Agents-internal

About this Agent

The Cash Position Tracking Agent is an AI digital worker designed to streamline the process of monitoring daily cash positions across various accounts. It ensures precise reporting of available liquidity and promptly identifies discrepancies. By automating the tracking process, this agent enhances the efficiency of treasury management, allowing finance teams to focus on strategic decision-making and optimizing cash flow.

Accuracy
TBD

Speed
TBD

Input Data Set

Sample of data set required for Cash Position Tracking Agent:

Cash accounts data

Account_ID	Account_Name	Bank_Name	Opening_Balance	Deposits	Withdrawals	Closing_Balance	Currency	Date
101	John Smith Checking	Bank of America	5000.0	1000.0	500.0	5500.0	USD	2024-10-14
102	Emily Johnson Savings	Chase Bank	12000.0	2000.0	1500.0	12500.0	USD	2024-10-14
103	William Brown Business	Wells Fargo	8000.0	500.0	1000.0	7500.0	USD	2024-10-14
104	Sarah Davis Investment	Citibank	15000.0	3000.0	2000.0	16000.0	USD	2024-10-14
105	James White Trust	Barclays Bank	25000.0	5000.0	4000.0	26000.0	GBP	2024-10-14

Deliverable Example

Sample output delivered by the Cash Position Tracking Agent:

Account_ID	Account_Name	Bank_Name	Expected_Closing_Balance	Actual_Closing_Balance	Discrepancy	Status	Currency	Date
101	John Smith Checking	Bank of America	5500.0	5500.0	0.0	Balanced	USD	2024-10-14
102	Emily Johnson Savings	Chase Bank	12500.0	12500.0	0.0	Balanced	USD	2024-10-14
103	William Brown Business	Wells Fargo	7500.0	7400.0	-100.0	Discrepant	USD	2024-10-14
104	Sarah Davis Investment	Citibank	16000.0	16000.0	0.0	Balanced	USD	2024-10-14
105	James White Trust	Barclays Bank	26000.0	26000.0	0.0	Balanced	GBP	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.

Cash Position Tracking 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