Asanka Lihiniyagodage
Back to home

Phoneline.ai

An AI agent that answers small businesses' phone calls from their own website and documents, and hands the call to a person when it should.

My role
Lead engineerBuilt the product end to end
Timeline
January 2025 to now
Stack
Python, FastAPI, PostgreSQLOpenAI Realtime API, React
Live product
phoneline.ai

The problem

Small businesses miss calls all the time. The owner is with a customer, the plumber is under a sink, the front desk is busy. The caller gets voicemail or hangs up, and the inquiry goes to a competitor.

Hiring a receptionist is expensive, and generic phone bots frustrate callers because they don't know anything about the business.

The idea

Most of what callers ask is already on the business's website: opening hours, prices, services, policies. Phoneline turns that content into an AI agent that picks up every call, answers like someone who knows the business, and passes the caller to a person when the question needs one.

Setup takes minutes: a business signs up, connects its website and any other documents, and forwards its calls.

What the product does

  • Answers every callHandles common questions like hours, pricing and policies without anyone picking up.
  • Knows the businessLearns from the business's website and documents, with no training sessions or scripts to write.
  • Hands off to peopleTransfers the caller to the team when they need a person.
  • Logs every callA dashboard shows each call, so the business can see who called and what they needed.

How it works

  1. Build the knowledge baseWhen a business signs up, its website and any other sources it provides are turned into a searchable knowledge base.
  2. Talk in real timeThe caller speaks with the agent through the OpenAI Realtime API, voice in and voice out, so the conversation flows naturally.
  3. Look up the answerWhen the caller asks something, the agent searches the knowledge base for the relevant passages.
  4. Answer from the business's contentThe reply is based on what the business has published, not the model's general knowledge.
  5. Hand off when neededIf the caller needs a person, the call is transferred to the team, and every call is logged in the dashboard.

What I built

  • AI pipelineA RAG system over each customer's website and other sources, prompt design and response evaluation.
  • Voice layerReal-time phone conversations on the OpenAI Realtime API, connected to the RAG system, plus call-transfer logic.
  • BackendPython FastAPI services, PostgreSQL, third-party integrations, deployment and infrastructure.
  • DashboardReact app for sign-up, agent configuration and call logs.
Phoneline architecture: a call goes from the phone network to the voice service, which talks to the OpenAI Realtime API, looks up answers in the knowledge base, and can transfer to the team. The dashboard and API share PostgreSQL. Caller Phone networkforwarded line Voice servicePython, FastAPI OpenAI Realtime APIvoice in, voice out Knowledge basewebsite + documents RAG lookup The teamcall transfer DashboardReact App APIFastAPI PostgreSQLaccounts, agents, calls call logs
A simplified view of the system. The voice service handles each live call; the dashboard and API manage accounts, agent settings and call history.
Asanka Lihiniyagodage
Asanka LihiniyagodageSenior Python AI engineer, Colombo

Need an AI feature like this?

Send a short description of what you're building and I'll reply with a concrete first step, usually within a day.