Autonomous planning is the ability of an artificial intelligence system to work out, on its own, a sequence of actions that will achieve a goal, and to revise that sequence as conditions change or as steps succeed or fail. Planning is one of the oldest topics in artificial intelligence and is central to robots, game
Autonomous Planning Read More »
Autonomous planning is the ability of an artificial intelligence system to work out, on its own, a sequence of actions that will achieve a goal, and to revise that sequence as conditions change or as steps succeed or fail.
Computer-use AI describes artificial intelligence systems that operate a computer in the way a person does. Instead of calling a purpose-built programming interface, the system looks at the screen, decides what to do and then controls the cursor and keyboard to click buttons, type text and move between applications. Because it relies on the same
Computer-Use AI Read More »
Computer-use AI refers to AI systems that operate a computer much as a person does, by viewing the screen and controlling the mouse and keyboard to complete tasks.
Conversational AI is a set of artificial intelligence technologies that let computers understand, process and respond to human language in dialogue, by text or speech, so that people can interact with software through natural conversation. It includes chatbots, voice assistants, customer-service agents and the AI assistants built on large language models. The field brings together
Conversational AI Read More »
Conversational AI is a set of artificial intelligence technologies that let computers understand, process and respond to human language in dialogue, by text or speech, so that people can interact with software through natural conversation.
Function calling is a feature of language model interfaces in which the model, given descriptions of available functions, returns the name of a function and a set of arguments in a structured format, which the application can then run to obtain data or perform an action. A developer might describe a function called get_order_status that
Function Calling Read More »
Function calling is a feature of language model interfaces in which the model, given descriptions of available functions, returns the name of a function and a set of arguments in a structured format, which the application can then run to obtain data or perform an action.
Human-in-the-loop AI (often shortened to HITL) is a design approach in which people take part in the operation of an automated system by reviewing its outputs, correcting its mistakes, approving its actions or supplying the data it learns from. Instead of treating a model as a black box that runs on its own, a human-in-the-loop
Human-in-the-Loop AI Read More »
Human-in-the-loop AI is a design approach in which people review, correct or approve the decisions of an automated system at defined points in its operation.
Memory in AI agents is the set of mechanisms that let an agent keep, retrieve and use information across steps and across sessions, including the current context, summaries, stored facts, past experiences and learned skills. A language model on its own has no persistent memory: each request starts fresh with only the text supplied. An
Memory in AI Agents Read More »
Memory in AI agents is the set of mechanisms that let an agent keep, retrieve and use information across steps and across sessions, including the current context, summaries, stored facts, past experiences and learned skills.
The Model Context Protocol (MCP) is an open standard that defines how AI applications connect to external tools, data sources and services. It was introduced by the AI company Anthropic in November 2024 [1]. Rather than writing a separate custom integration for every combination of application and data source, developers implement the protocol once on
Model Context Protocol Read More »
The Model Context Protocol (MCP) is an open standard that lets AI applications connect to external tools, data sources and services through a common interface.
A multi-agent system is a collection of interacting agents, each able to sense and act, that cooperate, coordinate or compete to solve problems that are difficult for a single agent to handle alone. The agents may be robots, programs, or language model based assistants, and they may share a goal, pursue separate goals or both.
Multi-Agent System Read More »
A multi-agent system is a collection of interacting agents, each able to sense and act, that cooperate, coordinate or compete to solve problems that are difficult for a single agent to handle alone.
Task decomposition is the process of breaking a complex goal into smaller, more manageable subtasks that can be solved in order or in parallel. It is an everyday strategy in engineering, project management and education, and a core technique in artificial intelligence. A request such as prepare a market report becomes a list of narrower
Task Decomposition Read More »
Task decomposition is the process of breaking a complex goal into smaller, more manageable subtasks that can be solved in order or in parallel, a technique used in problem solving, project management and artificial intelligence systems such as language model agents.
Tool calling is the ability of a language model to request that an external function or service be run, by producing a structured call with a name and arguments, so that it can fetch information or take actions beyond generating text. A model on its own cannot check today’s weather, query a company database or
Tool Calling Read More »
Tool calling is the ability of a language model to request that an external function or service be run, by producing a structured call with a name and arguments, so that it can fetch information or take actions beyond generating text.