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
🚀 I build AI Voice Call Agents that sound 100% human , not robotic.
Imagine an AI that can:
✅ Talk to your customers naturally:
✅ Handle inquiries & qualify leads
✅ Follow up instantly
✅ Close deals — just like a real salesperson
I’m a custom AI agent developer, and I’ve already built solutions for:
🔹 E-commerce brands
🔹 Personal brands
🔹 Voice-based lead systems that capture leads (from ads like Meta) and call them instantly
No delays. No missed opportunities. Just smart automation that converts.
If you're looking to scale your business with AI voice agents that actually sell, not just talk , I can help you build it.
📩 DM me if you're interested or want :to see how it works.😍 💯 🔥
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
Related posts
Dial: the AI front desk for one-person trades
The problem: one-person trades can't answer the phone from a roof or a crawlspace. Missed calls become lost jobs, and evenings go to quotes and follow-ups.
I built Dial and set it up for a demo HVAC shop, Dry Heat Air Co. in Mesa, AZ.
For customers
• An AI voice front desk that answers every call, asks the right questions and flags emergencies
• Online booking in plain words. Dial suggests the likely fault and offers real arrival windows from the owner's schedule. Booked in about a minute.
• A live job page, plus a My Visits account with every visit, quote and receipt
• One tap to confirm "I'll be home" or accept a quote
For the owner
• The whole day on one screen: what needs you, what the front desk handled, the route and time saved
• Hold to talk after a job. The voice note becomes the receipt, the quote and follow-ups on day 2, 7 and 14.
• Both sides update live, so there's no phone tag
Built with Lovable and Lovable Cloud, ElevenLabs for the voice agent and transcription, and Gemini to write up each job.
Try it: dial-frontdesk.lovable.app
The customer side has a shared demo account, so you can tap around and watch the owner's side update live.
Top-notch design.
Building AI agents is easy. Building one you can trust with a real business workflow is harder.
I built a Freelance Admin Agent to explore that problem using Strands Agents SDK and Claude Sonnet 4.5 on Amazon Bedrock.
The working MVP takes manually provided client emails and turns them into a structured payment workflow:
→ Classifies invoice and payment emails
→ Extracts client, invoice, amount, currency, dates and contextual details using structured output
→ Stores and matches records in SQLite
→ Uses deterministic logic to identify full/short and on-time/late payments
→ Uses a second agent to draft a contextual follow-up only when needed
→ Keeps the final decision with the human through Approve / Edit / Reject
One of the most valuable parts wasn't adding another AI feature. It was finding a real reliability issue during testing: reprocessing the same email could duplicate records and inflate payment totals.
I reproduced it through repeat testing, traced the database behavior, and fixed it.
That reinforced something I'm increasingly applying to my AI engineering work:
A useful AI product isn't just an LLM call. It needs clear boundaries between AI reasoning, structured data, deterministic business logic, persistence, testing, and human control.
The next iteration will focus on stronger production safeguards, including source-grounded financial extraction, precise currency handling, stricter trust boundaries for untrusted input, and eventually live inbox integrations.
I'm interested in building more systems like this for startups and teams with repetitive workflows that can genuinely benefit from AI agents and automation.
Stack: Python · Strands Agents SDK · Amazon Bedrock · Claude Sonnet 4.5 · Pydantic · SQLite · Streamlit
turning client emails into admin tasks is such a real freelancer pain, nice build 🔥