About this Agent

The Risk Scoring Agent is an AI-powered digital worker designed to streamline risk management by automatically assigning risk scores to identified risk factors. Utilizing advanced machine learning algorithms, this agent evaluates risk factors against predefined criteria to provide accurate and consistent risk assessments. By automating the risk scoring process, organizations can enhance their risk management strategies, improve decision-making, and maintain compliance with regulatory standards.

Accuracy
TBD

Speed
TBD

Input Data Set

Sample of data set required for Risk Scoring Agent:

Entity Name	Financial Stability	Operational Efficiency	Regulatory Compliance	Market Volatility	Cybersecurity Threat Level
Tech Solutions Inc.	8	7	6	4	9
Global Financial Corp.	5	6	8	3	7
Alpha Innovations	7	8	7	5	8
Secure Systems LLC	9	5	9	2	6

Risk Scoring Criteria

Risk Score Calculation

The total risk score is calculated using a weighted average approach, where each risk factor is multiplied by its respective weightage. The final score is then normalized to a scale of 0-100.

Formula

Total Risk Score = (Financial Stability 0.2) + (Operational Efficiency 0.15) +

(Regulatory Compliance 0.25) + (Market Volatility 0.1) +

(Cybersecurity Threat Level * 0.3)

Risk Factor	Description	Scoring Range	Weightage
Financial Stability	Assesses the financial health of the organization.	1 - 10	20%
Operational Efficiency	Evaluates the effectiveness of operational processes.	1 - 10	15%
Regulatory Compliance	Measures adherence to regulatory standards and guidelines.	1 - 10	25%
Market Volatility	Assesses the level of volatility in the market affecting the entity.	1 - 10	10%
Cybersecurity Threat Level	Evaluates potential risks related to cybersecurity incidents.	1 - 10	30%

Deliverable Example

Sample output delivered by the Risk Scoring Agent:

Entity Name	Financial Stability	Operational Efficiency	Regulatory Compliance	Market Volatility	Cybersecurity Threat Level	Total Risk Score
Tech Solutions Inc.	8	7	6	4	9	75
Global Financial Corp.	6	5	7	3	8	66

ZBrain credits and their usage

A credit is a unit of usage on ZBrain. Credits are consumed whenever you perform actions such as embedding documents or querying an app. Here’s how credits are utilized:

Document Embedding:

When you upload a document, it is processed and embedded to create a searchable vector representation. This step consumes credits based on the size of the document and the embedding model used.

Input Processing:

When you ask a question, the relevant context is retrieved from the embeddings and processed by the Large Language Model (LLM). This step incurs a credit cost based on the model and the number of input tokens.

Generating Output

The LLM then generates a response based on the processed input, consuming additional credits based on the number of output tokens.

The cost in credits for various models and processes is detailed below:

Models and Credit Consumption:

Model	Input Cost	Output Cost
GPT-4o	2,500 credits / 1M tokens	7,500 credits / 1M tokens
GPT-4	15,000 credits / 1M tokens	30,000 credits / 1M tokens
GPT-4-32k	30,000 credits / 1M tokens	60,000 credits / 1M tokens
GPT-3.5 Turbo	250 credits / 1M tokens	750 credits / 1M tokens

Embedding Models:

Model	Input Cost
text-embedding-3-small	20 credits / 1M tokens
text-embedding-3-large	130 credits / 1M tokens
ada v2	100 credits / 1M tokens

When you create a knowledge base or query an app, credits are deducted based on the embedding, input, and output token usage. This ensures you only pay for what you use while leveraging the full power of advanced AI models.

Risk Scoring Agent

About this Agent

Input Data Set

Risk Scoring Criteria

Risk Score Calculation

Formula

Deliverable Example

Company

Product

Contact us

Get more information

In this personalized demo, you will:

Explore ZBrain Platform

Discover Workflow Integrations

Engage in Q&A Session