I built ClientScout to help find the next client

Description and use

ClientScout streamlines client discovery for freelancers by aggregating business listings, generating structured profiles, and assessing relevance with Gemini and Gemma 4.

Problem

Freelancers and small agencies struggle to identify suitable business customers for their services.

Outcome

ClientScout consolidates prospect research, reducing manual effort and providing structured, vetted leads with contact details and relevance notes.

Workflow

• 1. Enter offer description, business type, and location. 2. ClientScout queries SerpApi for public Google Maps listings. 3. Gemini processes listings to create structured profiles. 4. Gemma 4 reviews each profile for relevance and drafts an opening. 5. User reviews profiles, saves prospects, filters, or exports CSV.
• 6. Optionally prepare an introduction using the editable template.
• 7. No automatic outreach is performed; the user sends outreach manually.

Evidence

SerpApi searches Google Maps for the requested business type and location. That gives the app public listing details to work with, including names, addresses, websites, and phone numbers when listed.

Source

Gemini reads those listings alongside the user's offer and turns them into structured profiles.

Source

Gemma 4 reviews how each business fits the offer. It suggests a possible opening and explains what's still unknown, such as the business's current setup or interest in the service.

Source

The hosted app uses gemma-4-26b-a4b-it through Google's API. A live test returned three guesthouses around Galle with public listing phone numbers and source links.

Source

Render hosts the Next.js app and its server routes. API keys stay on the server. Saved prospects stay in browser storage, so you don't need an account to try the workspace.

Source