Save moneyBusiness size: Small team

A couple used ChatGPT to open a Thai home kitchen instead of a restaurant lease and cut startup capital by more than 90%

Matt Rosenberg and Chef Kamonwan (Bangkok Rush Thai Kitchen) · United States · ChatGPT

Go to the skill

What the agent did

Matt Rosenberg left a digital marketing job to open a Thai restaurant with his wife, Chef Kamonwan. He used ChatGPT to size up neighbourhoods, model food and labour costs and learn about kitchen buildouts, and the numbers did not work for a lease. ChatGPT pointed to a legal home kitchen permit, a Microenterprise Home Kitchen Operation, and turned the regulations into checklists for permits and inspection. Once open in Alameda, it drafts replies to every Google and Yelp review, runs margin analysis per dish and plans a weekly social media calendar.

Result, as claimed

OpenAI reports the pivot "cut startup capital by more than 90%, from a potential six-figure lease to a few thousand dollars in permits and equipment." Switching from an LLC to a sole proprietorship saved nearly $1,400 a year, and review replies went from a day to under four hours. He says ChatGPT cut his manual workload by more than half.

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 the Bangkok Rush story on OpenAI Academy

Try it yourself

Before you sign a lease, ask an AI to model the numbers and list every legal way to start smaller.

Difficulty: Beginner

Prompt

I want to start a [type of food business] in [city, state or country] with a budget of [amount]. 1. Model monthly costs and break even for a shop lease versus any home kitchen, cottage food, market stall or shared kitchen option that is legal here. 2. For each legal option, list the permits, inspections and limits, with links to the official pages. 3. Turn the cheapest workable option into a step by step checklist with dates.

Tools

  • ChatGPT Named in the story. He used it for cost modelling, permit checklists, review replies and margin analysis

Steps

  1. Run the prompt with your real budget and city.
  2. Open every official link and confirm the rules yourself, or call the local health department.
  3. Pick the cheapest legal option and work through the checklist.
  4. After launch, use the same chat to price dishes from your actual ingredient costs.

Watch out: Home kitchen rules differ by city and change often. Confirm with the official health authority before you spend money, and do not rely on an AI summary for legal or tax structure decisions.

Starter version by Solopreneur Code

Skill: Planning and reviews

Add this skill

Planning and reviewsDifficulty: Beginner

Start-small food business check

Models a shop lease against legal smaller options such as a home kitchen, lists the permits and turns the cheapest workable one into a checklist.

Works with
ChatGPT, Claude, Gemini Needs an AI that can browse official pages. The story used ChatGPT.
Tools in the story
ChatGPT
Country
United States

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
Save moneyBusiness size: Small teamIncludes prompt

An 8-person AI company runs written AI playbooks in the background, and its CEO says it would otherwise need four to five more hires

Rachel Woods · Country unknown · Claude Code, Claude, ChatGPT

AI agents run AMP's department playbooks in the background through Claude Code. One reviews sales calls against company standards. Another answers sales team questions from the team's guide.

Result, as claimed

Woods says AMP has four full-time employees and four part-time contractors and would need at least four to five more people without its AI playbooks, including a sales and marketing manager, customer support specialist, executive assistant and operations coordinator. In September it spent $8,510 on Claude Code usage to run the playbooks, on top of team Claude and ChatGPT subscriptions.

Save moneyBusiness size: Small teamIncludes prompt

A 14-truck Tennessee fleet owner built his own trucking back office with Claude Code and ChatGPT for $55 a month and says it saves 20 to 25 hours a week

Wes Oberman · United States · Claude Code, ChatGPT, Claude Sonnet 4.6, Claude Opus 4.8, GitHub, Supabase, Vercel, Resend

Claude Code built the system from prompts ChatGPT drafted. In daily use, Claude Sonnet 4.6, backed up by Claude Opus 4.8, reads a broker rate confirmation PDF and fills the load fields in 15 to 20 seconds, including deduction terms. The system emails load details to the owner operator, tracks status to delivery, and combines invoice, rate confirmation and proof of delivery into one PDF for the broker.

Result, as claimed

Oberman says the system saves 20 to 25 hours a week and costs $55 a month in tool subscriptions, against a cheapest outside quote of about $1,500 a month. A separate AI settlement tool he built cut his wife's Thursday settlements from a 12-hour day to about an hour.

Eugene Tan, owner of Serangoon BBQ & Curry, photographs the parts of a new dish on his phone and feeds the pictures into ChatGPT along with a reference image. The Straits Times says the marketing material is ready in a few minutes.

Result, as claimed

The Straits Times reports that two years ago he would have budgeted around $2,000 for a full day of photography and several weeks of work. He switched to AI photos in 2025 and now makes the material for around $25 a month. He says a new product can be launched and promoted in as few as five days.