跟讀練習: The 7 phases of AI-driven development - 通過影片學習英語口語
選擇練習模式
每種模式都會開啟全屏練習室。
104 句
如果句子過短或過長，請點選 Edit 進行調整。
1
What's up friends, I'm going to keep this short and sweet.
2
I have identified seven phases of development with AI.
3
In other words, as you're working through coding with your AI coding assistant, in my case Claude Code usually, then these are the seven phases you should be thinking about for shipping great work.
4
The way you achieve these phases is kind of up to you.
5
There are many different implementations of it, but these are the ones that I have understood to be common across lots and lots of different approaches.
6
Whether you're doing Ralph loops like I mostly am, whether you're doing GSD, whether you're using spec kit, you are probably going to be using these seven phases.
7
If you dig this stuff and you believe that engineering fundamentals are really important in the AI age, then guess what?
8
So do I.
9
And this is what I cover and elaborate on in my newsletter.
10
This is not for vibe coders.
11
We are people that are serious about AI engineering and serious about building applications that are built to last.
12
So if that sounds like you and you want to improve your skills, then this is the place.
13
But without Without further ado, let's go into the list.
14
Phase 1 we start with the idea.
15
You have some kind of idea, some reason that you are invoking this progress, something that you want the AI to do for you.
16
This might be that you have an entire app idea that you want to build.
17
Or you might just have a narrow thing that you want to complete within the codebase that you're in, like a bug fix or a feature.
18
I also count refactors as part of this too, so if you have a codebase that you need to refactor then this process will work for you too.
19
This idea can be as small and as big as you like.
20
We can expand this idea and this process can take very, very large ideas and turn them into reality.
21
Or it can be teeny, very narrow and very focused.
22
Doesn't matter.
23
Now just to give you a glimpse of the future setup here, the idea is going to be turned into a set of tickets which a kind of AI is going to complete.
24
Now that set of tickets might end up being lots
25
and lots of different kind of like AIs working at once
26
or maybe just a big list of tasks that the AI is going to complete sequentially.
27
So if this idea involves any kind of research here, any kind of like difficult explore phases as part of building the code,
28
then you may want to include a research phase now.
29
For instance, if you're doing like a Stripe integration or maybe integrating with an API that's not very common, then you might want to create an asset
30
that kind of takes all of the research about
31
that thing like based on your idea and kind of caches it
32
and puts it inside the repo or somewhere that your agent can access.
33
Essentially, every time your agent is doing work, it might need to explore the repo in a fresh context window.
34
And if that exploration is difficult, so it's in an external API or it's somewhere that's hard to access,
35
then you'll want to cache it in a research.md asset and you'll definitely want to run a research phase at this point.
36
The next step after research is to get to prototyping.
37
Now in the prototype stage we're still not really sure what we're actually building on even maybe why we're building it.
38
Prototyping is really important if you need to impose your taste on the outcome.
39
In other words, maybe you need some UI that needs to look a certain way or behave a certain
40
you're not quite sure which one to do.
41
What I tend to do is just chuck up a bunch of different ideas on a throwaway route, which is kind of like the LLM showing me all of
42
the different ways it can think of to build out the prototype.
43
I then iterate on the prototype inside a couple of sessions and say, okay, no, that one looks like the best.
44
I found that doing this early is absolutely essential
45
because then you can actually commit the prototype to your codebase
46
and then make that available to the agent when it actually goes to implement it.
47
The next step, we are in step four now, is to create a PRD.
48
Now that we understand a bit more about the external APIs that we're using in the research phase, now that we understand a bit more about the prototype and we've actually seen some code,
49
it's time to start actually properly describing the destination.
50
We should now feel confident in ourselves that we can kind of understand the end state, what we're trying to create at the end.
51
We won't know all of the implementation decisions yet, we will just kind of know the basic stuff
52
that the user is going to see and the way that it's going to behave.
53
We don't have to call this a PRD by the way, this is a PRD is a product requirements document, but really it's just some kind of document that describes the end state of where we're going.
54
Now in the process of creating this end state, we really need to hammer out the design.
55
And this means we need to prompt the agent to absolutely grill us walking down every part of our decision tree.
56
I have a writer PRD skill that is purpose designed for this, which I will link to below if you're interested.
57
But once we've created the PRD, then it's time to actually start breaking down the PRD into some kind of implementation plan.
58
For those of you who are not developers, or you've never used a Kanban board or a Jira board or anything like that,
59
a Kanban board is just a list of tickets that have blocking relationships between them.
60
We're essentially just describing the work that needs to be done.
61
So I then have a separate skill for turning my PRD into separate issues.
62
We could create a single sequential plan that turns the PRD into like actual code, but with a Kanban board you actually get to parallelize really effectively.
63
And so I can just literally go on my Kanban board, all of the tickets that aren't blocking and spin up an agent for each one and get it to resolve it.
64
But of course what I'm starting to talk about here is execution.
65
So in some kind of loop here run a coding agent to execute all of the tickets on the Kanban board.
66
Most times you won't need to parallelise this, most times a sequential agent just working through each ticket will be enough.
67
And for me this is a Ralph loop which works really really effectively with this setup.
68
And I'll drop some links below on writing about Ralph that I've done.
69
once you've done with execution and you've got a completed asset for you to actually look at,
70
then you get the agent to create a QA plan for the human to QA the completed work.
71
And what this usually results in is more tasks in the Kanban board and going through the execution loop again.
72
So you will tend to loop these last three steps quite a few times until you iterate towards a perfect product.
73
And QA here also involves a human actually going and reading the code that has been produced during the execution loop.
74
That might not always be needed, especially if you're using a kind of gray box architecture that I've talked about in previous videos.
75
But overall, these seven phases are the things I'm thinking about whenever I'm working with an AI agent.
76
We start with the idea, some kind of app or feature or refactor.
77
If we know there are external dependencies and difficult to execute explore phases, then we cache it in a research phase.
78
And by the way, this research generally only lives for the lifetime of this sprint, essentially, or the lifetime of the idea that we're imposing on the app.
79
The reason for that is that research can go out of date, or it can just rot away, essentially, and actually cause our agent to take a wrong turn where it's not needed.
80
If I need to impose my taste, then I will use a prototype here.
81
So I will really just sit with an agent, human in the loop, to hash out some ideas.
82
This is not just for design as well it can be for software architecture too
83
or let's say testing something out with an external service.
84
This is an essential step because by the time we get to the PRD it's a little bit too abstract.
85
You really need concrete feedback first.
86
Then I write the PRD which is the documentation, the spec for where we are going.
87
Next I make a kind of understanding of the journey towards the PRD by turning it into a Kanban board.
88
I generally use GitHub issues for both the PRD and the Kanban board by the way, it's just an easy thing I've found.
89
Although GitHub doesn't have yet a kind of built in way to represent blocking relationships between tickets, so you might be just better off with something like linear which does.
90
Once the Kanban board is all ready and set up then I execute it in some kind of loop, for me that's a Ralph loop.
91
You could also I suppose do execution human in the loop style where you sit and execute the tickets individually.
92
But I generally find with all of this set up, with the research, with the prototype with the Kanban board with the PRD helping it, you can totally run this execution loop AFK and the results will be really good.
93
And to make sure
94
that they're really good we then enter a QA phase where we get the agent to produce a QA plan.
95
Then a human, yes a human, yep we're here, actually walks through and QAs the completed work
96
and then produces more tickets for the Kanban board which then goes and are executed, more QA, you get the idea.
97
But what do you think about this?
98
What did I get wrong and what am I missing here?
99
I imagine these phases will grow to 8 phases and 9 phases as I get more ideas.
100
There's no explicit mention of code review here really, I suppose I could do that as part of the execution flow.
101
I suppose maybe it comes under QA, but it's definitely an essential step to producing good code.
102
Either way, you can tell that I care about good code
103
and if you do too then you should check out my newsletter.
104
But whether you sign up or don't, thanks for watching and I'll see you very soon.
同頻道
C12
New Skills! v1.2 brings /wait-what, /writing-for-agents, and fixes /grill-me
British AccentDaily ConversationWorking Adults
C14
New Skills! v1.3 brings /pr, /implement-spec, and /retro
Business EnglishWorking Adults
C14
New Skills! v1.1 brings /wayfinder, /research, /implement, /to-spec, /to-tickets
British AccentBusiness EnglishUniversity StudentsWorking Adults
C13
mattpocock/skills: A complete AI Coding workflow, end-to-end
British AccentBusiness EnglishUniversity StudentsWorking Adults
B23
I was an AI skeptic. Then I tried plan mode
British AccentBusiness EnglishUniversity StudentsWorking Adults
B23
/wayfinder: Nothing is too big to plan anymore
British AccentBusiness EnglishUniversity StudentsWorking Adults
C12
How to actually force Claude Code to use the right CLI (don't use CLAUDE.md)
British AccentBusiness EnglishUniversity StudentsWorking Adults
C13
Learn anything with the /teach skill
British AccentBusiness EnglishUniversity StudentsWorking Adults
C16
5 Claude Code skills I use every single day
British AccentBusiness EnglishUniversity StudentsWorking Adults
C14
Most devs don't understand what agents are
British AccentDaily ConversationUniversity StudentsWorking Adults
C15
Can Cursor's HARDCORE Review Skill Stop The Slop?
British AccentBusiness EnglishUniversity StudentsWorking Adults
C12
Most devs don't understand how LLM tokens work
British AccentBusiness EnglishUniversity StudentsWorking Adults
C1New Skills! /handoff, /prototype, /review and /writing-* | Skills Changelog
British AccentBusiness EnglishUniversity StudentsWorking Adults
FOR YOU
推薦影片
C18
41 句
Design Thinking 101
Business EnglishUniversity StudentsWorking Adults
C113
204 句
The 7 Skills You Need to Build AI Agents
Business EnglishUniversity StudentsWorking Adults
C11
12 句
Rapid Engineering With AI
Business EnglishUniversity StudentsWorking Adults
C12
241 句
AI Concepts Every Product Manager Should Know in 25 Minutes | Crash Course
Business EnglishUniversity StudentsWorking Adults
C12
540 句
Incremental Cooking in UE 5.7: A Dive Into the UE Cook Pipeline | Unreal Fest Chicago 2026
Business EnglishUniversity StudentsWorking Adults
C11
309 句
Claude Code: The Advanced Guide (99% of Devs Skip These Features)
Business EnglishUniversity StudentsWorking Adults
C12
129 句
How to Become a Great Software Developer — Best Advice from Top-Notch Engineers
Business EnglishInterview EnglishUniversity Students
![Understand AI in 14 minutes – with Anthropic's Chloe Lubinski [ARC 2026]](https://img.youtube.com/vi/aBUniZHgCnE/mqdefault.jpg)
C14
179 句
Understand AI in 14 minutes – with Anthropic's Chloe Lubinski [ARC 2026]
Business EnglishDaily ConversationUniversity Students
C18
24 句
Introducing Automations: always-on coding agents
Business EnglishUniversity StudentsWorking Adults
C11
180 句
Your API Can’t Handle Real-World Integrations
Business EnglishUniversity StudentsWorking Adults
為什麼要通過這個影片練習口語？
在當今的英語學習中，掌握口語能力愈加關鍵，而通過觀看和模仿影片中的講話者進行訓練，將是提高英語發音的有效方法之一。這個影片講述了與人工智慧開發相關的七個發展階段，內容豐富且具體，既涉及實際應用，又展示了口語表達的流暢性。當你模仿這種表達方式時，不僅能夠幫助你理解相關的技術術語，還能增強你的口語自信心。通過練習，你會逐漸能夠在雅思口語練習中自如地使用這些表達，提高語言的自然流暢度，同時增強邏輯思維能力。
語法與表達在語境中的應用
- 用法一：建立概念 - “我發現了七個發展階段”， e.g. 這裡的“我發現”可以作為引出主題的開場，訓練如何用第一人稱表達自己的見解。
- 用法二：條件句的使用 - “如果你相信工程的基礎很重要，那麼……”這個句子結構在日常交流中非常實用，幫助表達觀點時建立條件關係。
- 用法三：敘述過程 - “在這個階段，我們要……” 這種說法可以用來描述過程，讓聽眾理解時間的進展，適合用於學術或工作中的口語表達。
常見發音陷阱
在影片中，某些詞彙的發音可能會成為學習者的難點。例如，"應用"（application）的發音需要注意其重音在後面，把音節拉長；還有“整合”（integration），前面的音節也容易發錯。此外，音調的抑揚變化也需要掌握，以確保表達的自然和流暢。通過“shadow speech”的練習，強化這些難讀的詞彙，將有助於你的發音更為標準，提升你的英語口語能力。
總體而言，建議英語學習者通過模仿和練習影片中的發言方式，深入理解發音的細節與語法結構，通過這些實際的訓練方法，不斷提高自己的口語能力，達到更高的雅思口語練習水平。
影片中的語法
說話人最常用的結構，並附上影片中的原話：
| 結構 | 影片中的用法 |
|---|---|
| 現在完成時 have/has + 過去分詞 — 過去發生但與現在仍有關聯的事 | have identified · have understood · we've actually seen |
| 被動語態 be + 過去分詞 — 強調發生了什麼，而不是誰做的 | are built · be turned · be done |
| 定語從句 who / which + 從句 — 補充說明人或事物 | route, which is · PRD which is |
什麼是跟讀法？
跟讀法 (Shadowing) 是一種有科學依據的語言學習技巧，最初開發用於專業口譯員的培訓，並由多語言者Alexander Arguelles博士普及。這個方法簡單而強大：您在聽英語母語原聲的同時立即大聲重複——就像是一個延遲1-2秒緊跟說話者的影子。與被動聽力或語法練習不同，跟讀法強迫您的大腦和口腔肌肉同時處理並模模擬實的講話模式。研究表明它能顯著提高發音準確性，語調，節奏，連讀，聽力理解和口語流利度——使其成為雅思口語備考和真實英語交流最有效的方法之一。