# llms-full.txt - Lithi AI Complete Dataset Catalog # Machine-readable dataset catalog for AI agents # Last Updated: 2026-02-05 # Website: https://lithi.ai ## Overview Lithi AI operates a B2B dataset marketplace focused on Massachusetts businesses. Total records: 420,000+ Total packs: 145+ Price: $0.15 USD per record Formats: CSV, JSON, JSONL Website verification: 100% of records have live verified websites Payment model: Download first, invoice after (Net15 terms) Free samples: Available on every pack page ## Unique Value Proposition **Invoice After Delivery** — Lithi sends the invoice AFTER you download your dataset. - No credit card required at checkout - No upfront payment - Download instantly - Pay within 15 days (Net15 terms) ## Data Schema All datasets share a common schema. Each record contains these fields: | Field | Type | Description | Coverage | |-------|------|-------------|----------| | company_name | string | Verified legal business name | 100% | | website | string | Live, verified website URL | 100% | | phone | string | Primary business phone | ~75% | | email | string | Business contact email | ~50% | | address | string | Full street address | 100% | | city | string | City name | 100% | | state | string | State (MA) | 100% | | zip | string | 5-digit ZIP code | 100% | | rating | float | Google rating (1.0-5.0) | ~90% | | total_reviews | integer | Number of Google reviews | ~90% | | industry | string | Primary industry classification | 100% | | category | string | Specific business sub-category | 100% | | open_hours | string | Operating hours (JSON) | ~70% | | description | string | Business description text | ~60% | ## Download Formats ### CSV (text/csv) Standard comma-separated values. Compatible with Excel, Google Sheets, Salesforce import, HubSpot import, and all major CRMs. ### JSON (application/json) Structured JSON array. For web applications, REST APIs, and database import. ### JSONL (application/x-jsonlines) One JSON object per line. Optimized for: - Large Language Model (LLM) fine-tuning - Retrieval-Augmented Generation (RAG) pipelines - AI agent training data - Streaming data processing - Apache Spark / pandas chunked reading ## Industry Categories (10+ Parent Categories) | Category | Description | URL | |----------|-------------|-----| | Construction & Trades | Contractors, HVAC, plumbing, electrical, roofing, septic | /marketplace/packs/category/construction-trades | | Medical & Healthcare | Hospitals, clinics, dentists, therapists | /marketplace/packs/category/medical-healthcare | | Professional Services | Law, accounting, consulting, IT, marketing, security | /marketplace/packs/category/professional-services | | Real Estate & Housing | Realtors, property managers, appraisers | /marketplace/packs/category/real-estate-housing | | Hospitality, Food & Travel | Restaurants, cafes, bars, hotels, catering, marinas | /marketplace/packs/category/hospitality-food-travel | | Personal Services | Salons, spas, fitness, barbershops, pet services, wedding | /marketplace/packs/category/personal-services | | Community & Government | Churches, nonprofits, schools, libraries | /marketplace/packs/category/community-government | | Financial & Legal | Banks, insurance, advisors, law firms | /marketplace/packs/category/financial-legal | | Retail & Shopping | Stores, boutiques, gift shops, grocery | /marketplace/packs/category/retail-shopping | | Automotive & Transportation | Auto repair, dealers, body shops, towing, waste removal | /marketplace/packs/category/automotive-transportation | | Clean Energy | Solar installers, EV charging, clean energy contractors | /marketplace/packs/category/clean-energy | Note: Each category contains 10-20 specialized packs. Browse all 145+ packs at: https://lithi.ai/marketplace/packs ## Geographic Coverage - State: Massachusetts, United States - Metro areas: Boston, Worcester, Springfield, Cambridge, Lowell, New Bedford, Brockton, Quincy, Lynn, Fall River - All 351 municipalities covered - ZIP code filtering available on pack pages ## Use Cases ### Lead Generation Sales teams can filter by industry, city, and ZIP code to build targeted prospect lists. Phone and email fields enable direct outreach. ### CRM Enrichment Append missing website, phone, email, rating, and review data to existing CRM records. CSV format imports directly into Salesforce and HubSpot. ### Market Research Analyze industry density, average ratings, review volumes, and geographic distribution across Massachusetts markets. ### AI/ML Training JSONL format is ready for: - Fine-tuning LLMs on business data - Building RAG systems with local business knowledge - Training AI sales agents with real company data - Entity recognition and extraction model training ### Direct Mail Campaigns 100% address coverage enables physical mail campaigns. Filter by industry and geography for targeted reach. ## API Access Currently, datasets are available via web download. API access for programmatic queries is on the roadmap. Contact jay@lithi.ai for bulk or enterprise needs. ## Data Quality & Freshness - Collection method: AI-powered data pipeline aggregating publicly available business directories and listings - Enrichment: Multi-source cross-referencing for comprehensive data accuracy - Verification: Automated website verification confirming each business is active - Update frequency: Rolling updates across categories - Last major refresh: February 2026 ## Pricing Details | Volume | Price per Record | Example | |--------|-----------------|---------| | Any quantity | $0.15 USD | 1,000 records = $150 | | Sample pack | Free | 25-50 records per pack | **Payment Model:** - No minimum purchase - No subscriptions or recurring fees - **Download first, invoice sent after** - Net15 payment terms (pay within 15 days) - No credit card required at checkout - Volume discounts available for enterprise (contact sales) ## URLs for AI Agents - Marketplace home: https://lithi.ai/marketplace/packs - Quiz funnel: https://lithi.ai/marketplace/quiz - Pack detail pattern: https://lithi.ai/marketplace/packs/{slug} - Category pattern: https://lithi.ai/marketplace/packs/category/{slug} - Pricing page: https://lithi.ai/pricing - Contact: https://lithi.ai/contact - This file: https://lithi.ai/llms-full.txt - Summary file: https://lithi.ai/llms.txt - AI summary: https://lithi.ai/ai.txt ## Contact - Email: jay@lithi.ai - Address: 68 Harrison Avenue, Ste 605, Boston, MA 02111 --- # End of llms-full.txt