Agents-internal

About this Agent

The Automated Resolution Suggestion Agent is an AI-driven tool designed to enhance the efficiency of IT Support teams. By analyzing help desk tickets, this digital agent provides AI-generated resolution suggestions for common issues, enabling support agents to resolve problems more swiftly. This innovative solution reduces response times, improves customer satisfaction, and optimizes the workflow of IT support departments.

Accuracy
TBD

Speed
TBD

Input Data Set

Sample of data set required for Automated Resolution Suggestion Agent:

Help desk tickets

Ticket ID	Issue Description	Category
1	Unable to connect to the internet.	Network Issue
2	Forgot password and can't access the account.	Account Issue
3	Printer is not printing even though it is connected.	Hardware Issue
4	Software update failed, causing performance issues.	Software Issue
5	Email not syncing on mobile device.	Mobile Issue

Deliverable Example

Sample output delivered by the Automated Resolution Suggestion Agent:

Ticket ID	Suggested Resolution	Confidence Score
1	Restart the router and check the network settings.	0.92
2	Reset the password using the account recovery option.	0.88
3	Check the printer's connection and reinstall the printer driver.	0.85
4	Reinstall the latest software update or roll back to the previous version.	0.9
5	Ensure that email account settings are correct and update the app.	0.87

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.

Automated Resolution Suggestion 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