Make moneyBusiness size: Solo

A talent agent built an AI chatbot with Make to answer client questions and grew from about 100 clients to 300 without new staff

U-Shin Kim (U-Shin Group Artists) · Austria · Make, ChatGPT

Go to the skill

What the agent did

Kim mapped his whole talent representation process and built Ari, an AI agent chatbot made with Make, which answers routine client questions, down to outfit suggestions for premieres. He also uses Make with ChatGPT for outbound emails and an actor application workflow.

Result, as claimed

Make says his client count went from about 100 to 300 with no new staff, and that he saves 15 hours a week. He is aiming for up to 1,000 clients, which is a goal, not a result.

This is the result as claimed in the public source linked below. It has not been checked and is not a typical outcome.

Proof

Read Make's customer story

Try it yourself

Build the answer bank and hand-over rules for a chatbot that answers your clients' routine questions.

Difficulty: Intermediate

Prompt

I run a [type of service business] with about [number] clients. Here are the questions clients ask me most often, with my usual answers: [paste 15 to 30 of them]. Turn this into (1) an answer bank written in my tone, (2) a list of questions the chatbot must never answer and must pass to me, such as fees, contracts and complaints, (3) a short hand-over message for those cases, and (4) ten test questions, including two tricky ones, to check it before clients use it.

Tools

  • Make Named in the story. He built the Ari chatbot and his workflows with it
  • ChatGPT Named in the story for his outbound emails

Steps

  1. Collect a month of the questions clients actually send you.
  2. Run the prompt and correct every answer yourself.
  3. Load the answer bank into the chatbot you build and connect it to your message channel.
  4. Read the chat logs every week and add the questions it got wrong.

Watch out: Clients may treat a chatbot answer as your promise, so keep fees, contracts and anything personal with a person.

Starter version by Solopreneur Code

Skill: Customer replies

Add this skill

Customer repliesDifficulty: Beginner

Chat answer bank with handover

Answers routine customer chat questions from your catalogue and past replies, and hands anything else to a person.

Works with
ChatGPT, Claude, Gemini, Any AI chat Test it in any AI chat on past chats first. Live use needs a chat agent such as Meta Business Agent on WhatsApp, as in the story.
Tools in the story
Meta Business Agent, WhatsApp Business, ChatGPT
Country
Indonesia

How to use this: Copy the skill, paste it into Claude, ChatGPT or Gemini, and ask it to save it as a skill. If it cannot, it will still follow the steps.

Show skill

If the Copy button does not work, select this text and copy it.

Sign up for the newsletter

Get the next story from Solopreneur Code in your inbox.

Form not loading? Subscribe on Substack

Back to all stories

More like this

Browse all stories
Make moneyBusiness size: SoloIncludes prompt

A marketing consultant had ChatGPT write a three-step late invoice chase and says drafting dropped from about 20 minutes to about 4 per client

Lilach Bullock @lilachbullock · United Kingdom · ChatGPT

ChatGPT wrote three reusable chase emails at day 1, 14 and 30 after the due date, and analysed a year of invoice and payment dates to find the slowest payers.

Result, as claimed

She says each chase email takes about four minutes per client instead of twenty. She says automatic reminders, AI-drafted follow-ups and one phone call as a last resort moved every overdue invoice she had in the last four months. Her average delay across 34 invoices was 19 days past terms, and she credits fixing her invoice terms, not AI, as the bigger change.

Make moneyBusiness size: Small teamIncludes prompt

Singapore rental business has an AI agent screen and route WhatsApp leads, and respond.io reports 90% of spam now filtered out

Angelina Liao · Singapore · respond.io AI Agents, respond.io mobile app, WhatsApp, TikTok, Instagram, Facebook Messenger, WeChat, Make, Pipedrive

A respond.io AI Agent handles the first stage of incoming conversations across five channels. It collects prospect details over chat from one set of instructions, filters spam and irrelevant messages, and routes residential inquiries to the sales team and hotel inquiries to a hotel agent. Lifecycle stages track each lead, and Make passes conversation and lead data to Pipedrive.

Result, as claimed

respond.io reports that 90% of irrelevant inquiries and spam are now filtered out automatically by the AI Agent. It says the WhatsApp conversion rate rose 2.5x, which it credits to AI qualification together with faster replies from the mobile app. It also says AI replies inside the WhatsApp window cut template fees that had cost about $350 a month.

Make moneyBusiness size: SoloIncludes prompt

A Belgian web designer says Make automations helped her 4x Diggiehippie revenue in under a year while keeping a full-time job

Ann Boen (Diggiehippie) · Belgium · Make

Ann used Make to automate Diggiehippie social posting and to evaluate leads, run email and WhatsApp follow-ups, and generate agreements and invoices, while she kept a full-time job.

Result, as claimed

Make's success story says Ann quadrupled Diggiehippie revenue in under one year. She automated social posting that had taken about ten hours a week, and built lead evaluation plus email and WhatsApp follow-ups that create agreements and invoices. She credits better follow-ups as one of the main reasons for the 4x. Absolute revenue figures are not given. Country confirmed from her Diggiehippie site and LinkedIn (Massenhoven / Antwerp area, Belgium).