Agents-internal

About this Agent

The Travel Expense Compliance Agent is a sophisticated AI digital worker designed to streamline the process of managing travel-related expenses. This intelligent agent automates the review of travel expense reports, ensuring that all claims adhere to corporate travel policies. By meticulously checking for compliance, the agent helps organizations maintain financial integrity and control over travel budgets. It flags any out-of-policy claims for further review, reducing the risk of unauthorized spending and enhancing overall efficiency in expense management.

Accuracy
TBD

Speed
TBD

Input Data Set

Sample of data set required for Travel Expense Compliance Agent:

Expense Type	Max Amount	Receipt Required	Special Rule
Flight	500.0	Yes	No unauthorized upgrades
Hotel	400.0	Yes	Exceptions with approval
Car Rental	150.0	Yes	None
Meal	50.0	Yes	None
Flight Upgrade	0.0	Yes	Only with approval

Employee Name	Date	Expense Type	Amount	Receipt Attached
John Smith	2024-09-15	Flight	350.0	Yes
Emily Johnson	2024-09-16	Hotel	450.0	No
James Brown	2024-09-17	Car Rental	100.0	Yes
Sarah Wilson	2024-09-18	Meal	50.0	Yes
Robert Taylor	2024-09-19	Flight Upgrade	200.0	No

Receipt ID	Employee Name	Expense Type	Amount
1001	John Smith	Flight	350.0
1002	Emily Johnson	Hotel	450.0
1003	James Brown	Car Rental	100.0
1004	Sarah Wilson	Meal	50.0
1005	Robert Taylor	Flight Upgrade	200.0

Deliverable Example

Sample output delivered by the Travel Expense Compliance Agent:

	Employee Name	Date	Expense Type	Amount	Status	Reason for Flagging
1	John Smith	2024-09-15	Flight	350.0	Compliant	NA
2	James Brown	2024-09-17	Car Rental	100.0	Compliant	NA
3	Sarah Wilson	2024-09-18	Meal	50.0	Compliant	NA
4	Emily Johnson	2024-09-16	Hotel	450.0	Flagged	Exceeds maximum allowed amount
5	Robert Taylor	2024-09-19	Flight Upgrade	200.0	Flagged	Unauthorized flight upgrade

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.

Travel Expense Compliance 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