Index / Work / Agenlead

An AI sales team that calls, qualifies and books — on its own.

Agenlead is an outbound calling platform built on autonomous voice agents. They dial a lead, hold a real conversation, answer questions, qualify intent, and book a consultation — then score and summarize every call automatically. I founded it and built it end-to-end: the product, the design, the iOS app, and the cloud automation that runs the agents.

Visit agenlead.com ↗

Role
Founder · Product, Design & Engineering
Period
2025 — present
Surface
iOS · Web · Voice (telephony)
Stack
React · Swift · n8n · Supabase · AWS
Status
Shipped · in production
Agenlead overview dashboard with campaigns, agents and leads
Context

The problem. Outbound sales is slow, expensive and inconsistent. A rep spends most of the day dialing numbers that don't pick up, repeating the same opening, and forgetting to log what happened. The good conversations get lost in the noise of the bad ones.

Agenlead's bet: a voice agent can do the repetitive 80% — dial, qualify, handle objections, book the meeting — and hand humans only the conversations worth their time, each one already transcribed and scored.

The hard part of an AI agent isn't the model. It's everything around it: the retries, the voicemail detection, the consent, and the moment a human should take over.
Architecture

One pipeline, five stages.

Every lead flows through the same path. I designed the orchestration as discrete, observable steps so any stage can fail, retry, or be inspected on its own — the difference between a demo and something you can run in production.

01 · Capture

Ingest & normalize

Leads arrive from web forms, CSV and ad integrations. An n8n workflow de-dupes and normalizes them into Supabase.

02 · Call

Voice agent dials

A conversational voice agent (ElevenLabs over Twilio telephony) places the call, follows the campaign script, and detects voicemail.

03 · Converse

Route intent live

A conversation handler resolves intent in real time — qualify, schedule, end — and can check calendar availability and book mid-call.

04 · Analyze

Score the transcript

When the call ends, an LLM reads the transcript and returns a structured result: outcome, a 0–10 interest score, and a short summary.

05 · Surface

Sync everywhere

Results sync to the iOS app and web dashboard in real time — lead status, call score, transcript and the booked event.

TypeScript React 19 Swift · iOS n8n ElevenLabs Twilio OpenAI · GPT-4o-mini Supabase · Postgres AWS ECS + RDS Docker Stripe
The product

From pipeline to a single tap.

The companion app turns all of that machinery into three things an operator actually needs: what's happening, what each call was worth, and what to do next.

Agenlead overview dashboard
Agenlead call detail with score and AI transcript
Agenlead lead detail with campaign and status
Surface 01 · Overview

The whole pipeline at a glance.

Active campaigns, live agents, leads and calls — with recent activity and status (interested, scheduled, agreed) updating in real time as agents work the list.

Surface 02 · Call detail

Every call, scored and transcribed.

The agent's full conversation, a 0–10 interest score, duration and outcome — generated automatically the moment the call ends. No rep notes required.

Surface 03 · Lead detail

One tap from insight to action.

Campaign, status and notes you can edit on the spot — and place a call directly from the record when a human should take the next step.

Engineering

Decisions that made it safe and cheap to run.

Privacy by design

Consent & isolation first

Consent-based outreach, per-tenant data isolation, and every secret kept in AWS Parameter Store — never in code or the client. Privacy policy and terms are surfaced inside the app, not buried.

Cost discipline

~$0.002 per analyzed call

I replaced brittle keyword matching with a single LLM analysis pass on GPT-4o-mini. The rewrite cut roughly 44% of the workflow code and ~60% of the data moved — at about two-tenths of a cent per call.

Operability

Isolated dev & prod

Separate environments on AWS ECS with managed RDS Postgres, containerized with Docker, automated backups, and rollback-capable deploys — so shipping doesn't mean gambling with live calls.

Outcomes

0 → 1
Founded, designed and built end-to-end — iOS, web and voice.
~$0.002
Cost per AI-analyzed call (GPT-4o-mini).
Voice AI
Autonomous agents that call, qualify and book.
iOS + Web
Real-time companion app and dashboard on one Supabase backend.
Reflection

Building Agenlead made the AI part feel almost easy compared to the systems work around it: telephony retries, voicemail detection, consent, idempotent workflows, and a clean handoff to a human at exactly the right moment. The product is the guardrails.

It's also the clearest example of the way I like to work — one person carrying a product from a Figma frame to a Swift screen to the cloud workflow that makes the voice agent actually dial.