Valuebase
Valuebase builds AI-driven mass-appraisal valuations for property assessment offices, separating land and improvement values and layering on AI assistants that review appraisals, run ratio studies, and calculate effective age.
Best for: Property assessors, appraisers, and real estate valuation teams that need defensible, auditable mass-appraisal valuations across residential, commercial, and land parcels.
Last reviewed 6/2/26
Pricing
- • Transparent pricing based on jurisdiction size, with no long-term contracts and free tools available
- • Specific dollar amounts are not published on the company site
- Integrations
- ProVal, Tyler Technologies, Patriot Properties
- Property types
- Residential, Commercial, Land
- Geography served
- United States and Canada
How Valuebase uses AI[1]
Valuebase builds property valuations from an ensemble of nine independent machine learning models that value residential, commercial, and vacant parcels with land and improvements separated. It auto-enriches each parcel with 50+ derived features such as flood zones, topography, corner lots, and street frontage, and redraws neighborhoods from physical boundaries and market data. AI assistants then review appraisals: ValPal checks taxpayer appraisals for USPAP compliance and drafts appeal responses, RatioPal generates IAAO ratio studies (COD, PRD, PRB), and AgePal calculates consistent effective age across properties.
- • Ensemble of nine ML models valuing residential, commercial, and vacant property, with land and improvement values separated
- • Automatic parcel enrichment with 50+ features (flood zones, topography, corner lots, street frontage) and market-based neighborhood redrawing
- • ValPal AI assistant reviews appraisals for USPAP compliance, flags unsupported adjustments, and drafts appeal responses
- • RatioPal and AgePal automate IAAO ratio studies (COD, PRD, PRB) and effective-age calculations
- • Per vendor: 36 jurisdictions in use, typical 30-day deployment, open and auditable models rather than a black box
AI type: Ensemble machine learning automated valuation models plus LLM-based appraisal review assistants
API: unknown MCP: unknown
Recognition[4]
Key numbers[1][2][3]
- • Per vendor: 36 jurisdictions in use, ranging from 5,000-parcel rural counties to state departments of revenue
- • typical 30-day deployment
- • ensemble of nine ML models with 50+ derived parcel features
- • raised $1.6M pre-seed (2023) and $6.3M seed (2024).
Credibility[1][2][3][5]
- Founders & team
- Co-founded by Lars Doucet (CEO; author of 'Land is a Big Deal' and land-value-tax advocate) and Will Jarvis.
- Customers
- 30+ jurisdictions across the US and Canada, from rural counties to state departments of revenue, including Tooele County (UT), City of Salem (VA), Tom Green CAD (TX), and Warren County (KY).
- Investors
- Narya Capital (lead), with Sam Altman, Nat Friedman, Julian Weisser, and Mythos Ventures.
Founded
2022
Headquarters
Austin, Texas, USA
Stage
Seed
Employees
11-50
Related companies
Clear Capital
National real estate valuation technology company whose ClearAVM machine-learning model and Restb.ai computer vision power lending-grade automated valuations and appraisal review across the mortgage value chain.
ClearAVM is a machine-learning automated valuation model that the company says covers 95% of US homes across 120M-plus properties, trained on closed-sale and refinance appraisal benchmarks and updated hourly. Clear Capital acquired computer-vision firm Restb.ai, which extracts property condition and features from photos at up to 99% accuracy and processes over 2 billion images monthly, to enrich valuation analysis.
Finvise
Finvise runs a hybrid model: a machine-learning valuation engine trained on 54 million-plus data points generates a value, reviewed and signed off by a RICS surveyor. The company reports the model lands within 10 percent of a human RICS valuation in 95 percent of cases (tested on 3,000-plus properties) and produces reports in roughly two seconds.
Finvise runs a hybrid model: a machine-learning valuation engine trained on 54 million-plus data points generates a value, reviewed and signed off by a RICS surveyor. The company reports the model lands within 10 percent of a human RICS valuation in 95 percent of cases (tested on 3,000-plus properties) and produces reports in roughly two seconds.
Built AI
Built AI uses machine learning to extract structured data from deal documents such as offering memos and rent rolls, then auto-generates cash-flow models and business plans in minutes, work that previously took weeks in Argus and Excel.
Built AI uses machine learning to extract structured data from deal documents such as offering memos and rent rolls, then auto-generates cash-flow models and business plans in minutes, work that previously took weeks in Argus and Excel.