# Build a Multi Agent Network (Automation)

A Multi-agent network involves multiple autonomous agents working together to achieve a common goal. Each agent in the network is designed to perform specific tasks, communicate with other agents, and make decisions based on real-time data. In the context of enterprises, an AI-powered multi-agent network can integrate various tools and processes, streamlining operations, enhancing decision-making, and ultimately improving client service.

The ReAct (Reasoning and Acting) template is a type of Artificial Intelligence template designed to enhance the decision-making and problem-solving capabilities of multi-agent systems. It combines reasoning (thought processes to understand and interpret information) with acting (taking actions based on reasoning outcomes). This integration allows ReACT agents to handle complex tasks that require both cognitive and operational skills.

Purple Fabric enables agentic workflows with multi-agent systems. Each expert agent in an agentic system can be powered by the LLM best suited to that agent from a quality, speed, and cost perspective.

Users must have the Gen AI User policy to create a Multi-Agent Network in Purple Fabric.

This guide will walk you through the steps to build a multi-agent network using Automation Agents in Purple Fabric.

Create an Automation Agent
Select a prompt template
Select a model and set model configuration
Provide the system instruction, action and examples
Run the model and view results
Publish the Agent

# Step 1: Create an Automation Agent

Head to the Expert Agent Studio module and click Build
In the pop up window that appears, Select AI Agent
Enter the name and description of the agent.
In Type, choose Automation Agent and click Create, the creation page appears

# Step 2: Select a prompt template

On the Agent creation page that appears, choose the ReAct Prompt template.

# Step 3: Select a model and set model configurations

Select a model
6. Select a model from the available List, considering model size, capability, and performance. Refer to the table to choose the appropriate model based on your requirements.

LLM Model	Model Input – As per Platform configured	Model Output	Input Context Window (Tokens)	Output Generation Size (Tokens)	Capability and Suitable For
Azure OpenAI GPT 3.5 Turbo 4K	Supports Text	Text	4096	4096	Ideal for applications requiring efficient chat responses, basic code generation, and traditional text completion tasks. Low latency and cost-effective.
Azure OpenAI GPT 3.5 Turbo 16K	Supports Text	Text	16384	4096	Ideal for applications requiring efficient chat responses, code generation, and traditional text completion tasks.Allows for longer conversations or documents in input
Azure OpenAI GPT – 4o	Supports Text (Jenitha Philominraj iAI - Doesn’t it support images on the platform?)	Text	128,000	16,384	GPT-4o demonstrates strong performance on text-based tasks like knowledge-based Q&A, text summarization, and language generation in over 50 languages. Also, useful in complex problem-solving scenarios, advanced reasoning, and generating deCotailed outputs. Recommended for complex ReAct agents
Azure OpenAI GPT – 4o mini	Supports Text	Text	128,000	16,384	A model similar to GPT-4o but with lower cost. Lower latency and slightly less performant compared to GPT-4o. Recommended for cost-sensitive ReAct agents
Bedrock Claud3 Haiku 200k	Supports Text + Image	Text	200,000	4096	The Anthropic Claude 3 Haiku model is a fast and compact version of the Claude 3 family of large language models. Claude 3 Haiku demonstrates strong multimodal capabilities, adeptly processing diverse types of data including text in multiple languages and various visual formats. Its expanded language support and sophisticated vision analysis skills enhance its overall versatility and problem-solving abilities across a wide range of applications.
Bedrock Claude 3 Sonnet 200k	Supports Text + Image	Text	200,000	4096	Comparatively more performant than Haiku, Claude 3 Sonnet combines robust language processing capabilities with advanced visual analysis features. Its strengths in multilingual understanding, reasoning, coding proficiency, and image interpretation make it a versatile tool for various applications across industries Recommended for ReAct agents involving multi-lingual and summary generation

Set Model Configuration
7. Click and then set the following tuning parameters to optimize the model’s performance. For more information, see Advance Configuration.

# Step 4: Provide system instructions, actions and examples

Provide System Instruction
A system instruction refers to a command or directive provided to the model to modify its behavior or output in a specific way. For example, a system instruction might instruct the model to classify data or extract data in a specific format etc.

8. Enter the following System instructions in the Perspective field by crafting a prompt that guides the agent with the automation task.

Add Actions
9. Click Add in the Actions section. The Actions window appears, use the search bar to find the required agents/tools
10. Provide the detailed description against each added Actions
Note: Providing the detailed description helps the LLM model to understand the context better against the actions
11. Use enable options to activate the Actions
12. Click (ellipsis icon) and select Delete if you wish to remove the Agent/tool.

Add Parameters
13. In the Parameter section, click Add
14. Enter the following information
Name: Enter the Name of the input parameter
Type: Choose File as the data type
Description: Enter the Description for each of the input parameters. The description of the parameters ensures accurate interpretation and execution of tasks by the GenAI Asset. Be as specific as possible
15. Click the settings icon against the input parameter to access settings and add input field settings
16. Choose the required file formats (PDF, JPEG, JPG) from the drop-down menu
17. Click Save to proceed

Define Output Schema
18. In the Output section, click Add to define the output schema for the Asset.
19. Enter the Variable Name, Type and Description for each of the output variables. Supported types include Text, number, Boolean, DateTime, Signature and Table.

Provide Examples
Examples help the content creation task at hand to enhance the agent’s understanding and response accuracy. These examples help the agent learn and improve over time.

20. In the Examples section, click Add
21. In the Examples section,update the following information:

Question: Initial query raised
Thought: Considerations or analysis related to the question
Action: Steps planned or taken in response to the question
Action Input: Inputs or resources needed to carry out the action
Observation: Monitoring or assessment of the action’s effectiveness
Thought: Further reflections or insights based on the observation
Final Answer: Conclusive response or resolution to the initial question.

# Step 5: Run the model and view results

22. In the Debug and Prompt section, provide the user input/query
23. Click Run to get the output in the required format
24. Review the generated output
25. Click Reference if you wish to view the reference of the output
26. Select the respective field information to view its reference
Note: If you are not satisfied with the results then, try modifying the System Instructions and the description of the output variables. You can also try changing to a different model

View Trace
27. If you wish to view the traces of the prompt and the result, click View trace
In the Trance window that appears, review the trace.

# Step 6: Publish the Agent

28. Click Publish if the desired accuracy and performance for extracting the data has been achieved
29. In the Agent Details page that appears, write a description and upload an image for a visual representation
30. Click Publish and then the status of the Agent changes to Published. This agent can be accessed in Expert Agent Studio

Note: Once the Asset is published, you can download the API and its documentation. The API can be consumed independently or used within a specific Use case. If you wish to consume this Agent via API, see Consume an Agent via API

You can also consume this automation Agent in the Monitor module. For more information, see Consume an Agent via Create Transaction