The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Voice Agent is an AI receptionist that answers calls and chats on behalf of a business, so no booking is lost after hours.
Every missed call is a customer who goes to whoever picks up first. This agent picks up every time:
• Talks with customers by voice (speech in and speech out) or by chat
• Detects what the caller wants: a new booking, a change, a question
• Pulls out customer details like name, phone number and date from natural speech
• Works out which service the customer is asking for
• Runs the whole booking lifecycle: create, update and cancel
• Runs fully locally with an Ollama LLM, so no call audio ever leaves the machine
• Includes a Next.js dashboard to monitor the agent and its bookings
By the numbers: 12 Python modules · under 3s response time · voice in and out · zero cloud LLM calls
Tech stack: Python, FastAPI, Ollama, Gemma 2, SQLite, Next.js
My role: Solo developer. I built the conversation logic, intent detection, detail extraction, booking system, API and dashboard.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Challenges
View all
Related posts
T-Platform, a unified trading app for crypto, stocks and forex.
Three markets, three apps, no way to see real exposure. We put all of it into one dark workspace: real-time charts, order execution, positions and history in a single view.
Full case study here: https://www.behance.net/gallery/255562509/T-Platform-Crypto-Stock-Trading-UXUI-Mobile
First contract on Contra finished!
How was it?
Outbound Agent — AI-Powered Multi-Tenant Insurance Verification & Document Follow-Up Platform
An AI voice agent that calls insurance and provider offices, verifies coverage, and faxes missing documents live on the call — with human escalation built in.
Calling doesn't scale with headcount — chasing missing documents and verifying insurance across hundreds of patient orders traditionally means hiring more staff to sit on hold. I built a multi-tenant AI voice platform that automates this end-to-end: the agent calls the office, identifies the patient using only the minimum PHI required, explains exactly what's missing, and confirms whether the prior request was received.
If the office needs the document resent, the agent can trigger it to go out by fax directly during the call, using the submission method already on file — no manual follow-up needed. If the call requires human judgment — escalation, a sensitive case, anything outside defined scope — it transfers to a live agent instead of guessing or hallucinating a response.
Every call returns structured, queryable data back to the platform: call status, blocker/reason, next step, submission path, full transcript, and recording reference — all mapped to the correct patient order. The platform is fully multi-tenant, with role-based access, tenant-scoped audit logs, and PHI-safe handling: call artifacts are automatically purged from the telephony layer once securely stored downstream.
Results: Consistent, structured call outcomes across every tenant on one schema, scalable outbound follow-up on flat headcount, and fully auditable, PHI-compliant operations throughout.
Stack: Python & FastAPI (backend) · SignalWire (telephony, call orchestration, fax dispatch) · Deepgram (speech-to-text) · ElevenLabs (voice synthesis) · RAG pipeline (grounding responses in live patient/order data) · webhook-driven post-call pipeline for transcript analysis and PHI cleanup.
If your team is stuck chasing missing documents or verifying insurance over the phone, this same agent can be rebuilt around your provider network and compliance requirements.
