Shadowing Practice: Learn to build effective Agentic AI systems with Andrew Ng - Learn English Speaking with Video
Choose a practice mode
Each mode opens a full-screen practice room.
28 sentences
If sentences are too short or too long, click Edit to adjust them.
1
Building effective agentic AI systems is one of the most valuable skills in AI today.
2
In this course, I share best practices for doing so
3
and you come away with a systematic understanding of how to build agentic systems.
4
I come with the term agentic AI to describe a growing category of AI projects,
5
not realizing that marketers would get a hold of that term and slap us a sticker on everything in sight.
6
Even though the hype on agentic AI has grown really rapidly, the reality of agentic systems being created and deployed has grown rapidly as well.
7
Unlike a single LM call that just directly generates a response, agentic AI systems can execute multiple LM -driven steps.
8
These steps can use tools, they can reason, they can iterate over the work to complete complex tasks.
9
In this course, you learn how to build agentic workflows using raw
10
Python without hiding all the steps in some framework so that you see how each step actually works.
11
You learn to take a complex application
12
and decompose it into a sequence of tasks that you can then implement as an agentic workflow.
13
You also learn how to implement the four key design patterns for agentic workflows.
14
Having worked on many agentic systems with many teams, I found
15
that the single biggest predictor for whether the team executes well lies in its ability to drive a disciplined error analysis process.
16
That is, to put in place evaluations or evals so that given a complex agentic workflow,
17
you can efficiently hone in on what components to focus attention on improving.
18
This way, you aren't just guessing how to spend time productively.
19
You let the eval's data guide you.
20
In this course, I'll also show you how to drive this process
21
and this will put you significantly ahead of the game compared to the vast majority of teams building agentic workflows today.
22
This course is taught in a vendor -neutral way in raw python
23
and the emphasis is on teaching you the core concepts
24
that you can then implement using any of the popular agentic AI development frameworks or using mail frameworks.
25
This long form course is currently available only on the deeplearning .ai website.
26
I hope you sign up for this course and when you've completed it, you know how to build agentic AI systems
27
which is one of the most in -demand skills on the job market today
28
and that will also let you build a lot of cool applications.
Download App
Everything you need to speak fluently
AI PronunciationScore every sentence
IPA PracticeMaster every sound
VocabularyBuild your word bank
Vocab GameLearn while playing
Same Channel
![#1 Machine Learning Specialization [Course 1, Week 1, Lesson 1]](https://img.youtube.com/vi/vStJoetOxJg/mqdefault.jpg)
B21
#1 Machine Learning Specialization [Course 1, Week 1, Lesson 1]
Daily ConversationUniversity Students
C216
The Ultimate Transformer Course for Working Engineers
Working Adults
C1AI for Everyone by Andrew Ng
Business EnglishUniversity StudentsWorking Adults
C1C4W1L01 Computer Vision
Business EnglishUniversity StudentsWorking Adults
FOR YOU
Recommend Video
C11
197 sentences
How I use AI to learn engineering (anti brain rot studying)
Daily ConversationUniversity Students
C11
124 sentences
Agentic AI Frameworks Explained: Workflows, Multi-Agent, & Production
Daily ConversationUniversity StudentsWorking Adults
C11
345 sentences
Andrew Ng on Coding Agents and Deciding What to Build
Daily ConversationUniversity Students
C15
182 sentences
How to Become an AI Product Manager in 2026 | Ex-Google, Microsoft
Daily ConversationUniversity StudentsWorking Adults
C11
105 sentences
AI Governance Explained: Ethical, Transparent & Accountable AI for the Future
Daily ConversationUniversity StudentsWorking Adults
C12
272 sentences
How I'd Learn n8n if I had to Start Over in 2026
Daily ConversationUniversity StudentsWorking Adults
C11
747 sentences
MIT Introduction to Deep Learning | 6.S191
Daily ConversationUniversity Students
C12
171 sentences
Why the Arab World never united
Daily ConversationUniversity StudentsWorking Adults
C11
207 sentences
Your AI Agent Starts Every Session Like a New Hire - Killian Carlsen-Phelan, Sonar
Daily ConversationUniversity StudentsWorking Adults
C12
64 sentences
P2 什么是机器学习【2024公认最好的 | 吴恩达机器学习 | 教程 | Machine Learning Specialization(超爽中英!)】
Daily ConversationUniversity Students
C11
74 sentences
LangChain in 5 Minutes (Explained Clearly)
Daily ConversationUniversity StudentsWorking Adults
C11
63 sentences
What Is AI? | Artificial Intelligence | What is Artificial Intelligence? | AI In 5 Mins |Simplilearn
Daily ConversationUniversity Students
Vocabulary and speaking notes for this lesson
This speaking lesson is built on the video “Learn to build effective Agentic AI systems with Andrew Ng”. The speaker keeps coming back to these words: agentic, systems, workflow, build, step. This video has 28 sentences and 418 words to shadow. The speech runs for 2:28. The speaker talks at a natural 170 words per minute, close to everyday conversation. Only 78% of the words are among the 3,000 most common in English, so the vocabulary is demanding.
Key vocabulary in this video
15 words from the video worth learning, with pronunciation and meaning:
| Word | Pronunciation | Meaning |
|---|---|---|
| framework noun | /ˈfɹeɪm.wɜːk/ | A support structure comprising joined parts or conglomerated particles and intervening open spaces of similar or larger size. |
| implement verb | /ˈɪmpləmənt/ | To bring about; to put into practice; to carry out. |
| skill noun | /skɪl/ | A capacity to do something well; a technique, an ability, usually acquired or learned, as opposed to abilities that are regarded as innate. |
| rapidly adverb | /ˈɹæpɪdli/ | With speed; in a rapid manner. |
| execute verb | /ˈɛksɪˌkjuːt/ | To kill, especially as punishment for a capital crime. |
| vast adjective | /væst/ | Very large or wide (literally or figuratively). |
| compare verb | /kəmˈpɛɚ/ | To assess the similarities and differences between two or more things [“to compare X with Y”]. Having made the comparison of X with Y, one might have found it… |
| sequence noun | /ˈsiː.kwəns/ | A set of things next to each other in a set order; a series. |
| component noun | /kəmˈpoʊ.nənt/ | A smaller, self-contained part of a larger entity. Often refers to a manufactured object that is part of a larger device. |
| neutral adjective | /ˈnuː.tɹəl/ | Not taking sides in a conflict such as war; nonaligned. |
| discipline noun | /ˈdɪsəplɪn/ | A controlled behaviour; self-control. |
| generate verb | /ˈd͡ʒɛn.ə.ɹeɪt/ | To bring into being; give rise to. |
| evaluation noun | /ɪˌvæljuˈeɪʃn̩/ | An assessment, such as an annual personnel performance review used as the basis for a salary increase or bonus, or a summary of a particular situation. |
| emphasis noun | /ˈɛmfəsɪs/ | Special weight or forcefulness given to something considered important. |
| hype noun | /haɪp/ | Promotion or propaganda, especially exaggerated claims. |
Grammar in this video
The structures the speaker uses most, with the exact words from the video:
| Structure | In the video |
|---|---|
| Present perfect have/has + past participle — a past action that still matters now | has grown · you've completed |
| Passive voice be + past participle — the focus is on what happens, not who does it | being created · is taught |
Pronunciation to watch
The speaker uses 3 contractions and reduced forms, such as aren't, I'll, you've. Say them the short way, as you hear them.
- Long words — get the stress right: evaluation /ɪˌvæljuˈeɪʃn̩/, systematic /ˌsɪs.tɪˈmæt.ɪk/
How to practise with this video
- Listen to the whole video once without speaking and note the words you do not know.
- Start at 0.75× speed, shadow it sentence by sentence, then go back to normal speed once it feels easy.
- Record yourself and compare with the original, paying attention to words like framework, implement, skill.
What is the Shadowing Technique?
Shadowing is a science-backed language learning technique originally developed for professional interpreter training and popularized by polyglot Dr. Alexander Arguelles. The method is simple but powerful: you listen to native English audio and immediately repeat it out loud — like a shadow following the speaker with just a 1–2 second delay. Unlike passive listening or grammar drills, shadowing forces your brain and mouth muscles to simultaneously process and reproduce real speech patterns. Research shows it significantly improves pronunciation accuracy, intonation, rhythm, connected speech, listening comprehension, and speaking fluency — making it one of the most effective methods for IELTS Speaking preparation and real-world English communication.