AI Agents - From Automation to Autonomous Operations

What are AI Agents?

To start from a very basic definition, think of an AI agent as your assistant or as a Software Agent.

When you ask your assistant to write an email, it works on it, taking it as a goal. When you ask it to write an email, it will write an email for you; it does not play music or do anything else. 

Hence, the first thing that can be said about these agents is that they are intelligent. They know what goals they are given and what actions they need to take to get that work done. 

Purpose of AI Agents

Currently, AI agents can do a wide variety of tasks, too, extremely well. Some of those tasks are: 

• Browsing Web

• Write and Execute Code

• Book a meeting 

• Make a payment,

• Analyse and Query Data, etc. 

We see new advancements in Artificial Intelligence every day, so the current limitations on an AI agent's list of things cannot do may become doable the next day. 

Every new advancement in Artificial Intelligence, particularly agent technology, moves us closer to AGI (Artificial General Intelligence). 

Growing Preference for AI Interaction

51% of consumers favor bots over human agents for immediate service, reflecting a reliance on AI for quick support. Additionally, 68% believe chatbots should match the expertise of skilled human agents, emphasizing the need for enhanced AI capabilities

Investment and Future Expectations

64% of CX leaders intend to boost investments in advanced chatbots within the year, while 58% expect their chatbots to become more sophisticated by 2024, indicating confidence in AI agents to enhance customer experience.

32 Unique Types of Agents and Why They Matter

Core Functional Capabilities

Memory Agents: Memory agents store, retrieve, and manage information to enhance learning and decision-making. They help AI systems remember past interactions, improve predictions, and optimize responses.

• Short-Term Memory Agent: Retains information briefly.
• Long-Term Memory Agent: Stores and recalls data over extended periods.
• Selective Forgetting Agent: Intentionally discards irrelevant information.

Processing and Reasoning: Processing and reasoning agents are responsible for understanding input data, drawing inferences, and making decisions.

• Narrow AI Agent: Excels in specific tasks6.
• General AI Agent: Demonstrates broad problem-solving abilities.

Perception and Input Modality: These agents interact with the world by processing various input types.

• Single Modality Agent: Processes input from one source (e.g., text only).
• Multi-Modality Agent: Integrates various input types (e.g., text, image, audio).

Action and Output Execution: Action-oriented agents perform tasks based on processed data.

• Tool Agent: Uses external tools to perform actions.
• Embodied Agent: Operates within a physical form or environment.

Structural Dimensions

Coordination and Communication: Coordination agents operate individually or in collaboration with others.

• Single Agent: Functions independently.
• Multi-Agent: Operates alongside other agents.
• Collaborative Agent: Works cooperatively with other agents.
• Competitive Agent: Operates in competition with other agents.

Planning Mechanism: Planning agents determine the best course of action.

• Internal Planning Agent: Plans actions internally.
• External Planning Agent: Relies on external systems for planning.

System Architecture: Defines how AI agents are designed and deployed.

• Homogenous Agent: Part of a uniform system architecture.
• Heterogenous Agent: Integrated into a diverse system architecture.

Scalability and Deployment: Determines how agents are implemented and expanded.

• Local Deployment Agent: Operates within a limited environment.
• Distributed System Agent: Deployed across a distributed network.

Role and Scope

Objective and Goal Orientation: Goal-driven agents are categorized based on how they interact with their environment.

• Reactive Agent: Responds to immediate stimuli.
• Proactive Agent: Initiates goal-oriented actions.

Task Specialization: AI agents may focus on specific or broad tasks.

• Task-Specific Agent: Designed for a particular task.
• General-Purpose Agent: Adaptable to various tasks.

Non-Functional Qualities

Efficiency and Performance: These agents focus on speed and accuracy.

• High-Speed Agent: Executes tasks rapidly.

• High-Accuracy Agent: Performs tasks with precision.

Ethics and Trust: Responsible AI requires fairness and transparency.

• Explainable Agent: Provides transparent reasoning for actions.

• Fairness-Oriented Agent: Minimizes bias in decision-making.

Robustness and Resilience: These agents handle failures and adapt to changes.

• Fault-Tolerant Agent: Continues operating despite errors.

• Dynamic Environmental Agent: Adapts to changing environments.

Interaction with System

Integration of External Capabilities: Agents interact with external tools and services.

• API-Driven Agent: Uses APIs to connect with external services.

• UI-Driven Agent: Interacts through user interfaces.

Environment and Context Interactions: These agents function in virtual or physical spaces.

• Virtual Agent: Operates in a simulated environment.

• Physical Agent: Interacts with the real world.

Use Cases of AI Agents

1. Personal Virtual Assistants

It is a very popular use case involving AI Agents. They can assist us in various tasks, such as reminding us of important events, planning our day, writing emails, and planning meetings.  

2. AI agents for Healthcare

AI agents in the healthcare industry can make a significant impact. They can make everything possible, from basic tasks such as helping people with their medical queries to remarkable tasks such as helping in drug discoveries. 

Many pharmaceutical companies, like Gilead Sciences and others, have already witnessed the potential of AI Agents. Whereas research used to take years, they have accelerated the whole process, making it all possible within months or even days.  

3. AI agents for Finance as Finance Analyst

Financial institutions can leverage the power of AI agents to help them detect fraud by learning transaction patterns from previous data. They can also use agents to build customer-friendly chatbots that respond faster and more accurately to users’ questions.

Additionally, autonomous financial analysis agents can analyze market trends, assess risks, and provide insights for investment decisions, enhancing overall financial strategy.

4. AI tutor and Researchers in Education and Research

Here, agents can help research by making the entire World Wide Web accessible through Natural Language prompts. This has reduced the time required to manually review research papers and made the best content accessible for any research. The workflow automation potential of these agents is transforming labour-intensive workflows in educational settings.

Autonomous Customer Agents enhance user experience by providing instant support, resolving queries efficiently, and personalizing interactions based on customer data.

Best Open Source Agents

1. AutoGPT

This is one of the first and highly capable open-source AI agents available. For a given goal, it first creates a set of sub-tasks. It then goes through each of those sub-tasks to get the work done. This process may even divide the sub-task into further sub-tasks based on the complexity of the task. 

It is the Agent dividing a complex task into sub-tasks and iterating through them to complete the work.

2. AutoGen

It is another of those remarkable releases in the field of Autonomous Agents. It allows you to build a Multi-Agent Conversational Framework inside your application for enhanced accuracy and better inference from the LLMs. 

For example, you must build an agent to query your structured database. Using AutoGen, you can pass on the initial query results through various other agents in the middle before finally producing the output to the user. Each agent has a defined task and a role assigned to it. If, at any step, an agent finds the responses unsatisfactory, it sends them back to the previous agent for re-evaluation. 

Levels of AI Agents 

1. Tools (Perception + Action)

2. Reasoning & Decision making

3. Memory + Reflection

4. Generalization & Autonomous Learning

5. Personality (Emotion + Character) and Collaborative Behavior (Multi-agents)

Figure 1 -  Level of Personal LLM Agents

Figure 2 -  Level of AI Agents

Reference:- https://arxiv.org/pdf/2405.06643

Challenges in Adoption for AI Agents

1. Data Dependent

The backbone of any AI agent is the large language model (LLM). Hence, the accuracy of the response and intelligent behaviour of the overall agents directly depend on the richness of the data on which the LLM was trained.

The Agents may become highly biased if the LLM in the backend is not trained on the right data set. 

2. Limited Understanding of Context - Context Management and Intelligence 

Regarding the currently available open-source AI agents like AutoGPT and others, they have a short-term memory, making it hard for them to hold on to the context in a longer conversation. 

3. Security Concerns

AI Security and LLM software supply chain security are critical aspects for AI Quality and AI assurance and governance aspects. 

4.  Trustworthy AI Aspects 

AI agents lack common sense and ethical perspectives; they can easily be made to work toward goals with malicious intent. Considerations regarding accountability, transparency, ethics, responsibility and bias in decision-making are critical in regulated industries, especially healthcare, finance, transportation.