While AI agents have made tech headlines around the world, the real-world examples of AI agents aren’t always obvious.
In this article, I’ll take you through the types of AI agents with examples of each. But keep in mind: even though these are divided by type, most advanced AI systems are combinations of multiple types of AI agents.
For example, self-driving cars – or autonomous vehicles – involve utility-based agents, goal-based agents, model-based reflex agents, and learning agents. It’s a complex process, so it requires a lot of moving parts.
And it's the same premise for AI agents in supply chain management. They’ll use several types of agents in order to optimize logistics, inventory management, stocking, and deliveries.
But to make it easier, let's dive into what each type of AI is designed to accomplish, with a few examples of how it already manifests in the real world.
For example, AI agents are increasingly used in enterprises for tasks that were previously impossible to automate. Flexible AI building platforms means the use cases are endless.
- E-commerce AI agents are used to place orders, track and provide updates on shipping, facilitate image-based search, send follow-ups about cart abandonment, provide product reviews from previous customers, and give personalized product suggestions to users.
- Most AI agents made on Botpress are used for sales and marketing functions, like AI lead generation or creating an AI sales funnel.
- These agents can build lead lists, send personalized communications, and qualify leads (even better than a human). They can strategize and facilitate marketing campaigns, and run analyses on competitors.
- In AI customer support, AI agents are able to take actions on behalf of users, like changing their password or managing a refund.
- They can provide product suggestion and even advanced technical support. (Our clients have curbed their support tickets by 65% with AI agents.)
- Hotels and other hospitality businesses are perfectly suited to AI assistants: they're multilingual, 24/7, and easily accessible to guests. AI agents for hotels can streamline room services, suggest nearby amenities, upsell hotel services, and help staff coordinate needs.
1. Utility-Based Agents
Unlike simpler agents that might merely react to environmental stimuli, utility-based agents evaluate their potential actions based on the expected utility. They’ll predict how useful or beneficial each option is in regards to their set goal.
Utility-based agents excel in complex decision-making environments with multiple potential outcomes – like balancing different risks in order to make investment decisions, or weigh side effects of treatment options.
The utility function of these intelligent agents is a mathematical representation of its preferences. The utility function maps to the world around it, deciding and ranking which option is the most preferable. Then a utility agent can choose the optimal action.
Since they can process large amounts of data, they’re useful in any field that involves high-stakes decision-making.
Financial Trading
Utility-based agents are well-suited for stock and cryptocurrency markets – they’re able to buy or sell based on algorithms that aim to maximize financial returns or minimize losses. This type of utility function can take into account both historical data and real-time market data.
Dynamic Pricing Systems
Ever paid extra for an Uber or Lyft in the rain? That’s a utility-based agent at work – they can adjust prices in real-time for flights, hotels, or ride-sharing, based on demand, competition, or time of booking.
Smart Grid Controllers
These types of intelligent agents are the ‘smart’ in smart grids: it’s utility-based agents that control the distribution and storage of electricity.
They optimize the use of resources based on demand forecasts and energy prices to improve efficiency and reduce costs.
Personalized Content Recommendations
You finish watching a movie and Netflix recommends 3 more just like it.
Streaming services like Netflix and Spotify use utility-based agents to suggest similar content to users. The optimized utility here is how likely you are to click on it.
2. Goal-Based Agents
Goal-based AI agents are – you guessed it – designed to achieve specific goals with artificial intelligence.
Instead of just responding to stimuli, these rational agents are capable of considering the future consequences of their actions, so they can make strategic decisions to reach their goals.
Unlike simple reflex agents, which respond directly to stimuli based on condition-action rules, goal-based agents evaluate and plan actions to meet their goals.
What makes them distinct from other types of intelligent agents is their ability to combine foresight and strategic planning to navigate towards specific outcomes.
Roomba
Robotic vacuum cleaners – like the beloved Roomba – are designed with a specific goal: clean all accessible floor space. This goal-based agent has a simple goal, and it does it well.
All their decisions made by this goal-based agent (like when to rotate) are made in pursuit of this lofty goal. The cats that sit on top of them are just a bonus.
Project Management Software
While it may also use a utility-based agent, project management software usually focuses on achieving a specific project objective.
These AI agents will often schedule tasks and allocate resources so that a team is optimized to complete a project on time. The agent evaluates the most likely course of success and actions it on behalf of a team.
Video Game AI
In strategy and role-playing games, AI characters act as goal-based agents – their objectives might range from defending a location to defeating an opponent.
These dolled-up AI agents consider a variety of strategies and resources – which attack to use, which power-up to burn – so that they can achieve their goal.
3. Model-Based Reflex Agents
When you need to adapt to information that isn’t always visible or predictable, model-based reflex agents are the tool to use.
Unlike simple reflex agents that react solely based on current perceptions, model-based reflex agents maintain an internal state that allows them to predict partially observable environments. This is an internal model of the section of the world relevant to their duties.
This model is constantly updated with incoming data from their environment, so that the AI agent can make inferences about unseen parts of the environment and anticipate future conditions.
They assess the potential outcomes of their actions before making decisions, allowing them to handle complications. This is especially useful when doing complex tasks, like driving a car in a city, or managing an automated smart home system.
Because of their ability to combine past knowledge and real-time data, model-based reflex agents can optimize their performance, no matter the task. Like a human, they can make context-aware decisions, even when the conditions are unpredictable.
Autonomous Vehicles
Even though these cars span multiple types of intelligent agents, they’re a good example of model-based reflex agents.
Complex systems like traffic and pedestrian movements are exactly the kind of challenge that model-based reflex agents are designed for.
Their internal model is used to make real-time decisions on the road, like braking when another car runs a red light, or slowing down rapidly when the car ahead does the same. Their internal system is constantly updating based on their environmental inputs: other cars, activity at crosswalks, the weather.
Modern irrigation systems
Model-based reflex agents are the powerhouse behind modern irrigation systems. Their ability to respond to unexpected environmental feedback is perfectly suited for weather and soil moisture levels.
The AI agent’s internal model represents and predicts various environmental factors, like soil moisture levels, weather conditions, and plant water requirements.
These agents continuously collect data from sensors in their fields, including real-time information on humidity, temperature, and precipitation.
By analyzing this data, the model-based reflex agent can make informed decisions about when to water, how much water to dispense, and which zones of a field require more attention. This predictive capability allows the irrigation system to optimize water usage, ensuring that plants receive exactly what they need to thrive (without wasting water).
Home automation systems
The internal model here is that of a home’s environment – these systems are continuously updated with data from sensors, and use this information to inform their decisions.
A thermostat will detect changing temperatures and configure as needed. Or a lighting system might detect darkness outdoors and adjust accordingly – since this darkness might come from nighttime, or from an unexpected thunderstorm, it requires an intelligent agent to both anticipate and react to differences.
4. Learning Agents
Learning agents stand out due to their ability to adapt and improve over time based on their experiences.
Unlike more static AI agents that operate solely on pre-programmed rules or models, a learning agent can evolve its behavior and strategies. Because of this learning element, they’re most often used in changing environments.
Fraud Detection
Fraud detection systems operate by continuously collecting data and then adjusting to recognize fraudulent patterns more effectively. Since scammers are always changing their tactics, fraud detection agents need to keep adapting, too.
Content Recommendation
Platforms like Netflix and Amazon use a system equipped with a learning agent to improve their recommendations for movies, shows, and products.
Even if your profile says you should like horror and thriller movies, if you suddenly switch to rom-coms, your recommendations will adapt. Just like us, it’s always learning.
Speech Recognition Software
Applications like Google Assistant and Siri make use of a learning agent to better understand sour garbled attempts to speak to them.
It’s thanks to learning agents that these systems get better at understanding accents and slang – so we can ask Siri things like, “Och, Siri, can ye find me the nearest chippy for some supper? I'm pure peckish!"
Adaptive Thermostats
Even smart thermostats – like Nest – learn from user behavior, like when users tend to be home or away, and their preferred temperatures.
This information might always be changing, so thermostats must be able to adapt over time – this makes them another example of a learning agent.
.webp)
5. Hierarchical Agents
Hierarchical agents are different from other types of AI agents largely due to their structured, multi-layer approach to problems.
Hierarchical agents are similar to a complex organizational structure, with different levels of decision-making. Different agents within the system will have different areas of specialization, making them more efficient at handling complex, multi-step tasks.
Hierarchical agents are one of the more complex ways to deploy AI agents, since they’re made up of multiple smaller AI agents.
In a sentence: A hierarchical agent structure is all about the structured process of decision-making across different levels of a system.
Manufacturing Robots
In advanced manufacturing systems, hierarchical agents orchestrate the production line.
High-level agents plan and allocate tasks across the system, while lower-level agents control specific machinery like robotic arms for assembly tasks.
Each can communicate with the other to ensure a smooth flow of production – that’s multi-level decision-making at work.
Air Traffic Control Systems
These systems use hierarchical agents to manage the safe and efficient flow of air traffic. Since the task is a complex one spanning multiple functions, a hierarchical agent system is necessary for proper execution.
Higher-level agents handle broader regional traffic management, while lower-level agents focus on specific tasks such as takeoffs, landings, and taxiing at individual airports.
Autonomous Warehouse Robots
Hierarchical agents are what manages inventory and package handling in warehouses enhanced with machine learning.
High-level agents optimize warehouse layout and inventory distribution, while lower-level agents operate individual robotic forklifts and sorters to execute the physical tasks of moving and organizing goods.
6. Robotic Agents
It’s exactly what we like to think of when we picture an intelligent agent: the robotic agent.
With an added performance element, robotic agents are the poster children of artificial intelligence agents. These intelligent agents operate in a physical environment, rather than just existing as software agents.
These physical embodiments of AI agents are typically equipped with sensors like cameras or touch sensors. This kind of AI agent is especially useful in tasks that are dangerous or very repetitive – it can be more efficient and cost-effective to have an artificial intelligence agent do these tasks instead.
This type of AI agent is combined with other types of artificial intelligence, so it can physically carry out utility tasks or goal tasks, sometimes within multi-agent systems or hierarchical systems.
Assembly Line Robots
There are plenty of robots on assembly lines. These AI agents perform tasks such as welding, painting, and assembling parts, all with high precision and speed.
Since they’re intelligent agents, they can optimize production time while maintaining a fixed performance standard.
Surgical Robots
Surgery is both high stakes and precise, making it ideal for AI agents.
Robotic agents like the da Vinci Surgical System assist surgeons when they perform precise and minimally invasive procedures. These AI agents don’t perform surgeries autonomously, but they extend the surgeon's capabilities.
Agricultural Robots
Robots are commonly used in the agricultural cycle, from planting seeds, to harvesting crops, to monitoring field conditions.
These AI agents help increase productivity, because it can be easier for a machine to plant 10,000 carrot seeds than get a human to do it.
Service Robots
The most famous service robot of all – that’s right, it’s WALL-E. A distant runner-up is the restaurant robots that bring your endless orders of all you-can-eat sushi directly to your table.
We use service robots everywhere: robotic vacuum cleaners, providing information to guests at hotels, and delivering goods to customers at all kinds of establishments.
7. Virtual Assistants
Virtual assistants are powered by natural language processing and artificial intelligence – and they’re perhaps the most familiar examples of AI agents to the general public.
These intelligent personal assistants understand and process human language (with natural language processing) to perform tasks, like setting reminders and managing emails.
This type of AI agent also includes a learning element: they can learn from user interactions, they become more personalized and effective over time.
Siri
One of the first mainstream virtual assistants, Siri is integrated into most Apple devices, including iPhones, iPads, Macs, and the Apple Watch.
Siri helps with a variety of tasks, like making calls, sending texts, setting reminders, providing directions, and answering general knowledge questions.
Alexa
Available on Amazon Echo devices and other Alexa-enabled products, this virtual assistant plays music, controls smart home devices, makes shopping lists, and provides news updates. And ruined the name ‘Alexa’ for humans.
Google Assistant
You know this agent program from Android phones and Google Home devices. Google Assistant excels in pulling information from the web, scheduling events, managing smart home products, and facilitating real-time translation.
Its deep integration with Google's services makes it particularly powerful for tasks involving maps, YouTube, and search functionalities.
8. Multi-Agent Systems
The beauty of multi-agent systems lies in their diversity and the richness of their interactions.
Agents within these systems are often incredibly varied, ranging from a simple software agent that filters data to complex entities that manage critical functions in smart grids or transportation networks.
Each agent operates semi-autonomously but is designed to interact with other agents, forming a dynamic ecosystem where collective behavior emerges from individual actions. For this kind of agent program, collaboration is key.
Traffic Management Systems
You can find these intelligent agents in traffic management, multiple agents represent different traffic signals, surveillance cameras, and information systems.
These AI agents collaborate to optimize traffic flow, reduce congestion, and respond to real-time conditions like accidents or road work. Each agent handles data from its locality and communicates with others to adjust traffic signals accordingly – so teamwork is a necessity.
Smart Grids for Energy Management
Smart grids also involve numerous AI agents, each controlling different aspects of electricity distribution, from generation stations to individual smart meters in homes.
These AI agents work together to efficiently balance energy supply and demand, integrate renewable energy sources, and maintain grid stability.
The coordination of a multi-agent system ensures optimal energy distribution and cost efficiency across the network.
Supply Chain and Logistics
In supply chain management, agents represent various stakeholders like suppliers, manufacturers, distributors, and retailers. These agents coordinate to optimize the supply chain process, from procurement to delivery, ensuring efficiency and reducing costs.
Autonomous Swarm Robotics
Sometimes during exploration or rescue missions, swarms of robots are deployed.
Each robotic agent operates semi-independently but coordinates with the other AI agents to cover larger areas, share sensory data, or collaboratively move objects.
This is particularly useful in challenging environments – like collapsed buildings or planetary surfaces – where teamwork among a large AI system can achieve much more than individual AI agents.
9. Simple Reflex Agents
A simple reflex agent is the runt of the litter. It has very limited intelligence and operates on a direct condition-action rule.
These rule-based agents aren’t suited for complex tasks. However, they’re perfectly adept at the specific tasks they’re designed for.
Simple reflex agents are suited for straightforward tasks in a predictable environment. This kind of agent’s actions affect the world around it, but only in specific tasks.
Thermostats
It’s 6pm in the winter? Crank that heat up. It’s noon in the summer? This simple reflex agent, with its limited intelligence, will turn on the AC.
Automatic doors
While its perceived intelligence is low, automatic doors are often examples of simple reflex agents. This AI agent senses a human in front of a door, and it opens. Beautifully simple.
Smoke detectors
This AI agent operates from your kitchen ceiling. Yep, it’s a simple reflex agent, too. It senses smoke, and it sounds an alarm.
Basic spam filters
Some agents in artificial intelligence have been helping us daily for years. The email spam filter is one of these. Basic versions don’t use natural language processing, but rather keywords or the sender’s reputation.
Build an AI agent of your own
There are a lot of types of AI agents, some far harder to build than others.
But if you’re looking to build an agentic chatbot – that can take action into your daily systems, like sending emails and booking meetings – we can help you out.
Our platform has an easy drag-and-drop interface for beginners, and endless extensibility for professional developers.
We even host an active community of 20,000+ bot-builders, if you want support throughout the process.
Start building today. It’s free.
FAQ
Are AI agents sentient?
No, AI agents are not sentient. They follow software programs that indicate their goals, although they can act autonomously in order to achieve outcomes.
What is the decision and action process for AI agents?
Different types of AI agents will observe their environments and take actions differently. Some use modeling data, and others use sensors. They have different goals based on their programmed reasoning.
What is a model-based agent?
A model-based agent is another way to refer to a model-based reflex agent, a type of AI agent that combines past data and current inputs to determine the best course of action.
.svg)
