쉐도잉 연습: Context Engineering for AI Agents: 4 Failure Modes to Avoid - 영상으로 영어 말하기 배우기

연습 모드 선택

각 모드는 전체 화면 연습실로 열립니다.

116 문장
문장이 너무 짧거나 길면 Edit를 눌러 조정하세요.
1
context windows have grown from well a few thousand tokens to well a lot bigger like a million
2
or more and that's room for more stuff more instructions tool results docs you name it
3
so if we think about ai agents
4
and we give them access to this big old context window well
5
they should probably be getting better at long -running tasks shouldn't they?
6
I mean the more context the better job they can do.
7
Well a recent study looked at 18 frontier models
8
and it turned out that they all got less reliable as the context window got bigger.
9
Researchers have taken to giving this thing a name and that is context rot.
10
The more tokens in the window the less reliably the model uses any of them.
11
And this is the problem that context engineering is there to solve.
12
Context engineering is deciding what actually goes into this context window at each step of an agent's run.
13
Now there are many ways an agent's context can go wrong and I'm going to cover four of them.
14
The four failure modes that you can encounter when working with these big context windows.
15
And because I'm feeling nice I'll also suggest how to fix each one.
16
And the funny thing about those fixes is they involve deliberately throwing away information.
17
So how does an agent get better by holding less context?
18
Well to answer that we should first take a look at what's actually filling up these giant context windows.
19
So let's say an AI agent was given the job to migrate an aging code base over to a new database driver.
20
So I'm talking about here we are building a migration AI agent.
21
Now at the beginning of the context window the first thing most likely in here is the system prompt.
22
That's the standing instructions for how the agent operates in general.
23
Now the agent task itself
24
that will also be stored in here as well just as a prompt on its own
25
and it might not be very big it might only be a couple of lines.
26
Then many agent harnesses also pull in a bunch of project instructions.
27
Now these are things like an agents .md file explaining how this particular project is built.
28
Then after that we might have some tool definitions, a description of every tool the agent can call.
29
And from here on in the context window turns into a bit of a running log
30
so we're going to have a message history here this is every step the the agent has taken
31
and after let's say an hour of running well
32
this could get pretty big that's going to be a lot of steps
33
and then the biggest band is probably the tool results
34
that we store here which is things like file contents
35
and test output and error logs and schema dumps
36
so the job description the prompt is a few lines near the front
37
and pretty much everything else is the stuff
38
that the agent kind of piles up along the way oh
39
and buried in this as well there happens to be a note
40
this is a note the agent wrote itself it says
41
that the new driver retries failed connections automatically
42
so the old retry code can be deleted
43
so the note just basically says hey don't bother with writing any retry code why do i mention
44
that we'll come back to
45
that anyway why is a full context window a problem well
46
a model doesn't look things up in its context the way
47
a database looks up a row every token in the window
48
is competing for a finite amount of attention essentially an attention budget.
49
And to me, this is kind of the crux of it.
50
The window might hold a million tokens, but the attention spread across those tokens is finite.
51
Now, what about those failure modes?
52
Let's start with the first one.
53
Number one, that is context poisoning.
54
So I cryptically mentioned the agent wrote itself a note about the new driver retrying failed connections automatically.
55
Well it turns out that that note is completely wrong.
56
The agent shouldn't have done this.
57
It basically skim the driver's documentation, it misread it, and then it's written down a false conclusion.
58
And that's all poisoning is.
59
A mistake gets into this context window somewhere and then gets treated as fact because to the AI model,
60
its own notes, they look like the ground truth.
61
So file after file, our agent has been deleting perfectly good retry code.
62
Next, number two, that is context distraction.
63
This is where the sheer size of the history starts steering the agent.
64
Now a language model at its heart is just a pattern continuation machine
65
and when the context holds at say an hour of an agent's own past actions, that history becomes pretty much the strongest pattern around,
66
stronger than the reasoning it picked up in training.
67
So instead of asking what the job needs next the model
68
might drift into doing more of what it has already done
69
in this message history agents in this state can get stuck just kind of going over old ground
70
what about number three that is context confusion
71
and this one comes from the tools our agent here is wired into quite a lot of stuff
72
there's probably some amount of version control here
73
it might be access to a database console maybe it also is logging tickets into a ticketing system
74
and each of these tool definitions is in the window whether it actually gets used
75
or not and having more of them makes choosing the right tool a bit harder
76
and in one benchmark a model failed a task
77
when it was offered 46 tools but it then passed the very same task
78
when it was only offered 19 tools
79
that is tool sprawl work okay number four that is context clash
80
which is when the window contains information that disagrees with itself
81
so take that note with the bad information at some point our agent is going to see
82
that no retries are happening and it's going to figure out
83
that that note was wrong and it will probably make a note of
84
that into its message history as well
85
but the problem then is we now have both versions sitting in the window
86
that are presenting conflicting information so these are four different ways a context window can go bad
87
all right so what about some potential fixes well for poisoning one of the fixes is to validate.
88
Before a conclusion gets written down into this context window, check it against something real.
89
So one quick connection test and our agent would never have written this no retry code note.
90
What about distraction?
91
Well, the fix there is really too compact.
92
When the history gets really, really long, the agent can summarize it,
93
which is to say it throws the full log away and starts again from the summary,
94
a shortened version of what was in this message history in the window.
95
Now compaction is lossy.
96
A summary of a summary can start to drift like a photocopy of a photocopy.
97
So consider moving as much out of the context window as possible and put them into permanent files instead.
98
Detailed information can be retained in those files, and then it can be pulled into the context window only when it's actually needed.
99
All right, what about context confusion?
100
Well, that is a curation problem, so the fix is to curate.
101
The agent doesn't need 46 tools for database migration, so just give it the handful that the job calls for,
102
and then it can always go and fetch others
103
if it actually needs them then finally context clash well the fix there can be to prune so
104
when information gets superseded just delete the old version rather than leaving both in the window
105
we could have deleted this guy entirely or go further
106
and start a fresh window just restating the current corrected state of the job
107
and leave the poison stuff behind so
108
if a false conclusion gets saved that's poisoning so you can validate
109
if the history has taken over that's distraction so compact
110
if the agent has more tools than the task needs that's confusion
111
so curate and if the context disagrees with itself that's a clash and the fix is prune.
112
And all four fixes work by throwing something away.
113
An agent can get better at long tasks by holding less.
114
Now I'd love to know how you keep an agent's context lean.
115
Do you have your own context engineering fixes?
116
Let me know in the comments.

앱 다운로드

유창하게 말하는 데 필요한 모든 것

AI 발음 평가문장마다 점수 확인
IPA 발음 연습모든 소리 마스터
단어 학습나만의 단어장 만들기
단어 게임놀면서 외우기

같은 채널

FOR YOU

추천 영상

이 레슨의 어휘와 말하기 포인트

이 말하기 레슨은 영상 “Context Engineering for AI Agents: 4 Failure Modes to Avoid”을(를) 바탕으로 합니다. 가장 자주 반복되는 단어는 다음과 같습니다: context, agent, window, tool, note. 이 영상에는 섀도잉할 문장 100개와 단어 1451개가 있습니다. 말하는 구간의 길이는 10:08입니다. 화자는 분당 약 143단어의 일정한 속도로 말해서 섀도잉하기에 편한 속도입니다. 단어의 86%가 영어에서 가장 많이 쓰이는 3,000단어에 속합니다. 나머지는 연습 전에 미리 확인해 두세요.

이 영상의 핵심 어휘

영상에 나오는 익혀 둘 만한 단어 15개를 발음, 뜻과 함께 정리했습니다.

단어발음뜻
poison 명사/ˈpɔɪ.zən/독
token 명사/ˈtoʊkən/토큰
database 명사/ˈdeɪtəˌbeɪs/데이터베이스
delete 동사/dɪˈliːt/삭제(削除)하다
conclusion 명사/kənˈkluːʒən/종결
summary 명사/ˈsʌm.ə.ɹi/요약, 개요
confusion 명사/kənˈfjuːʒən/혼란
prompt 동사/pɹɑmpt/부추기다
log 명사/lɔɡ/통나무
migration 명사/maɪˈɡɹeɪʃ(ə)n/이주
output 명사/ˈaʊtpʊt/출력
wire 명사/ˈwaɪɚ/철사
solve 동사/sɒlv/해결하다
reliable 형용사/ɹɪˈlaɪəbl̩/믿음직스럽다
encounter 동사/ɪnˈkaʊntɚ/만나다, 부닥치다

영상에 나오는 구동사

단어뜻
throw away 동사버리다
write down 동사적다, 적어 두다

이 영상의 문법

화자가 가장 많이 쓰는 문형을 영상 속 실제 표현과 함께 정리했습니다.

문형영상 속 표현
수동태 be + 과거분사 — 누가 하는지보다 무슨 일이 일어나는지에 초점was given · be stored · is built
현재완료 have/has + 과거분사 — 과거의 일이 지금도 관련이 있을 때have grown · have taken · has taken

주의할 발음

화자는 doesn't, gonna, I'm 같은 축약형과 약화된 형태를 12번 사용합니다. 들리는 대로 짧게 발음하세요.

  • “sh”와 “zh” 소리: conclusion /kənˈkluːʒən/, confusion /kənˈfjuːʒən/, instruction /ɪnˈstɹʌkʃən/, clash /ˈklæʃ/, distraction /dɪsˈtɹæk.ʃən/
  • 긴 단어 — 강세 위치에 주의: essentially /ɪˈsɛnʃəli/, deliberately /dɪˈlɪb.(ə.)ɹət.li/, documentation /ˌdɑkjəmɛnˈteɪʃən/, continuation /kənˌtɪnjʊˈeɪʃ(ə)n/, photocopy /ˈfəʊtəˌkɒpi/

한국어 화자가 어려워하는 소리:

  • /f/ — ㅍ(/p/)으로 바꾸지 말고 윗니를 아랫입술에 대기: confusion /kənˈfjuːʒən/, drift /dɹɪft/, finite /ˈfaɪ.naɪt/, handful /ˈhæn(d)fʊl/, frontier /ˈfɹʌntɪə/
  • /v/ — ㅂ(/b/)과 구별하기: solve /sɒlv/, involve /ɪnˈvɑlv/, validate /ˈvæl.ɪ.deɪt/
  • /z/ — ㅈ이 아니라 성대를 울리는 /s/: poison /ˈpɔɪ.zən/, summarize /ˈsʌməˌɹaɪz/

이 영상으로 연습하는 방법

  1. 먼저 말하지 않고 영상을 끝까지 듣고 모르는 단어를 적어 둡니다.
  2. 보통 속도로 한 문장씩 섀도잉하고, 화자의 리듬과 맞을 때까지 반복합니다.
  3. 자신의 목소리를 녹음해 원본과 비교하고, poison, token, database 같은 단어에 특히 주의합니다.

쉐도잉이란? 영어 실력을 빠르게 키우는 과학적 방법

쉐도잉(Shadowing)은 원래 전문 통역사 훈련을 위해 개발된 언어 학습 기법으로, 다언어 학자인 Dr. Alexander Arguelles에 의해 대중화된 방법입니다. 핵심 원리는 간단하지만 매우 강력합니다: 원어민의 영어를 들으면서 1~2초의 짧은 지연으로 즉시 소리 내어 따라 말하는 것——마치 '그림자(shadow)'처럼 화자를 따라가는 것입니다. 문법 공부나 수동적인 청취와 달리, 쉐도잉은 뇌와 입 근육이 동시에 실시간으로 영어를 처리하고 재현하도록 훈련합니다. 연구에 따르면 이 방법은 발음 정확도, 억양, 리듬, 연음, 청취력, 말하기 유창성을 크게 향상시킵니다. IELTS 스피킹 준비와 자연스러운 영어 소통을 원하는 분들에게 특히 효과적입니다.

섀도잉 방법: 단계별 전체 가이드 읽기 →