Agents-internal

About this Agent

The Late Payment Follow-up Agent is an AI digital worker designed to seamlessly manage and track overdue payments within the accounts receivable process. This intelligent agent automatically sends timely reminders to clients regarding their outstanding invoices, ensuring that collections are made promptly. By keeping a diligent eye on late payments, this AI worker helps reduce bad debt and improve cash flow, allowing finance teams to focus on more strategic tasks.

Accuracy
TBD

Speed
TBD

Input Data Set

Sample of data set required for Late Payment Follow-up Agent:

Combined Client and Invoice Data

ClientID	ClientName	Email	Phone	BillingAddress	Country	InvoiceID	InvoiceDate	DueDate	Amount	Status
101	John Smith	john.smith@outlook.com	+1-555-8750	97 Elm St	USA	INV001	2023-08-01	2023-08-31	1500	Overdue
102	Mary Johnson	mary.johnson@outlook.com	+1-555-4327	61 Oak St	USA	INV002	2023-09-05	2023-10-05	2500	Paid
103	David Brown	david.brown@outlook.co.uk	+44-207-6810	191 Maple Ave	UK	INV003	2023-09-01	2023-09-30	1000	Overdue
104	Susan White	susan.white@outlook.com	+1-555-5939	306 Pine Rd	USA	INV004	2023-09-15	2023-10-15	500	Pending

Deliverable Example

Sample output delivered by the Late Payment Follow-up Agent:

Payment Reminder - Invoice INV001

Dear John Smith,

We hope this email finds you well. This is a friendly reminder that Invoice INV001 for the amount of 1500 was due on 2023-08-31 and is currently overdue.

Please arrange payment at your earliest convenience to avoid further delays. If payment has already been made, please disregard this message.

Thank you for your prompt attention to this matter.

Best regards,

Provana Corp

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.

Late Payment Follow-up 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