Credit Score
The credit score in this system is determined based on a combination of factors related to the user's API usage. The calculation involves several steps, each contributing to the final score:
Base Score:
The credit score starts with a base value, typically 600 points if the user has purchased API tokens (at least 1 USDT). But if the user never interact with the system, the credit score will be 500.
Model Usage:
WitchBot Usage: If the user has chatted with WitchBot more than 10 times, an additional 25 points are added to the credit score.
Pilot Kombat Usage: If the user has used Pilot Kombat and accumulated more than 100 points, an additional 25 points are added to the credit score.
Advanced Model Usage: If the user has collectively used advanced models using Context Pilot VSCode plugin
more than 10 times, another 25 points are added.
more than 100 times, another 25 points are added.
Usage Consistency:
The score considers how consistently the user interacts with the API over time. If the usage is spread evenly across different days, the credit score can be increased by up to 50 points. This is determined by analyzing the standard deviation of daily API usage, with more consistent usage leading to a higher score.
Credit Check (TODO):
More credit score will be added or deducted with the user's borrow and payback history, this part will be added in the future.
Professional skills (TODO):
signals of showing the skillset for using AI solving complicated real problems will be treated as a positive indicator of good credit, and will have positive impact on credit score.
Final Credit Score
The final credit score is a sum of the base score plus any additional points earned through model usage and consistency. The score provides an overall measure of the user's reliability and engagement with the API.
Last updated