> ## Documentation Index > Fetch the complete documentation index at: https://docs.tythe.finance/llms.txt > Use this file to discover all available pages before exploring further. # Principal Underwriting > How the Credit Rating and the Credit Limit are produced, what moves them, what they drive, and how to dispute them. Every principal is underwritten from its first day on Tythe, using its on-chain history alone. Everything it does afterwards, on Tythe and, with consent, in its bank accounts, sharpens the picture. This page explains the sources, the model, the outputs, and the process for disputing a result. ### Three sources | Source | What it contains | Availability | Weight | | ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------ | --------- | | On-chain activity | The history of every wallet you bind, across Base and Ethereum: stablecoin and major-asset flows, counterparties and their concentration, balance history and volatility, wallet age and continuity, protocol interactions. Transfers are classified into economic events (revenue in, payments out, treasury moves, financing) against a labelled counterparty registry. | Day one, no permission needed | Baseline | | Activity on Tythe | Every receipt, mandate adherence, Loan repayment, Lend and Save behaviour. First-party and verified at the source. | Accrues from your first action | Strongest | | Bank data | Balances and up to 24 months of categorised transactions through a regional provider, with a signed Data Consent. | Optional, revocable | Extension | Each feature the model uses carries a provenance weight: activity on Tythe outranks bank data, which outranks inferred on-chain activity. The model uses both the value and its provenance. ### Graceful degradation A principal is ratable on the first source alone. The second and third sources tighten the confidence band and, over time, raise the Credit Rating and the Credit Limit. A principal that never connects a bank account and never borrows is still rated, from on-chain history and whatever it does on Tythe. ### The model The Entity Underwriting Engine is a constrained machine-learning model. Three things make it constrained. * **Structure.** Established credit science is encoded as feature design and monotonic constraints, so the model cannot contradict it. Greater revenue stability can never lower a Rating. Higher counterparty concentration can never raise one. A longer clean repayment history can never hurt one. * **Training and calibration data.** The model is trained on public on-chain data at scale, using measurable proxies for financial durability (activity survival, cashflow continuity, drawdown recovery, counterparty churn), and calibrated on the public outcomes of undercollateralised on-chain credit protocols. Credit Limits are set conservatively at launch by calibration. * **Continuous learning and versioning.** Every underwriting decision and every Loan outcome on Tythe is logged as a labelled example. The model is retrained on a schedule. Every version is recorded in the attestation that carries your Rating, so a version can be retired by governance and any decision traced to the version and inputs that produced it. The model produces reason codes for every rating. It never uses protected characteristics. ### Outputs and what they drive | Output | What it is | What it drives | | --------------- | ---------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- | | Credit Rating | A bounded score of creditworthiness | Your Rating band | | Credit Limit | A USDC ceiling sized to serviceable capacity and anchored to durable revenue | The credit envelope your agents draw within; your own direct draws | | Rating band | The tier your Rating falls in | The fraction of your balance pledged as Coverage on each Loan; the APR curve your Loans price from | | Confidence band | How tightly the Rating is known | Wider with fewer sources; narrows as sources connect and history accrues | | Reason codes | The top factors behind the Rating | Shown in your console; the basis of a dispute | Your Credit Limit can fall on re-rating. Existing Loans keep their terms. New draws shrink to the new available limit, and your agents' credit shares shrink with it. ### Cadence and triggers Ratings are refreshed weekly and on triggers: a large balance change, a missed capture, a dispute, a newly connected source, a suspension. Each refresh produces a new attestation. ### Disputes Your console shows the reason codes behind every rating. Each rating lists the factors that most affected it and the direction of their effect. Submit the dispute from the console with the factor you contest and any supporting information. Tythe reviews the inputs and the model's treatment of them. Where an input was wrong or the model mis-handled it, the correction lands in your next attestation. Ratings are assessments, not negotiations. A dispute can correct an error; it cannot change a rating that reflects the data correctly. ### What is never used Protected characteristics. Data you have not consented to. Bank data outside its consented scope. Data from other principals' bank accounts. For developers. A principal's current Rating and Credit Limit are readable on-chain from the attestation registry, with the model version and expiry. See the [contract reference](/developers/contract-reference). How each agent earns its effective scope inside the ceiling you set. How the Credit Rating and the Credit Limit become Loans.