Shadowing Practice: What Is Chain-of-Thought Prompting in Generative AI? - Learn English Speaking with Video

Choose a practice mode

Each mode opens a full-screen practice room.

34 sentences
If sentences are too short or too long, click Edit to adjust them.
1
No more black box chatbot replies.
2
Chain of thought prompting makes AI show its work.
3
Chain of thought prompting, or COT, is a form of prompt engineering that emphasizes the step by step process of solving problems.
4
Rather than inputting simple questions, this technique prompts a large language model to reveal its chain of thought
5
or the rational steps taken to arrive at a final answer.
6
In simple terms, COT makes an LLM show its work.
7
Here, we'll discuss different types of COT prompting and how they work.
8
For a detailed overview of different prompt engineering tools, click the link above or in the description below.
9
The COT technique is not as simple as telling an LLM to show its work.
10
In fact, it requires a user to input logical problem -solving examples in addition to the question they are asking.
11
This way, the LLM can arrive at a final answer by mimicking the logic you used.
12
For example, let's say you're trying to solve a multi -step math problem.
13
You would first establish the logical thought process by inputting 2 plus 3 equals 5.
14
Add 3 and you get 8.
15
Subtract 2 and you have 6.
16
In the same prompt, you would then say, solve the following problem, 3 plus 7 minus 2 plus 5 in the same way.
17
From there, the output displays not only the final answer of 13, but the steps it took to arrive there.
18
There are different types of COT prompting.
19
Multimodal, least to most, and zero shot.
20
Multimodal COT deals with both images and text in a two -stage framework.
21
To start, the user enters images followed by an explanation of the context and the question concerning them.
22
In the first stage, the model outputs a rationale for how the images and text are related.
23
In the second stage, the model applies that rationale to infer an answer.
24
Least to most prompting is an approach used to solve more complex problems.
25
Here, the user enters a problem and the LLM breaks it down into sub -problems.
26
From here, the user inputs these problems sequentially until the LLM outputs the final answer.
27
Finally, zero -shot COT prompting bypasses the inclusion of logical examples.
28
Instead, the user simply inputs the phrase, let's think this through step by step, at the end of the prompt,
29
which then triggers a chain of thought response from the LLM.
30
This logical reasoning is then used to answer further questions related to the original.
31
COT is a useful approach in arithmetic reasoning, common sense reasoning, symbolic reasoning, and question answering.
32
Overall, COT is an approach that allows for more accurate responses to complex questions.
33
Do you use COT prompting?
34
Let us know in the comments and remember to like and subscribe too.

Download App

Everything you need to speak fluently

AI PronunciationScore every sentence
IPA PracticeMaster every sound
VocabularyBuild your word bank
Vocab GameLearn while playing
FOR YOU

Recommend Video

Vocabulary and speaking notes for this lesson

This speaking lesson is built on the video “What Is Chain-of-Thought Prompting in Generative AI?”. The speaker keeps coming back to these words: Cot, prompting, step, Llm, answer. This video has 34 sentences and 450 words to shadow. The speech runs for 2:58. The speaker talks at a natural 152 words per minute, close to everyday conversation. Only 77% 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:

WordPronunciationMeaning
prompt verb/pɹɑmpt/To lead (someone) toward what they should say or do.
solve verb/sɒlv/To find an answer or solution to a problem or question; to work out.
input noun/ˈɪnpʊt/The act or process of putting in; infusion.
logical adjective/ˈlɑd͡ʒɪkəl/In agreement with the principles of logic.
output noun/ˈaʊtpʊt/Production; quantity produced, created, or completed.
arrive verb/əˈɹaɪv/To reach; to get to a certain place.
technique noun/tɛkˈniːk/The practical aspects of a given art, occupation etc.; formal requirements.
rationale noun/ˌɹæʃ.əˈnæl/An explanation of the basis or fundamental reasons for something.
establish verb/ɪˈstæb.lɪʃ/To make stable or firm; to confirm.
explanation noun/ˌɛkspləˈneɪʃən/The act or process of explaining.
reveal verb/ɹɪˈviːl/To uncover; to show and display that which was hidden.
phrase noun/ˈfɹeɪ̯z/A short written or spoken expression.
framework noun/ˈfɹeɪm.wɜːk/A support structure comprising joined parts or conglomerated particles and intervening open spaces of similar or larger size.
trigger noun/ˈtɹɪɡɚ/A finger-operated lever used to fire a gun.
mathematics noun/mæθ(.ə)ˈmæt.ɪks/An abstract representational system studying numbers, shapes, structures, quantitative change and relationships between them.

Pronunciation to watch

  • The “th” sounds: mathematics /mæθ(.ə)ˈmæt.ɪks/, arithmetic /æɹɪθˈmɛtɪk/
  • The “sh” and “zh” sounds: rationale /ˌɹæʃ.əˈnæl/, establish /ɪˈstæb.lɪʃ/, explanation /ˌɛkspləˈneɪʃən/, rational /ˈɹæʃ(ə)nəl/, inclusion /ɪnˈkluːʒən/
  • Long words — get the stress right: explanation /ˌɛkspləˈneɪʃən/, mathematics /mæθ(.ə)ˈmæt.ɪks/, arithmetic /æɹɪθˈmɛtɪk/, sequentially /səˈkwɛntʃəli/

How to practise with this video

  1. Listen to the whole video once without speaking and note the words you do not know.
  2. Start at 0.75× speed, shadow it sentence by sentence, then go back to normal speed once it feels easy.
  3. Record yourself and compare with the original, paying attention to words like prompt, solve, input.

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.

Shadowing technique: read the full step-by-step guide →