Every new Texas company, in a sheet by 7 AM: sell fresh-business feeds to the firms that serve them
A builder wired n8n to drop every new UK company registration into Google Sheets each morning, for about $0.25 per 100 rows. Texas publishes the same kind of data free: a state dataset with over 3 million entities and their charter dates, updated weekly.
Published Oct 27, 2026
The Wow
What someone built
An n8n workflow that pulls the newest UK Companies House registrations through a scraper each morning and appends name, number, type, address and industry code to a sheet.
- License
- Tutorial on DEV; UK registry data under the Open Government Licence v3.0. Texas data is published on data.texas.gov
- Install
- Follow the tutorial for the UK, or point a scheduled script at the data.texas.gov dataset and filter on sos_charter_date.
- A business you could build on it
- New-company feed for one Texas county
Why it's remarkable
The whole pipeline costs pennies a day. In Texas you don't even need the scraper: data.texas.gov serves new charters through an open API.
The Opportunity
The business it reveals
Sell a filtered weekly sheet of new companies in one county to the local firms that want to meet them first.
Who would pay
CPAs, bookkeepers, insurance agents, small-business bankers, payroll providers and web designers.
The Flip
3 ways you could turn this into a business
New-company feed for one Texas county
- Who pays
- CPAs, bookkeepers, insurance agents and small-business bankers
- How it would earn
- A monthly subscription per firm for a weekly filtered sheet (our hypothesis)
- Why it might work
- One new client covers years of the fee, and the data is free to pull, so margins are high.
- What already exists
- Commercial new-business list vendors, checking the state site by hand, or word of mouth.
Niche feed: new trucking and logistics companies
- Who pays
- Truck insurance agents, factoring companies, CDL schools and compliance services
- How it would earn
- A premium monthly feed filtered to transport-related new entities (our hypothesis)
- Why it might work
- New carriers need insurance, factoring and drivers right away, and the vendors who serve them compete on speed.
- What already exists
- FMCSA new-authority lists sold by data vendors and manual registry checks.
New-business welcome mailer service
- Who pays
- Local firms that want to reach new businesses by mail
- How it would earn
- A per-campaign fee to turn the feed into printed welcome letters or postcards sent to registered addresses (our hypothesis)
- Why it might work
- Mail to a registered business address is a familiar, low-risk channel, and the feed gives perfect timing.
- What already exists
- Direct-mail agencies and EDDM postcards.
Why we'd try "New-company feed for one Texas county" first: Free data, a buyer who already pays for leads, and a product you can sample to them next Monday.
Build It
How you could build it
A scheduled pull of newly chartered Texas companies for chosen counties, tagged by likely business category, delivered to subscribers as a weekly Google Sheet.
First step: Query data.texas.gov's Active Franchise Taxpayers dataset for your county with a sos_charter_date in the last 14 days, clean it into a sheet, and send it as a free sample to one bookkeeper you know.
Agents and tools
- data.texas.gov API (dataset 9cir-efmm)
- n8n, Make or a scheduled script
- Google Sheets
- An AI model to tag business category (ChatGPT, Claude, Gemini, Grok Bot or similar)
Setup
- Pull rows where sos_charter_date is in the last 7 days and taxpayer_county_code matches your county.
- Drop exempt and non-operating records and obvious holding companies.
- Tag each company's likely category from its name and entity type.
- Write one tab per subscriber niche and share the sheet.
- Schedule it weekly and spot-check each run.
What the agent does
- Writes and maintains the query
- Tags likely business category
- Flags probable shells and duplicates
- Summarizes the week's new companies
What you do
- Chooses counties and niches
- Sells to local firms
- Checks quality each week
- Handles customer requests
Your first customer: A bookkeeper or independent insurance agent in your county, given two free weekly sheets before you ask for a subscription.
Test demand first: Send a free weekly sheet to five local firms for two weeks. Success: at least two say a lead was new to them and one agrees to pay for the next month.
Your starter instructions
Paste this into the AI agent you use (ChatGPT, Claude, Gemini, Grok Bot or another) as your first message. Copying it starts work in your own agent; it doesn't create or deploy a business by itself.
Running it
What stays human: Choosing the niche and counties, checking each week's feed for junk entries, selling to local firms, and handling cancellations and requests.
- Startup cost (estimate)
- Under $50 to start (estimate) (Estimate: the Texas dataset is free to query; costs are an automation plan or a small server and light AI usage. The UK route adds about $0.25 per 100 rows per the tutorial)
- Running cost
- Under $30 a month (estimate) (Rough estimate: automation runs and AI tagging for a few thousand rows a month; not measured)
- How much the agent runs
- Agents run one core part; people run the rest.
Pricing your own version? Use the free startup-cost worksheet.
The evidence
What the source shows: The creator's DEV tutorial and the Texas Comptroller's Active Franchise Taxpayers dataset (updated Oct 24, 2026). We checked both.
What's ours: The Texas feed, the niches, the pricing and the flips are our application.
Worth planning around
- Many new entities are holding companies that never trade, so the feed needs filtering.
- Buyers who contact these companies must follow do-not-call lists and anti-spam law.
- Paid new-business list vendors already exist; the edge is local focus and freshness.
Sources
- steadfetch: New UK company registrations in Google Sheets every morning with n8n (DEV)
- Texas Comptroller: Active Franchise Taxpayers dataset (data.texas.gov)
Sources reopened Oct 27, 2026. Spot a mistake? Tell us and we'll correct it in public.
Keep reading
- How people make money with n8n (guide)
- How much of the work do AI agents actually run? (guide)
- He still can't write code. His five-person ad agency now runs on about 270 tools he built with Claude. Every owner-run firm needs its first five
- A marketer who doesn't code built an elk-call coaching app with Claude Code and says it hit a $650K run rate in 110 days. Every skill learned by sound is the same opening
- A free n8n workflow flags fake supplier invoices before anyone pays them — and Germany's e-invoice switch makes it a service bookkeepers can sell
- Marc Lou's agent chased a broken-shoe refund through three support desks and got his 850 AED back. Small stores now need a claims desk that can answer agents
- Every discovery and launch plan