My client approved her mood board in one round. Her words - "I LOVE the new mood board! I don't want to change a thing!"

That did not happen because of luck or good taste. It happened because the design was the last step, not the first.

Before I opened Figma, I had already 1. Asked why her website was urgent right now, and listened to the whole answer 2. Learned where her clients came from and which source was drying up 3. Heard what she was tired of seeing on other therapist websites 4. Noticed the personal detail she almost talked herself out of, her greyhounds

Endless revisions usually mean the designer is guessing. Strategy first means you are not guessing.

If you are a therapist, psychologist or practitioner dreading a website project because you expect weeks of back and forth, it does not have to work that way. berniceebenezer.com/therapists

AI Customer Support Agent for Web Form, Gmail & WhatsApp An AI support agent that answers customer questions across a web form, Gmail and WhatsApp, and hands off to a human team when it should. Load-tested with 200+ messages and no lost messages.

I built an AI customer support agent as a demo for a fictional SaaS company called Flowmint. Customers can write through a web form, Gmail or WhatsApp. The agent finds the answer in a knowledge base, replies on the same channel, and passes the conversation to a human team (Billing, Sales, Support) for refunds, special pricing, or when a customer asks for a person.

One agent for three channels, with replies formatted for each (a clean HTML email, a short WhatsApp message, a private web tracking page)

Safety rules written in code: it can only quote approved prices, and refunds always go to a human

Remembers returning customers on email and WhatsApp

Private ticket tracking page with a secret tracking code

If the AI service is busy, it switches to backup AI models, and to a knowledge-base answer if all are limited

I load-tested the agent for 24 hours with 200+ messages across all three channels, using simulated customers plus real emails and WhatsApp messages I sent myself.

212 messages in, 212 replies out, none lost

Only 3.3% needed a human

Areas I’m improving: faster replies with a paid AI plan, and spam protection for the web form.

Tech stack: Python, FastAPI, OpenAI Agents SDK, Kafka, PostgreSQL, Next.js, Docker, Gmail API, WhatsApp Cloud API.

Writing the safety rules in code, not in the prompt, is the part I like most: approved prices only, and refunds always go to a human. My RAG demo also passes the question to a person when the guide has no answer. How does your agent decide that a customer "asks for a person": a fixed list of phrases, or does the model decide?