Luyện nói tiếng Anh bằng Shadowing qua video: Agentic AI Frameworks Explained: Workflows, Multi-Agent, & Production
Chọn chế độ luyện tập
Mỗi chế độ mở một phòng luyện tập toàn màn hình.
124 câu
Nếu các câu quá ngắn hoặc quá dài, hãy bấm Edit để chỉnh sửa.
1
Hi, let me guess.
2
The world around you is abuzz with agentic AI systems and their massive potential.
3
So you decide to go off and build an agentic AI system.
4
You look for the best available framework out there.
5
And now, all of a sudden, you have 17 GitHub tabs open, five medium blocks bookmarked, and you are still clueless on how to proceed.
6
Yes, we've all been there.
7
LangChain, LangGraph, CrewAI, Autogen, SemanticKernel.
8
There are so many powerful frameworks out there, but which one would you pick?
9
And in order to answer that question, you first need to understand which type of agentic AI system you want to build.
10
In this video, we are going to cover five types of most common agent AI projects or systems.
11
We are going to discuss an example for each of those
12
and also list frameworks which are best suited for those types of agentic AI systems and projects.
13
First, let's get some basics out of the way.
14
What exactly is an agentic AI framework?
15
An agentic AI framework is a toolkit for building agentic AI systems.
16
Let's understand with an example.
17
Let's say you have an agent to analyze some sales data.
18
This agent goes to a database and extracts the relevant data.
19
It analyzes the data, maybe runs some calculations, and then generates a report and crafts a response that can be sent to the concerned person.
20
Now, there's a lot going on here and there's a lot of coordination that's needed.
21
And it gets even more complex when you have multiple agents working.
22
And that's exactly why you need an agentic AI framework.
23
The framework is like a building block.
24
Unlike a chatbot application where you just ask a question and get an answer,
25
the agentic AI system actually does a lot of planning, acting, and iterating.
26
It is because of this complexity involved that we need an agentic AI framework.
27
These are like building blocks that help us deploy and manage agentic AI systems.
28
Now, these have some predefined functions that help us build agentic AI systems with more ease and agility,
29
such as we have predefined architectures.
30
We might have integration and monitoring tools.
31
We might also have some task management capabilities and communication protocols.
32
Together, these features and functionalities give Agentic AI Frameworks the capability to allow us to build these systems with ease.
33
Like we discussed before, there are multiple Agentic AI Frameworks available out there, but they're not all competing to do the same type of tasks.
34
In fact, they're optimized for different types of Agentic AI systems.
35
Most Agentic AI systems and projects we are working on today fall into one of the five categories.
36
First, we have linear workflows.
37
We have autonomous AI agents or autonomous multi -agent systems.
38
We have role -based AI systems, production orchestration systems, and then we have rapid prototyping.
39
Let's dive in and understand each of these in more detail.
40
Let's start with the simplest one, linear workflows.
41
Now, this type of an agentic AI system is where things progress in a step -by -step fashion.
42
It is more predictable what's going to happen next.
43
And the steps follow a certain sequence.
44
For example, consider a customer -facing application.
45
Let's say a customer support agent.
46
The role of this agent is when a user asks a question,
47
the agent is going to take the question and search the knowledge base for relevant responses.
48
It's then going to craft a response and send it back to the user
49
and maybe take an additional action such as creating a support ticket.
50
Now, if you observe, these steps are progressing in a certain fashion,
51
in a certain sequence, and these systems are more useful when you need the flows to be more reliable.
52
There isn't a need for multiple agents to collaborate to make this happen, and that gives you more control on how things progress.
53
A good example of frameworks that are suitable for this kind of a setup include Lankchain and Lamaindex.
54
Lankchain is more suited for setups where multiple steps need to be happening in a certain sequence
55
and Lama index is highly suitable for applications that are heavy on the data retrieval and indexing.
56
For more complex setups, you could also use LangGraph, which is also by Langchain.
57
Next, we have the autonomous agentic AI systems.
58
In these systems, you typically give AI a goal and have it figure out how to accomplish it.
59
So in this system, it's very common to see multiple agents
60
These agents talk to each other to accomplish the common goal.
61
A good example of this could be an AI coding assistant.
62
You could have a planner agent that plans the solution for you.
63
You could have a coder agent that actually writes the code for you, and a reviewer agent that is reviewing the code,
64
making recommendations, and also helping with the debugging.
65
These agents are constantly talking to each other in order to give the best code possible to you.
66
So in this kind of setup, the problem is usually open -ended.
67
And that's the kind of problems this kind of setup is most helpful for.
68
So frameworks that work best for this kind of a scenario include autogen.
69
You could also use experimental setups like baby AGI.
70
And Crew AI could also be helpful
71
for designing these kinds of systems where problems are open -ended and multiple agents are collaborating together to achieve a shared goal.
72
Next, we have the role -based agentic AI systems.
73
These are kind of similar to the autonomous agentic AI systems where there are multiple agents collaborating.
74
So it is also a multi -agent setup.
75
But what makes it different is that each agent within the setup has a defined role.
76
They are still communicating with each other to accomplish that goal, but they are operating within the confines or the constraints posed by their role descriptions.
77
They are still working together, but with clear boundaries.
78
A good example of this could be a content generation agent.
79
Here you could have a researcher agent that goes on the web
80
and fetches all the material that's needed to write a piece of content.
81
There could be a writer agent that looks at all the content
82
that has been fetched and writes up an article that goes out on a social media website, let's say.
83
And then there could be an editor agent that's looking at the article
84
that has been written and makes some edits to it.
85
Now they have very clearly defined roles and they don't go into other agents' roles when they do this.
86
They have discussions, but they're strictly confined to the description that has been given to them for their particular roles.
87
A good framework that is applicable here is crew AI.
88
But you could also use autogen with some structures around it for this kind of agentic AI systems.
89
There are also some niche frameworks that are applicable to very specific tasks like for example, for software development kind of tasks, you have chat dev.
90
So these are the kind of frameworks that you would use for role -based agentic AI systems.
91
Next up, we have the production orchestration systems.
92
Like the name suggests, this is when AI moves out of the experimentation phase
93
and gets real or moves into a real world system.
94
These kind of systems require deep integration with APIs, databases, and business workflows.
95
Consider the example of an AI operations agent.
96
This agent detects alerts, searches the documentation for the alerts and then run some automation scripts
97
and send summaries in a real world scenario within an organization.
98
Good examples of frameworks that are suitable for this kind of an AI system include agent framework,
99
which essentially is a combination of semantic kernel and autogen.
100
Another good example here is line graph,
101
which works for well -structured, multi -layered applications.
102
Agent Framework is suitable both for orchestration as well as for running autonomous workflows.
103
Last but not least, you have the rapid prototyping.
104
So you always don't need a perfect architecture.
105
You just need to check if your idea would work or not.
106
These types of systems are best when you need to quickly validate ideas.
107
It helps you build quick prototypes to see if you can bring your ideas to reality.
108
These kind of systems are where you ideally have a user interface where you can drag components
109
and bring them onto a canvas to build quick workflows and test ideas.
110
Examples of tools or frameworks that are useful here include Langflow and FlowWise.
111
These tools offer you a good graphical user interface where you can bring components onto a canvas
112
and connect models and workflows and quickly test out your ideas that you can later on take into production.
113
These are very quick for rapid prototyping, and hence the name.
114
So when choosing a framework, do not ask which framework is the best.
115
Instead, ask what kind of system am I trying to build?
116
If it's predictable, use a workflow approach.
117
If it's exploratory, use the autonomous agents.
118
If it needs teamwork, use role -based systems.
119
If it's going into production, use the production orchestration frameworks.
120
And if you are testing ideas, use the rapid prototyping tools because the right framework depends on whether you're building a pipeline,
121
a team of agents, or a production AI system.
122
Which agentic AI framework is your typical go -to?
123
Feel free to comment below and don't forget to like and subscribe.
124
Thank you.
Tải Ứng Dụng
Mọi thứ bạn cần để nói trôi chảy
Chấm điểm AIChấm từng câu nói
Luyện IPAThành thạo mọi âm
Từ vựngMở rộng vốn từ
Game Từ vựngHọc qua chơi
📺 Cùng kênh
B21
Every Generation Thinks This Time Is Different: The AI Job Myth
Daily ConversationWorking Adults
C12
What is Event Driven Architecture (EDA)?
Daily ConversationUniversity StudentsWorking Adults
C12
What Is Jev? The AI Model That Doesn't Generate Text
Daily ConversationUniversity StudentsWorking Adults
C18
AI, Machine Learning, Deep Learning and Generative AI Explained
Daily ConversationUniversity StudentsWorking Adults
C11
Spec-Driven Development: AI Assisted Coding Explained
Daily ConversationUniversity StudentsWorking Adults
C15
AI Agents vs Business Rules: Which Should Make Decisions?
Daily ConversationUniversity StudentsWorking Adults
C13
AI & Education: Generative AI & the Future of Critical Thinking
Business EnglishUniversity StudentsWorking Adults
C12
EDR vs. EPP vs. NGAV
Business EnglishWorking Adults
C13
MCP vs ADK: How Modern AI Agents Connect and Work Together
University StudentsWorking Adults
C11
Cybersecurity Architecture: Data Security
Business EnglishUniversity StudentsWorking Adults
C113
The 7 Skills You Need to Build AI Agents
Business EnglishUniversity StudentsWorking Adults
C118
How Smart Organizations Will Use AI: Jevons Paradox & Workforce Impact
Business EnglishUniversity StudentsWorking Adults
C111
What are AI Agents?
Business EnglishUniversity StudentsWorking Adults
C16
Cybersecurity Architecture: Five Principles to Follow (and One to Avoid)
Business EnglishUniversity StudentsWorking Adults
C11
Zero Trust Explained in 4 mins
Business EnglishUniversity StudentsWorking Adults
✨ Video gợi ý
C11
74 câu
LangChain in 5 Minutes (Explained Clearly)
Daily ConversationUniversity StudentsWorking Adults
C120 câu
Alexandr Wang on what matters in an age of abundant intelligence
Daily ConversationUniversity StudentsWorking Adults
C11
33 câu
Enhancing AV Simulation with Generative AI - DRIVE Labs Ep. 36
Daily ConversationUniversity StudentsWorking Adults
C13
106 câu
Most devs don't understand what agents are
British AccentDaily ConversationUniversity StudentsWorking Adults
C11
105 câu
AI Governance Explained: Ethical, Transparent & Accountable AI for the Future
Daily ConversationUniversity StudentsWorking Adults
C11
346 câu
Trust the Process: How to Design Teams That Actually Work
Daily ConversationUniversity StudentsWorking Adults
C15
182 câu
How to Become an AI Product Manager in 2026 | Ex-Google, Microsoft
Daily ConversationUniversity StudentsWorking Adults
C18
55 câu
When AIs act emotional
Daily ConversationUniversity StudentsWorking Adults
C11
114 câu
Harnessing generative AI in architecture, engineering & construction
Daily ConversationUniversity StudentsWorking Adults
C11
215 câu
Creator of C# and TypeScript: "AI will NEVER Replace Coders, Here's Why" | Anders Hejlsberg
Daily ConversationUniversity StudentsWorking Adults
C11
553 câu
How AI Is Changing Strategy—and 4 Skills Leaders Need Next
Daily ConversationUniversity StudentsWorking Adults
Từ vựng và ghi chú luyện nói cho bài học này
Bài luyện nói này dựa trên video “Agentic AI Frameworks Explained: Workflows, Multi-Agent, & Production”. Những từ được nhắc lại nhiều nhất trong bài: agent, framework, agentic, example, role. Video này có 115 câu và 1583 từ để luyện shadowing. Phần lời nói dài 11:41. Người nói giữ tốc độ đều, khoảng 135 từ mỗi phút, vừa sức để nói đuổi theo. Chỉ 79% số từ nằm trong 3.000 từ tiếng Anh thông dụng nhất, nên từ vựng khá khó.
Từ vựng quan trọng trong video
15 từ đáng học trong video, kèm phiên âm và nghĩa:
| Từ | Phiên âm | Nghĩa |
|---|---|---|
| autonomous tính từ | /ɔˈtɑnəməs/ | tự trị |
| prototype danh từ | /ˈpɹəʊtətaɪp/ | nguyên mẫu |
| suitable tính từ | [ˈsjuː.tə.bɫ̩] | phù hợp, thích hợp |
| sequence danh từ | /ˈsiː.kwəns/ | dãy |
| helpful tính từ | /ˈhɛlp.fl̩/ | hay giúp đỡ |
| architecture danh từ | /ˈɑː.kɪˌtɛk.t͡ʃə/ | kiến trúc |
| component danh từ | /kəmˈpoʊ.nənt/ | bộ phận |
| database danh từ | /ˈdeɪtəˌbeɪs/ | cơ sở dữ liệu, CSDL |
| scenario danh từ | /sɪˈnɛəɹioʊ/ | trường hợp, kịch bản |
| canvas danh từ | /ˈkæn.vəs/ | can-vát |
| analyze động từ | /ˈæn.əˌlaɪz/ | phân tích |
| fetch động từ | /fɛt͡ʃ/ | tìm |
| dragon danh từ | /ˈdɹæɡən/ | rồng |
| sudden tính từ | /ˈsʌd.ən/ | thình lình, đột ngột |
| connect động từ | /kəˈnɛkt/ | nối |
Những câu đáng luyện lại
Các câu ngắn, trọn ý trong video mà bạn có thể dùng lại khi giao tiếp hằng ngày:
- Yes, we've all been there.
- First, let's get some basics out of the way.
- Let's understand with an example.
- Let's start with the simplest one, linear workflows.
- Instead ask what kind of system am I trying to build?
Ngữ pháp trong video
Những cấu trúc người nói dùng nhiều nhất, kèm đúng cụm từ trong video:
| Cấu trúc | Trong video |
|---|---|
| Thì hiện tại hoàn thành have/has + quá khứ phân từ — việc đã xảy ra nhưng còn liên quan đến hiện tại | have predefined · has been fetched · has been written |
| Câu bị động be + quá khứ phân từ — nhấn vào việc xảy ra, không phải người làm | can be sent · has been fetched · has been written |
| Mệnh đề quan hệ who / which + mệnh đề — thêm thông tin về người hoặc vật | frameworks which are · LangGraph, which is |
Phát âm cần chú ý
Người nói dùng 10 dạng rút gọn, ví dụ don't, they're, gonna. Hãy nói theo dạng ngắn đúng như bạn nghe.
- Âm “sh” và “zh”: accomplish /əˈkɑm.plɪʃ/, integration /ˌɪn.tɪˈɡɹeɪ.ʃən/, essentially /ɪˈsɛnʃəli/, recommendation /ˌɹɛkəmɛnˈdeɪʃən/, documentation /ˌdɑkjəmɛnˈteɪʃən/
- Từ dài — đặt trọng âm cho đúng: autonomous /ɔˈtɑnəməs/, collaborate /kəˈlæb.ə.ɹeɪt/, architecture /ˈɑː.kɪˌtɛk.t͡ʃə/, integration /ˌɪn.tɪˈɡɹeɪ.ʃən/, applicable /əˈplɪk.ə.bəl/
Những âm người Việt thường gặp khó:
- Cụm phụ âm cuối — đọc đủ từng âm, đừng nuốt âm cuối: sequence /ˈsiː.kwəns/, component /kəmˈpoʊ.nənt/, craft /ˈkɹæft/, connect /kəˈnɛkt/, hence /ˈhɛns/
- Âm /tʃ/, /dʒ/ và /ʒ/ — tiếng Việt không có, đừng đọc thành “ch” hay “gi”: architecture /ˈɑː.kɪˌtɛk.t͡ʃə/, fetch /fɛt͡ʃ/, generate /ˈd͡ʒɛn.ə.ɹeɪt/, researcher /ˈɹiˌsɝ.t͡ʃɚ/, niche /nɪt͡ʃ/
- Âm /æ/ — mở miệng rộng hơn âm “e”: rapid /ˈɹæp.ɪd/, collaborate /kəˈlæb.ə.ɹeɪt/, craft /ˈkɹæft/, canvas /ˈkæn.vəs/, analyze /ˈæn.əˌlaɪz/
Cách luyện với video này
- Nghe hết video một lần, chưa cần nói, và ghi lại những từ bạn chưa biết.
- Nói đuổi từng câu ở tốc độ bình thường, lặp lại mỗi câu đến khi nhịp của bạn khớp với người nói.
- Ghi âm giọng mình rồi so với bản gốc, chú ý các từ như autonomous, prototype, suitable.
Phương Pháp Shadowing Là Gì?
Shadowing là kỹ thuật học ngôn ngữ có cơ sở khoa học, ban đầu được phát triển cho chương trình đào tạo phiên dịch viên chuyên nghiệp và được phổ biến rộng rãi bởi nhà đa ngôn ngữ học Dr. Alexander Arguelles. Nguyên lý cốt lõi đơn giản nhưng cực kỳ hiệu quả: bạn nghe tiếng Anh của người bản xứ và lặp lại to ngay lập tức — như một "cái bóng" (shadow) đuổi theo người nói với độ trễ chỉ 1–2 giây. Khác với luyện ngữ pháp hay học từ vựng bị động, Shadowing buộc não bộ và cơ miệng phải đồng thời xử lý và tái tạo ngôn ngữ thực tế. Các nghiên cứu khoa học xác nhận phương pháp này cải thiện đáng kể phát âm, ngữ điệu, nhịp điệu, nối âm, kỹ năng nghe và độ lưu loát khi nói — đặc biệt hiệu quả cho người luyện IELTS Speaking và muốn giao tiếp tiếng Anh tự nhiên như người bản ngữ.