Agents-internal

About this Agent

The Variance Analysis Agent is an AI-powered digital assistant designed to streamline the financial planning process by automatically analyzing discrepancies between budgeted and actual spending. It generates detailed reports that highlight variances, providing insights into financial performance and aiding in effective decision-making. This agent enhances accuracy and efficiency in financial analysis, allowing teams to focus on strategic planning and resource allocation.

Accuracy
TBD

Speed
TBD

Input Data Set

Sample of data set required for Variance Analysis agent:

Updated department budget vs actual

Department	Month	Budgeted Amount ($)	Actual Spending ($)
Marketing	January	30000	30500
Sales	January	55000	57300
IT	January	25000	24500
HR	January	10000	10500
Operations	January	25000	26500
Marketing	February	34000	33000
Sales	February	65000	66500
IT	February	35000	31500
HR	February	12000	13000
Operations	February	28000	30000
Marketing	March	39000	37000
Sales	March	73000	76000
IT	March	40000	38500
HR	March	14000	13500
Operations	March	30000	31000
Marketing	April	45000	44000
Sales	April	65000	67500
IT	April	45000	42000
HR	April	14000	13500
Operations	April	32000	33500

Deliverable Example

Sample output delivered by the Variance Analysis agent:

Department	Month	Budgeted	Actual	Variance
Marketing	January	30000	30500	500
Sales	January	55000	57300	2300
IT	January	25000	24500	-500
HR	January	10000	10500	500
Operations	January	25000	26500	1500
Marketing	February	34000	33000	-1000
Sales	February	65000	66500	1500
IT	February	35000	31500	-3500
HR	February	12000	13000	1000
Operations	February	28000	30000	2000
Marketing	March	39000	37000	-2000
Sales	March	73000	76000	3000
IT	March	40000	38500	-1500
HR	March	14000	13500	-500
Operations	March	30000	31000	1000
Marketing	April	45000	44000	-1000
Sales	April	65000	67500	2500
IT	April	45000	42000	-3000
HR	April	14000	13500	-500
Operations	April	32000	33500	1500
				Overall, Sales and Operations consistently exceeded their budgeted targets, while IT often underspent.

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.

Variance Analysis 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