▎Common Agentic AI Terms
1. Agentic AI: AI systems designed to act autonomously, perceive their environment, make decisions, and take actions to achieve specific goals with minimal human intervention.
2. Autonomous Agent: An AI that can operate independently, make choices, and execute tasks without direct human command for each step.
3. Perception: The ability of an agent to interpret sensory input from its environment (e.g., text from a user, data from a system, visual information).
4. Action: The output or execution performed by an agent based on its perception and decision-making process (e.g., writing text, calling an API, performing a calculation).
5. Goal-Oriented: Agents designed with specific objectives or tasks they are programmed to achieve.
6. Planning: The process by which an agent determines a sequence of actions to achieve its goal, often involving breaking down complex tasks into smaller sub-tasks.
7. Reasoning: The cognitive process an agent uses to process information, draw inferences, and make logical deductions to inform its actions.
8. Memory: The agent's ability to store and recall information from past perceptions, actions, or conversations to inform future decisions.
9. Tools: External functions, APIs, or services that an agent can leverage to perform actions beyond its core capabilities (e.g., a calculator, a web search API, a database query tool).
10. Tool Use: The capability of an agent to identify, select, and invoke appropriate tools to gather information or execute tasks required to achieve its goals.
11. ReAct (Reasoning and Acting): A framework that combines thought processes (reasoning) with actions, allowing agents to iteratively plan, act, and observe the environment's response.
12. Self-Reflection / Self-Correction: The agent's ability to evaluate its own past actions and reasoning, identify errors or suboptimal steps, and adjust its strategy.
13. Multi-Agent Systems: Systems composed of multiple AI agents that can interact with each other to collaborate, compete, or achieve complex, distributed goals.
14. Task Decomposition: The process of breaking down a large, complex goal into a series of smaller, manageable sub-tasks that an agent can execute sequentially or in parallel.
15. State Management: Keeping track of the current situation, context, and progress of an agent throughout its execution of a task or interaction.
16. Goal Setting: The ability of an agent to define, refine, or adapt its own goals based on context or external feedback.
17. Environment Interaction: The agent's ability to perceive changes in its operating environment and react accordingly.
18. Human-in-the-Loop (HITL): A system design where human feedback or intervention is incorporated at specific points in the agent's decision-making or execution process.
19. Prompt Chaining: A technique where the output of one prompt or agent's action becomes the input for the next, creating a workflow of sequential tasks.
20. Agent Orchestration: The management and coordination of multiple agents or multiple steps within a single agent's workflow to ensure tasks are completed effectively and efficiently.
Claim your Free $5 Bonus Here:
https://bit.ly/3wUxw09
LinkedIn profile 👇
https://www.linkedin.com/in/subarno-roy-3b2251374
Join our WhatsApp Channel 👇
https://whatsapp.com/channel/0029VbAi27y0lwghBe9mE42i
WhatsApp Community Link 👇
https://chat.whatsapp.com/HPJDqRr6G1sKQIqfdJF3pL
1️⃣ Big Data
📎 Channel Link:
[ https://t.me/bigdataofficial ]
---
2️⃣ Machine Learning
📎 Channel Link:
[ https://t.me/machinelearningofficial ]
---
3️⃣ Cloud Computing
📎 Channel Link:
[ https://t.me/cloudcomputing_official ]
---
4️⃣ Python
📎 Channel Link:
[ https://t.me/python_programming_resources ]
Share with your College Whatsapp Groups & Friends too
All the best 👍👍
