Agents-internal

About this Agent

The Loan Covenant Monitoring Agent is an AI digital worker designed to ensure that organizations remain compliant with loan covenants. It continuously monitors loan agreements for any potential breaches, alerting finance teams promptly to enable timely corrective actions. By automating the oversight of loan covenants, this AI worker helps mitigate risks associated with non-compliance, ensuring financial stability and adherence to contractual obligations.

Accuracy
TBD

Speed
TBD

Input Data Set

Sample of data set required for Loan Covenant Monitoring Agent:

Loan covenants

Covenant_ID	Borrower_Name	Loan_Amount	Interest_Rate	Loan_Start_Date	Loan_End_Date	Covenant_Type	Covenant_Value	Current_Value	Compliance_Status
LC001	John Smith Holdings	500000	3.5%	2022-05-01	2027-05-01	Debt-to-Income Ratio	2.5	2.6	Non-compliant
LC002	Miller Enterprises	750000	4.0%	2021-07-01	2026-07-01	Minimum Liquidity	100000.0	120000.0	Compliant
LC003	Carter & Co	300000	3.75%	2023-01-15	2028-01-15	Fixed Charge Coverage	1.25	1.15	Non-compliant
LC004	Greenway Industries	1000000	4.25%	2020-09-01	2025-09-01	Debt-to-Equity Ratio	1.5	1.4	Compliant
LC005	Morgan Enterprises	600000	3.95%	2022-03-01	2027-03-01	Net Worth Requirement	500000.0	475000.0	Non-compliant

Deliverable Example

Sample output delivered by the Loan Covenant Monitoring Agent:

Alert_ID	Covenant_ID	Borrower_Name	Issue_Detected	Suggested_Action	Alert_Date
A001	LC001	John Smith Holdings	Debt-to-Income Ratio Breach	Review loan terms and mitigate	2024-10-14
A002	LC003	Carter & Co	Fixed Charge Coverage Breach	Reassess financial performance	2024-10-14
A003	LC005	Morgan Enterprises	Net Worth Requirement Breach	Contact borrower for action	2024-10-14

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.

Loan Covenant Monitoring Agent

About this Agent

Input Data Set

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