A Gentle Introduction to AI Agents

In partnership with

Find out why 1M+ professionals read Superhuman AI daily.

In 2 years you will be working for AI

Or an AI will be working for you

Here's how you can future-proof yourself:

1. Join the Superhuman AI newsletter – read by 1M+ people at top companies

2. Master AI tools, tutorials, and news in just 3 minutes a day

3. Become 10X more productive using AI

Join 1,000,000+ pros at companies like Google, Meta, and Amazon that are using AI to get ahead.

Sign up and start learning AI

Hello everyone and welcome to my newsletter where I discuss real-world skills needed for the top data jobs. 👏

This week I’m discussing the rise of AI Agents.  👀

 Not a subscriber? Join the informed. Over 200K people read my content monthly.

 Thank you. 🎉

AI agents are systems or programs that can perceive their environment, make decisions, and take actions to achieve specific goals—often with a degree of autonomy. They show reasoning, planning, and memory and have a level of autonomy to make decisions, learn, and adapt.

An agent takes the power of generative AI a step further, because instead of just assisting you, agents can work alongside you or even on your behalf. Agents can do a range of things, from responding to questions to more complicated or multistep assignments. What sets them apart from a personal assistant is that they can be tailored to have a particular expertise.

Key Features of AI Agents

• Autonomous: They can operate without constant human instructions.

• Goal-directed: They work toward a specific objective or outcome.

• Responsive: They react to changes in their environment.

• Adaptable: Some can learn from experience and improve over time.

Their capabilities are made possible in large part by the multimodal capacity of generative AI. Multimodal simply means using or combining multiple types of input or communication.  

AI agents can process multimodal information like text, voice, video, audio, code, and more simultaneously; can converse, reason, learn, and make decisions. They can learn over time and retain that conversation with memory. Agents can work with other agents to coordinate and perform more complex workflows.

As an aside, the artificial intelligence community is in love with anthropomorphizing everything possible. Memory here simply means being able to keep longer chat conversations or other important information across sessions over time. Hell, they even have long term and short term memory. 😂In a moment you’ll learn that memory is one of the three fundamental capabilities of an agent.

AI agents use a combination of advanced algorithms, machine learning techniques, and decision-making processes. Here are the three components that intelligent agents share:

1. Architecture and algorithms. AI agents are built on complex systems that let them process a lot of data and make informed decisions. Machine learning helps these agents learn from experience and improve over time.

2. Workflow and processes. An AI agent's workflow usually starts with a specific task or goal. It then creates a plan of action, executes the necessary steps, and adapts based on feedback. This process keeps AI agents continually improving their performance.

3. Autonomous actions. AI agents can perform tasks without human intervention, making them ideal for automating repetitive processes in software development like code reviews or vulnerability detection.

AI agents come in various forms, each suited to different applications:

• Simple reflex agents. These agents act solely based on the current environment's state, making decisions through a set of predefined rules.

• Model-based reflex agents. Unlike simple reflex agents, these agents maintain an internal model of the world, allowing them to consider past actions and predict future states.

• Goal-based agents. These agents work with specific goals in mind, making decisions that move them closer to achieving these goals.

• Utility-based agents. These agents consider different outcomes and how likely they are to happen, ultimately choosing to take the actions that’ll make the most of their utility or benefit.

• Learning agents. These agents can improve their performance over time by learning from their environment and experiences.

Multiple AI agents can be deployed together to tackle complex tasks. Working together makes AI agents even more effective in software development and other industries.

Here are the four core high-level steps that Ai agents follow.

• A user gives the agent system a task. AI agents work autonomously to plan and derive how to achieve the task.

• Agent system plans, allocates, and executes work. An AI agent system breaks down a workflow into tasks and subtasks, which a manager agent assigns to other, specialized subagents. These specialized agents draw on prior experiences and learned domain expertise, coordinate with one another, and use both organizational and external data to execute assignments.

• Agent system may iteratively improve output. The agent system may request additional user input to ensure accuracy and relevance. Once the final output is delivered, the agent system may request feedback from the user.

• Agent executes action. The agent executes any necessary actions to fully complete the task.

Engage Prospects at the Perfect Moment With Our AI BDR

A poorly timed outbound message is a wasted message. Ava tracks your prospects in real-time and waits for them to trigger an intent signal before automatically sending them a personalized email or LinkedIn message.

Hire Ava who automates your entire outbound demand generation process, including:

• Intent-Driven Lead Discovery Across Dozens of Sources

• High Quality Emails with Human-Level Personalization

• Follow-Up Management

• Email Deliverability Management

Book a demo to see how Ava can 10x your outbound.

AI agents require three fundamental capabilities to effectively tackle complex tasks: planning abilities(LLM), tool utilization, and memory management. Let's dive into how these components work together to create functional AI agents.

Below is a diagram of an agent. The diagram is from a tool called N8N. It’s a low code tool for building agents. I’m using this picture because the agent has three core things coming from it. This makes it easy to understand the three core components for each model. It has the model, memory and tools.

The one great aspect of agentic workflows is the ability to switch out models and tools. In the picture below we are using ChatGPT but you can use any model you’d like. Additionally, there use cases for specific models that are beyond the scope of this introduction.

Model: The Brain of the Agent

At the core of any effective AI agent is its planning capability, powered by large language models (LLMs). Modern LLMs enable several crucial planning functions:

• Task decomposition through chain-of-thought reasoning

• Self-reflection on past actions and information

• Adaptive learning to improve future decisions

• Critical analysis of current progress

While current LLM planning capabilities aren't perfect, they're essential for task completion. Without robust planning abilities, an agent cannot effectively automate complex tasks, which defeats its primary purpose.

We learned about chain of thought in yesterday’s article on reasoning models. Chain of Thought is a technique where the model explains its reasoning in steps before giving an answer. 👀

Tool Utilization: Extending the Agent's Capabilities

The second critical component is an agent's ability to interface with external tools. A well-designed agent must not only have access to various tools but also understand when and how to use them appropriately. Common tools include:

• Code interpreters and execution environments

• Web search and scraping utilities

• Mathematical calculators

• Image generation systems

These tools enable the agent to execute its planned actions, turning abstract strategies into concrete results. The LLM's ability to understand tool selection and timing is crucial for handling complex tasks effectively.

A tool is something an AI agent uses to extend its abilities, like searching the web, doing math, running code, or accessing a database.

Memory Systems: Retaining and Utilizing Information

The third essential component is memory management, which comes in two primary forms:

1. Short-term (Working) Memory

   • Functions as a buffer for immediate context

   • Enables in-context learning

   • Sufficient for most task completions

   • Helps maintain continuity during task iteration

2. Long-term Memory

   • Implemented through external vector stores

   • Enables fast retrieval of historical information

   • Valuable for future task completion

   • Less commonly implemented but potentially crucial for future developments

Memory systems allow agents to store and retrieve information gathered from external tools, enabling iterative improvement and building upon previous knowledge.

The synergy between planning capabilities, tool utilization, and memory systems forms the foundation of effective AI agents. While each component has its current limitations, understanding these core capabilities is crucial for developing and working with AI agents. As the technology evolves, we may see new memory types and capabilities emerge, but these three pillars will likely remain fundamental to AI agent architecture.

Thanks for reading and have a great day. 🎉

SQL is the SINGLE most important skill for any data professional. I’ve curated the top questions for acing the SQL Server interview with my latest GPT release. I call the GPT SQL Server Hyper Focus on my platform called LogikBot.

Sounds more complicated than it is. It is simply a tool for preparing for the real-world SQL Server interview using ChatGPT. I’m an interview resource for Microsoft. I know what the questions are.

🥳 Here’s a code to receive $20 off the first month. Yep, that means the first month is only $30 dollars. This will be good for the first 20 subscribers. This price includes all the courses, the study guides, the GPT and the exam crams.

CODE: MEMDAY25

Below are some extras outside of the courses. Just a sample. There’s a lot more including the DP-600, the new Fabric exam cram. 

Ok. Back to SQL Server Hyper Focus. Here’s what it looks like. 

The top 5 statements above are mine. They come from a document I added to my GPT. I provided the instructions and data to ChatGPT for the model. The model is then trained on my data.

The novice might be thinking… so what? Well, I’ve just given you an interactive way to pass the SQL Server part of most SQL Server related technical interviews. If you are completely new to information technology and don’t know what a technical interview is, here you go.

For those seeking any information technology role, the technical interview is where you lose and get the job. It’s stressful and unforgiving. You either do well or forget about that job. 🤯

There are no instructions. You learn the material how you want to. Simply ask ChatGPT to create a study guide and off you go. Using ChatGPT gives you a world of flexibility.

When you are using the GPT ask it anything you need clarification on. Once you understand what an index is, you might what to see the code behind it.

If you are serious about a job working with the Microsoft Ecosystem, I guarantee this one GPT will be among the top purchases you make in your career.

Stay focused, stay hyper focused. 🎊