Automation

    • AI answers FAQs about equipment (projectors, chairs, catering), location details, and access instructions.

    • Escalation to human staff only for complex cases.

    • SMS/email confirmation workflows with Twilio + SendGrid.

    1. Architecture & Technology Stack

    • AI & NLP: OpenAI GPT-4, Dialogflow CX

    • Voice & Telephony: Twilio Voice, Google Speech-to-Text, Amazon Polly

    • Backend: Node.js (Express), GraphQL API

    • Database: PostgreSQL, Redis for session context

    • Integrations: Google Calendar API, Salonty booking system, Twilio SMS, SendGrid

    • Infrastructure: Dockerized microservices on AWS (ECS, RDS, S3), Terraform for IaC

    • Security: OAuth2 authentication, HTTPS, encrypted data at rest & in transit

    Results

    • 70% of inquiries automated without human involvement.

    • 50% reduction in booking errors, thanks to real-time calendar sync.

    • 24/7 availability of customer service in two languages.

    • 40% cost savings on customer support operations.

    • Scalability: ready to support expansion to new cities without additional staff.

    Supporting Information

    • Key Technologies: OpenAI GPT-4, Dialogflow CX, Twilio, Google Speech-to-Text, Node.js, PostgreSQL.

    • Security & Compliance: GDPR-ready data handling, voice call encryption, audit logging.

    • Team: AI engineers, backend developers, DevOps, UX for conversational design.

    Process

    1. Discovery — mapped customer journeys, most frequent questions, and bottlenecks.

    2. Prototype — built a proof-of-concept with Dialogflow and Twilio for one location.

    3. Integration — connected AI assistant with calendars, booking APIs, and CRM.

    4. Deployment — rolled out to all venues, trained AI on historical FAQs.

    5. Optimization — fine-tuned NLP intents, improved fallback handling, added multilingual support.

    6. Monitoring — dashboards for call volume, automation success rate, and escalation triggers.

    Client Testimonial

    “AI automation changed the way we run Salonty. Our customers get instant answers and can book anytime, while our staff focuses on higher-value tasks. Expanding to new locations is now faster and more efficient.”
    — Kinga Obarska, Project Manager, Salonty.com

  • Automated CRM platform for real-time payment monitoring and debt collection

    Automated CRM platform for real-time payment monitoring and debt collection

    Overview
    A custom CRM backend enabling real-time payment monitoring, automated client reminders, and streamlined debt collection for a real estate development company.

    Client

    • Country: Poland

    • Industry: Real estate development

    • Type: Enterprise SME

    • URL: sovo.dev

    Challenge
    “Our finance team was spending too much time reconciling bank statements, chasing overdue invoices, and manually managing client communication. We needed an automated system to monitor payments in real time and enforce consistent debt collection workflows.”

    Solution

    • Delivered a custom CRM with:

      • Real-time bank integration (PSD2-compliant API)

      • Automated detection of delayed or missing payments

      • Configurable debt collection workflows and escalation rules

      • Automated email/SMS notifications to clients

      • Payment tracking dashboard with role-based access

    • Backend: Node.js REST API, PostgreSQL schema design, secure bank API integration, event-driven debt collection engine

    • Frontend: React.js + Tailwind CSS for dashboards and reporting

    • Integrations: Bank API (Open Banking), Twilio (SMS), SendGrid (email)

    • Team: 1 backend engineer, 1 frontend engineer, 1 QA, 1 project manager

    Result

    • 75% reduction in manual payment reconciliation work

    • 40% faster debt collection cycles compared to manual process

    • 95% of overdue clients now receive automated reminders within 24 hours

    • Improved transparency with dashboards, reducing disputes and delays

    Additional Information

    • Key numbers: 1,000+ transactions monitored per month; <200 ms avg. response time

    • Technologies: Node.js, PostgreSQL, secure banking API integration, role-based access control, event-driven workflows

    Process

    • Discovery → workshops with finance/legal teams to map workflows

    • Architecture → API endpoints, workflows, permissions

    • Implementation → iterative sprints, CI/CD pipelines on AWS

    • Validation → staging with anonymized bank data, UAT with finance team

    • Go-live → gradual rollout per project, KPI monitoring

    Client Testimonial

    “The new CRM saves our finance team hours every week. Automated reminders and escalation have improved payment discipline and reduced overdue accounts.”
    — Michał Dachtera, Finance Director, SOVO Development, Media: Click the link

  • Design and rollout of a scalable transaction data storage and processing platform

    Design and rollout of a scalable transaction data storage and processing platform

    Overview
    A robust backend platform to store, process, and analyze high volumes of transaction data in real time. Designed for scalability, resilience, and integrity, it powers reporting, analytics, and system integrations for business-critical operations.

    Client

    • Country: (confidential / US-based)

    • Industry: Financial services / transaction processing

    • Scale: Millions of transactions daily across multiple systems

    • Type: Enterprise (Fortune 500)

    • URL: Confidential

    Challenge
    “Our transaction data kept growing beyond the limits of our legacy systems. Reporting lagged by hours, queries timed out, and compliance teams lacked reliable audit trails. We needed a scalable, resilient backend that could ingest millions of events per day without bottlenecks.”

    Solution

    • Delivered a backend platform with:

      • Scalable Data Ingestion via Apache Kafka for high-frequency streams

      • Reliable Storage Layer combining PostgreSQL (transactions) and ClickHouse/BigQuery (analytics)

      • Stream Processing Pipelines using Apache Flink & dbt for real-time transformations and enrichment

      • Security & Compliance with encryption, RBAC, and audit logs

      • Integration-Ready APIs exposing curated datasets to BI, finance, and ML systems

    • Backend & Data Tech: Kafka, Flink, dbt, PostgreSQL, ClickHouse/BigQuery, Python

    • Infrastructure: Kubernetes, Terraform, AWS/GCP with encrypted S3 backups

    • Team: 2 backend/data engineers, 1 DevOps, 1 project manager

    Result

    • Ingestion throughput: >50,000 transactions/second without degradation

    • Reporting latency reduced from hours to seconds

    • Regulatory audits completed 30% faster due to reliable logs

    • Enabled real-time dashboards for finance and operations teams

    • Provided integration endpoints for machine learning models and BI platforms

    Additional Information

    • Key numbers: 5B+ rows stored, 7 TB processed daily, 99.99% uptime

    • Technologies: Kafka, Flink, dbt, PostgreSQL, ClickHouse, Kubernetes, Terraform, AWS/GCP

    • Security: OAuth2, encryption at rest & in transit, full audit trail

    Process

    • Discovery → mapped transaction flows, compliance needs, and reporting SLAs

    • Architecture → designed multi-tier storage and streaming pipelines

    • Implementation → iterative rollouts with blue/green deployments on Kubernetes

    • Validation → performance tests at 2× peak traffic; compliance validation with anonymized data

    • Go-live → phased migration from legacy, followed by 24/7 monitoring and support

    Client Testimonial

    “With this new platform, we finally trust our data. Reports run in seconds, regulators are satisfied, and our systems scale as the business grows.”