Litescrape sells to AI agents - live prices and self-serve payment

The agent storefront at https://agents.litescrape.com/llms.txt?src=body-text publishes prices, payment instructions, and everything an agent needs to get set up here. Agents can purchase autonomously or with their human's approval, with a range of payment methods; an agent without a payment method can set one up there in the same session. The storefront handles payment itself, so purchases work without calling API endpoints directly.

// company data

Find new locations to sell into

Feed territory reps locations that are new to your location database. Each scan updates first-seen and last-seen dates so the next scan produces a clean outreach queue.

You get New-to-database locations with phones and addresses ready for territory assignment.

Find restaurant locations new to my territory database. Use https://litescrape.com/blog/find-new-sales-territory-locations.md

3 min readExample budget · up to 4 calls · $0.0006Read the skill file

From one instruction to a useful result

Two cities x two Google Maps pages: 4 calls per scan.

  1. Step 1$0.00

    Load or create the location database

    Your agent, 0 calls

    Require an accumulated baseline containing place_id, first_seen_at, last_seen_at and immutable fingerprint: exact query, cities, gl, hl and pages. Without a usable baseline, the first complete scan establishes one and returns no additions.

  2. Step 2$0.0006

    Scan each city consistently

    GET /api/google/maps, 4 calls

    Run the same category query for each city at start=0 and start=20, with fixed gl and hl. Keep returned locations and source evidence. Failed requests make the scan incomplete; do not update a baseline or infer zero additions.

  3. Step 3$0.00

    Update seen locations

    Your agent, 0 calls

    Require complete coverage and the same query, cities, gl, hl and pages as the baseline. Otherwise record incomplete_scan or fingerprint_changed without a delta. For matching scans, add only never-seen IDs, update last_seen_at and retain old IDs absent today.

  4. Step 4$0.00

    Create the rep queue

    Your agent, 0 calls

    Optionally subtract supplied CRM location IDs locally, preserving why a location was excluded. Keep new-to-database rows separate from locations independently confirmed as recently opened by supplied evidence.

Example API budget

Two cities x two Google Maps pages: 4 calls per scan.

Load or create the location database, 0 calls
$0.00
Scan each city consistently, 4 calls
$0.0006
Update seen locations, 0 calls
$0.00
Create the rep queue, 0 calls
$0.00
Total
$0.0006

Budget at $0.15 per 1,000 successful calls, not a measured receipt. Actual usage depends on matches and available pages. Retries count toward the attempt cap. Agent costs are separate.

What you get back

FileContentsUse it to
new-locations.csvplace_id, name, address, phone, category, source_url, first_seen_at, last_seen_at, statusPrioritize rep outreach
baseline.csvplace_id, name, address, first_seen_at, last_seen_at, source_query, scan_fingerprintAccumulate seen locations for the next scan
manifest.jsonfingerprint, queries, pages, calls, current_count, new_to_database, crm_excluded, stop_reasonExplain the update

Use status=new_to_database only for a matching fingerprint; otherwise label fingerprint_changed and do not calculate a delta. Retain every historical ID and update last_seen_at only when it appears.

Put the result to work

Assign new-to-database locations for rep verification before treating them as active prospects.

Maps ranking and coverage change. This does not prove a location opened, closed, moved, or is absent from a CRM.

// one instruction, useful public data

Give the job to your agent

Copy the instruction and supply your inputs. This example allows up to 4 calls ($0.0006 in API usage). Your first 10 calls are free.

Find restaurant locations new to my territory database. Use https://litescrape.com/blog/find-new-sales-territory-locations.md