Kevin Welter.
ENDE

My AI employee

Qualified leads from Google Maps.

Olaf has been running in my business since July 2026, and there's a ready-made template for him in Premium.

I give Olaf a location, an industry and the traits of my ideal customer. He searches Google Maps and public company pages, checks every candidate against the same criteria and returns only the matching businesses as a rated, documented list. He can look for outdated websites, but he can also identify other target customers when their traits can be verified publicly.

My implemented use case: finding local businesses with outdated websites.

Join the communityRead first: Learning Claude
View community

198

candidates screened

8

documented assignments

2×

check before handover

Lead scout

Use case: finding outdated websites

This is the use case I have already implemented and tested: eight lead runs across eight locations of different sizes, from small town to city.

198

Candidates screened

8

Assignments

3 to 5 real leads per 20 candidates

Rule of thumb

The rule of thumb from his own course holds across every single run: regardless of whether the town is big or small, 20 screened candidates turn into 3 to 5 real leads, the rest fails the criteria. One example from a run: a beauty studio, 4.9 stars from more than 70 reviews, but no HTTPS and no mobile viewport tag, address and phone number checked beforehand against the public Google profile.

The more honest part is what Olaf discards himself. In the same runs he caught several of his own false alarms: a site with outdated tech underneath but a modern, working design; another with an old copyright year in the footer but otherwise built to current standards. Both were flagged as false alarms instead of counted as leads. Even so, the first cross-check by my website colleague Ralf still found errors in 4 of 10 briefings, which is why every lead now gets checked a second time before handover.

Olaf for your business

Not just old websites. Olaf searches for your ideal customers.

My use case screens local businesses for outdated websites. You replace the industry, location and scoring matrix with the publicly verifiable traits that matter for your offer.

How I use him

Find local businesses with outdated websites

Olaf searches Google Maps, checks the website, technology and business details, rejects false positives and delivers a documented shortlist for Ralf's website offer.

Adapted to you

Your search area and lead criteria

You define the location, industry, required traits, exclusion rules and weighting. Olaf applies the same review to every candidate and documents why each one fits or gets removed.

What you change

  • Location, region or search radius
  • Industry and business type
  • Publicly verifiable traits
  • Scoring and exclusion rules

Other possible uses

  • Practices without online booking
  • Hotels with weak reviews
  • Businesses without a careers section
  • Multi-location companies in a target region

The process stays: Search Google Maps systematically, verify every claim against a public source, reject false positives and hand over only evidence-backed leads.

How Olaf turns Google Maps into a qualified lead list

The target audience can change while the process stays the same: search, filter against your criteria, and document the result.

01

Search by location and industry

Olaf gathers suitable businesses through Google Maps and the Google Places API. He works through the search one location and one industry at a time.

Result: a complete candidate list for the next screening step.

02

Rate against your criteria

You define what makes a lead relevant. That can be an outdated website, specific reviews, a location, a type of business or other traits that can be verified publicly.

Result: unsuitable candidates are removed with a documented reason.

03

Verify evidence and document it

Olaf checks websites, public profiles and screenshots where needed. For every remaining lead, he records the source, reason and rating instead of returning a loose address list.

Result: a prioritized shortlist you can continue working with.

What he can't do, where I approve

He contacts no one. No emails, no calls, no trace at the company. Pure research on public data.

Addresses, contact details and company traits are never guessed. Anything that cannot be backed by a public source is marked as unclear or discarded.

Olaf needs clear criteria before a run. He doesn't decide which target audience makes commercial sense for your offer.

A handover for further work only happens once I say so explicitly. Never on his own.

Learn the process. Or load Olaf directly.

Standard

Standard: build it yourself

$5a month

Learn the structure, rules and approval gates, then adapt Olaf to your own business.

  • Understand the build step by step
  • Adapt rules and examples to your own business

Premium

Ready-made template

Premium: ready-made template

$149a month

Olaf is a ready-made package in the community.

  • Load Olaf as a proven employee folder
  • Adapt the template to your workflows and approvals
  • Community and course in one shared workspace
Join the community

As of October 29, 2026

Frequently asked questions about Olaf

Can AI find new customers?

AI can take over the groundwork: finding public businesses, checking them against clear criteria and documenting a prioritized shortlist. Olaf delivers the checked list; the contact and the deal are still up to me.

Can Olaf only find businesses with outdated websites?

No. That is the use case I have already implemented. Olaf can also identify other target customers when I provide a location, industry and reliable selection criteria that can be checked publicly.

What does an AI tool for outreach cost?

Olaf runs on my Claude subscription plus the Google Places API, which costs small cent amounts per query. There's no separate license fee for the tool itself.

Does AI replace cold calling?

No, it replaces the research beforehand. Olaf contacts no one; he delivers a rated list. Whoever calls or writes afterwards is still me.

Which AI is suited to researching companies?

For structured, repeatable research, an AI employee with a fixed tool chain works better than a single chat: the same search area, the same criteria and the same checks every time.

Is an AI employee worth it for consultants and agencies?

Anywhere a pre-qualification step checks many candidates against a few criteria, this is a good starting point: consultants and agencies with their own target definition can rebuild the same tool chain around their own criteria.

Want to know who you should be searching for next?

Olaf's template is in the community. You take the tool chain and adapt the search area, target audience and scoring matrix to your offer.

Join the community

Read on

Also:Finding New Clients as a Freelancer·Winning New Customers in the Trades·Winning New Clients as an Insurance Broker·Learn Claude: The Path in Five Stages·Hiring an AI Employee: The Process·Creating an AI Employee: How to Start·AI Employees for Consultants and Agencies·My AI Workforce: Fourteen Employees, One Boss·Hire your first AI employee·Back to the org chart