Workflow Demo

Agents can find the local businesses that aren't advertising yet. Small agencies need that list.

Two founders pointed agents at their local markets and asked a new question: who's missing something? One found that none of the top 10 gyms in Palm Beach County were running Meta ads. Another cut 310 Phoenix HVAC companies to 30 with no after-hours line, overnight. Small agencies would pay for that list.

Published Oct 21, 2026

The Wow

What someone built

Miles Ketcham had his agent team rank 36 gyms and studios in Palm Beach County for his ad agency, then checked the top 10 in Meta's Ad Library: none were running Meta ads (Oct 19, 2026). VORLEN_X ran an agent overnight with one rule, "public data only. invent nothing. contact nobody without my yes": it pulled 310 HVAC companies from map listings, removed 41 franchises, read 251 live websites, kept 30 with no after-hours line, drafted an opener for each, sent none, and deleted 3 of its own claims it couldn't prove (Oct 20, 2026).

Workflow Demo

License
A method described in public posts; no code or template is shared. Write your own implementation
To use it
Nothing to install. The BUILD IT steps below are our own version of the method.
A business you could build on it
Ad-gap prospect reports for small local agencies

Why it's remarkable

Lead lists tell you who exists. These agents find the gap itself, with evidence: the one thing a business is missing that an agency happens to sell. And one of them was built to invent nothing and contact nobody, which is exactly the shape a sellable report needs.

The Opportunity

The business it reveals

A monthly "gap report" per vertical and territory: the gyms with no ads, the HVAC firms with no after-hours line, the dentists with no online booking. Agencies and freelance media buyers already spend hours building these lists by hand.

Who would pay

Two- to ten-person local marketing agencies and freelance media buyers who work one vertical and one area at a time. Lead-list tools already sell raw business data to the same buyers.

The Flip

3 ways you could turn this into a business

Missed-call gap lists for answering services

Who pays
Answering services and AI receptionist resellers
How it would earn
A monthly list of businesses with no after-hours line in a chosen trade and city (our hypothesis)
Why it might work
The overnight run filtered 251 websites down to 30 with no after-hours line, which is exactly the buyer an answering service wants.
What already exists
The AI receptionist market is crowded, so resellers need targeting; generic lead lists don't show after-hours coverage.

Territory gap audits for franchise development teams

Who pays
Franchise brands and multi-location owners sizing up a new territory
How it would earn
A one-time audit of independent competitors' gaps (ads, booking, reviews) in a territory (our hypothesis)
Why it might work
The same checks show where independents are weak before a location opens.
What already exists
Market-research firms and franchise consultants already do territory studies, more broadly and at higher prices.

Why we'd try "Ad-gap prospect reports for small local agencies" first: The buyer is easy to name and reach, the research is what agents already do well, and a 10-business sample is a pitch you can make this week.

Build It

How you could build it

A repeatable gap report: ranked businesses, the gap each one shows, the evidence, the date checked, and a one-line opener.

First step: Pick one vertical in your town, have your agent rank 30 independent businesses from official listings data, then check the top 10 yourself in Meta's Ad Library. Count how many show no ads.

Agents and tools

  • Your AI agent with browsing and code
  • Google Places API
  • Meta Ad Library (browser, checked by hand)
  • Google Sheets

Setup

  1. Choose one vertical and one county.
  2. Get a Places API key and keep within its terms.
  3. Write the gap checks you'll run (site has no Meta or Google tag, no online booking, no after-hours line).
  4. Make a report template with an evidence and date column.
  5. Build one sample report and check every row by hand.

What the agent does

  • Pulls and ranks businesses from official listings data
  • Removes franchises and chains
  • Reads each business's public website for the chosen gaps
  • Drafts a one-line opener per business
  • Flags any claim it couldn't verify

What you do

  • Checks the top results in Meta's Ad Library by hand
  • Confirms every gap before delivery
  • Sells the report and sets the price
  • Leaves all outreach to the agency

Your first customer: A local agency owner you show a free 10-business sample for their own vertical.

Test demand first: Show the 10-business sample to five agency owners. Success: at least one asks for the full county list or agrees to a paid pilot. Failure: nobody does, which suggests gaps aren't what agencies buy.

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.

Get a launch plan

Running it

What stays human: Choosing the vertical and area with the buyer; checking the top results by hand in Meta's Ad Library (see risks); confirming each gap before it goes in the report; selling the report. The agency, not the agent, contacts the businesses.

Startup cost (estimate)
About $0 to start (Estimate: Meta's Ad Library is free in the browser, and Google lists a monthly free usage allowance for the Places API on its pricing page (check current limits). Not measured)
Running cost
Agent usage and the minutes of hand-checking per report are unknown until a pilot measures them.
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: Both runs are the creators' own posts on X (Oct 19 and Oct 20, 2026). We read them; we haven't rerun them. The dollar figure in one post is the creator's target for his own offer, not money earned.

What's ours: The monthly gap report is our application, built on official data sources and checked by a person before delivery.

Worth planning around

  • Meta's Ad Library API doesn't return ordinary commercial ads in the US, so the ad check is a manual browser lookup; automated collection from Meta's site breaks its terms.
  • Use the official Places API for listings rather than scraping maps.
  • No ads found on the date checked isn't proof a business never advertises; say exactly that in the report.
  • The agency's cold emails are commercial email with CAN-SPAM duties.

Sources

Sources reopened Oct 21, 2026. Spot a mistake? Tell us and we'll correct it in public.

Keep reading

The Daily Paycheck: one remarkable AI business at a time, and exactly how you could build around it. Free; unsubscribe anytime.

Get new AI business discoveries by email.