AI voice agents that answer calls and book appointments
New to Contra
AI voice agents that answer calls and book appointments
I designed and developed a specialized AI phone receptionist for veterinary clinics.
The system handles real PSTN and SIP calls through FreeSWITCH. It combines streaming speech recognition, LLM orchestration and low-latency voice synthesis to communicate naturally with pet owners.
The agent can answer questions about veterinary services, business hours, location, parking and clinic policies. It can identify the pet owner’s reason for calling, distinguish routine appointment requests from potentially urgent situations, check configured availability and guide the caller through a veterinary visit request.
The system includes:
• Real US telephone and SIP call handling
• Pet-aware reason-for-visit collection
• Routine, sick-visit and urgent-request routing
• Veterinary service and provider information
• Appointment booking, rescheduling and cancellation flows
• Email confirmations and owner notifications
• Safe escalation for urgent or unresolved situations
• Call recordings, transcripts and structured summaries
• Appointment status and administrative review
• Configurable services, staff, schedules, policies and instructions
• Replaceable speech recognition, LLM and voice providers
I developed the telephony architecture, real-time conversational pipeline, backend APIs, veterinary call flows, appointment logic, email integration, administration, deployment and real-call testing.
The agent does not diagnose animals or replace veterinary judgment. Urgent, uncertain or clinically sensitive requests are handled according to configured escalation rules.
This is an independently developed product, not a paid client project.
3
2
279
I designed and developed Anna Dental AI, a specialized phone receptionist for dental practices.
The system answers real PSTN and SIP calls through FreeSWITCH and combines streaming speech recognition, LLM orchestration and low-latency voice synthesis to hold natural telephone conversations.
Anna can answer questions about dental services, expected price ranges, business hours, providers and clinic policies. It can identify the requested treatment, match the caller with an appropriate provider, check configured availability and guide the caller through an appointment request.
The system also includes:
• Real US telephone and SIP call handling
• Dental service and provider matching
• Price, hours, location and policy questions
• Appointment booking, rescheduling and cancellation flows
• Email confirmations and appointment management links
• Safe escalation for unresolved or sensitive requests
• Call recordings, transcripts and structured summaries
• Appointment status and administrative review
• Configurable services, staff, schedules and agent instructions
• Replaceable speech recognition, LLM and voice providers
I developed the telephony architecture, real-time voice pipeline, backend APIs, appointment workflows, email integration, web administration, deployment and testing.
The agent is designed for administrative communication and scheduling. It does not provide diagnoses or replace professional clinical judgment.
This is an independently developed product, not a paid client project.
1
185
I designed and developed a specialized AI phone receptionist for hair and beauty salons.
The system answers real telephone calls, explains salon services and prices, identifies the requested treatment, handles appointment requests and sends email confirmations.
It uses FreeSWITCH and SIP telephony with streaming speech recognition, LLM orchestration and low-latency voice synthesis. The agent supports natural interruptions and is optimized for telephone-quality audio.
I also built business-specific service matching and confirmation logic. During real-call testing, phrases such as “men’s haircut” produced several transcription variants, so the system uses aliases, conversational context and confirmation rules instead of relying on a single raw transcript.
The management layer provides call recordings, transcripts, summaries, appointment status and configurable information such as services, staff, prices, opening hours, promotions and agent instructions.
My responsibilities included telephony architecture, backend development, AI orchestration, appointment workflows, email integration, administration, deployment and real-call testing.
This is an independently developed product, not a paid client project.
1
153
I built a workflow that turns a business website into a testable AI phone receptionist.
The system analyzes the website, extracts services, staff, opening hours, policies, and other relevant information, then creates an isolated voice-agent demo for that business. Instead of sending a generic recording, we can provide a real phone number that allows the business to test the agent through an actual call.
When the website or scheduling system supports an integration, the agent can check availability and book appointments during the call. Otherwise, it safely captures the caller’s details and preferred time for staff follow-up.
If a business decides to continue after the demo, the same foundation can be expanded into a production receptionist with databases, customer-specific business rules, calendar and CRM integrations, confirmations, call summaries, analytics, and administrative controls.
The extracted information can also reveal gaps in the business website. Its content and structure can then be improved so both visitors and the AI receptionist receive clearer, more reliable information.
The main lesson I share is that website extraction alone is not enough. Information must be normalized, validated, and restricted to the source material before it can be used safely in a live voice conversation.
The demonstration uses a fictional dental clinic and real recordings from my working voice-agent system. No patient data, real customer information, or invented testimonials are included.
I used Descript to assemble and refine the presentation, edit the narration and real-call sections, create captions, and prepare the final submission.
Designed and developed a digital platform that helps homeowners, architects, and construction professionals understand the impact of insulation on a building's energy performance. Created in collaboration with experts in construction physics, civil architects, and software engineers, the application transforms highly complex calculations into a simple and intuitive user experience.
0
49
I designed a mobile-responsive web application that enables mining operators to perform tire inspections directly in the field, even in some of the world's most demanding industrial environments. Built for global deployment across mining sites, the platform replaces manual processes with a streamlined digital workflow that improves data accuracy, safety compliance, and operational efficiency.
Automation & Data Analytics | SQL | Power BI | Excel | R
Automation & Data Analytics | SQL | Power BI | Excel | R
A production‑ready web application demonstrating real‑world CRUD functionality and internal dashboards commonly used by small teams and startups.
Includes email/password authentication, a full CRUD system with sorting and filtering, detailed item views, and an overview dashboard with status breakdowns and recent activity. Admin features allow archiving records and basic role-based access.
Built with React and TypeScript on the frontend and a Node.js / Express API, with a clean, maintainable codebase and a neutral, professional UI designed as an internal tool rather than a marketing site.
0
290
📊 Sales Performance Analytics Dashboard (Power BI)
This Power BI dashboard was developed as part of a technical case study to demonstrate a business‑first approach to performance analytics.
The report is designed to support both executive‑level decision‑making and operational sales management by focusing on:
Revenue performance tracking
Key performance drivers (Orders & Average Order Value)
Team‑level performance monitoring
Individual agent insights
Data quality validation and exception handling
🔎 Key Functional Areas
Executive Overview
Provides a high‑level summary of Net Revenue and its primary drivers, supported by a monthly trend and rolling average to identify emerging performance patterns and reduce short‑term volatility.
Performance Diagnostics (Region × Time)
Enables root‑cause analysis by highlighting when and where performance changes occurred across regions and time periods.
Sales Team Monitoring
Supports day‑to‑day management through ranked team performance metrics, enabling prioritization of coaching or follow‑up actions.
Agent‑Level Analysis
Offers a focused performance view per individual contributor, including category mix and territory‑level revenue drivers.
Data Quality Monitoring
Separates adjustments (e.g. returns, discounts) from gross performance to prevent misleading KPI interpretation.
💼 Business Value
Designed to:
Monitor operational performance
Identify revenue drivers behind month‑over‑month changes
Detect under‑ or over‑performing teams
Support targeted coaching
Enable fast, data‑driven decision‑making
🛠 Tools & Concepts Used
Power BI
Data Modeling (Fact / Dimension)
KPI Design
MoM Analysis
Driver‑Based Revenue Monitoring
AOV Tracking
Data Quality Checks
2
2
205
OpsHub – Internal Operations System
A custom internal tool built to centralize client management, project tracking, task workflows, and invoicing in one clean dashboard.
It replaces spreadsheets and manual coordination with a structured, role-based system that improves operational visibility and financial tracking.
Ideal for small teams that need clarity, control, and scalable internal workflows.
2
4
280
Internal invoicing and billing web application for tracking invoices, payment status, and basic revenue records, with CRUD workflows and a clear operational dashboard.