Trust center
A serious buyer product is built on evidence, not mystery.
Twellie publishes a source-backed evidence dossier: exact-property facts, qualified closed-sale records, available history, cost assumptions, provenance, gaps, and follow-up tasks. Automated valuations, fair-price labels, model adjustments, and offer ceilings stay out of customer output while prospective validation remains incomplete.
Core logic
Rules before words
Property matching, evidence status, closed-sale qualification, and public redaction come from stored deterministic rules. Explanatory text cannot add an unpublished price conclusion.
Accuracy policy
No fake percentage
We do not publish a price-accuracy claim or customer valuation. Any future valuation release requires a prospective, segmented benchmark and a separately reviewed product change.
Report proof
Source status stays visible
Material inputs are labelled as supported, partial, missing, conflicting, demo, or needing verification when that status is known.
User promise
Explicit scope
The dossier states what each source can establish, what remains unknown, and which professional must verify it. It never turns a missing price conclusion into a failed customer section.
Reliability roadmap
The operating plan
01
Data moat
Unify live listings, closed comps, public records, tax, permits, hazards, photos, insurance signals, and buyer context into one normalized property graph.
02
Evidence qualification
Apply deterministic checks to property identity, active listing facts, source freshness, and subject-relevant closed sales.
03
Diligence workflow
Convert available evidence into explicit gaps, responsible professionals, and transaction deadlines without recommending a price.
04
Proof trail
Every dossier stores source status, provider record references, retrieval dates, report scope, and generated-output timestamps.
05
Workflow capture
Attach verified inspection findings, written quotes, title documents, insurance evidence, lender terms, and closing records to the same property dossier.
06
Distribution
Win trust through public benchmarks, sample reports, buyer education, and partnerships with lenders, inspectors, attorneys, and buyer communities.
Accuracy transparency
What we will publish before claiming accuracy
Benchmark sample
Recent closed sales only; no stale deed prices or active listings.
Coverage split
City, ZIP, property type, price band, comp density, and data-source mode.
Metrics
Median absolute error, p90 absolute error, bias, evidence-range coverage, and median range width.
Failure cases
Rural homes, unusual architecture, thin comps, distressed sales, major unseen renovation.
Trust gates
What must be true before scale
500+ recent closed-sale rows in each launch market before local accuracy copy goes live.
Every report exposes live, hybrid, or demo data status in the header.
Every displayed sale keeps its recorded facts and source reference; model adjustments are not published.
Automated values, fair-price labels, and offer ceilings remain outside the public product.
Every explanation is grounded in stored source records, not free-form price opinion.
Plain-English promise
The report should make a buyer harder to mislead.
That means visible closed-sale evidence, explicit source gaps, known-versus-missing ownership costs, and no software-generated value or walk-away number.
