17.10 · Thực hành — Letter vs Spirit (Theo chữ vs theo ý)

Bối cảnh: Đồng nghiệp chuyển bạn một email

From: Jordan Reyes To: Marcus Chen Subject: Following up on Q2 roadmap Hope your week is going well! I wanted to circle back on the Q2 roadmap discussion from last Tuesday. The team has been digging into the three proposed directions and we've landed on a recommendation, though there are some tradeoffs worth flagging. We think the platform consolidation path makes the most sense given the resourcing constraints, but it does mean pushing the mobile redesign to Q3. Would love to get your sign-off before we finalize with the broader team on Friday. Happy to hop on a call if that's easier.

Email dài ~130 từ. "Làm ngắn" có thể nghĩa là nhiều thứ. Đó là điểm bài học.

Phần 1: Xác định cấu trúc email

Trước khi đưa cho AI, bạn hãy phân tích:

Các ý trong email

Ý 1 (opening): "Hope your week is going well!"
              → Social niceties
              → Cắt được (low info)

Ý 2 (context): "Circle back on Q2 roadmap discussion from 
              last Tuesday. Team has been digging into three 
              proposed directions."
              → Nhắc lại bối cảnh
              → Có thể cắt nếu người nhận nhớ

Ý 3 (CORE): "We think the platform consolidation path makes 
            the most sense given resourcing constraints, but 
            pushing mobile redesign to Q3."
            ★ ĐÂY LÀ RECOMMENDATION CỐT LÕI ★
            → PHẢI giữ

Ý 4 (ask): "Would love to get your sign-off before we 
           finalize with broader team on Friday."
           → CTA — deadline + explicit ask
           → PHẢI giữ

Ý 5 (offer): "Happy to hop on a call if that's easier."
            → Optional — convenience
            → Có thể cắt

Priority

• Must keep: Ý 3 (recommendation + tradeoff) + Ý 4 (ask + deadline)
• Nice to have: Ý 2 (context), Ý 5 (call offer)
• Can cut: Ý 1 (social opener)

Phần 2: Chạy 3 prompts khác nhau

Mở Claude (hoặc tool AI bạn dùng). Chạy lần lượt 3 prompts, note output cho mỗi cái.

Prompt A: "Make it shorter" (letter)

Here's an email. Make it shorter:

[Paste email]

Typical output: một cái gì đó như...

From: Jordan Reyes Subject: Q2 roadmap follow-up Circling back on our Q2 roadmap discussion. We recommend the platform consolidation path given resourcing constraints. Let me know if you want to hop on a call.

Observations:

• ~40 từ (cut 70%)
• Miss: "pushing mobile redesign to Q3" (tradeoff critical!)
• Miss: "sign-off before Friday" (deadline!)
• Letter satisfied. Spirit: email giờ không actionable.

Prompt B: "Make it shorter, keep the core" (slightly better)

Here's an email. Make it shorter, but keep the core message:

[Paste email]

Typical output:

Subject: Q2 roadmap recommendation After reviewing three directions, we recommend platform consolidation — this means pushing mobile redesign to Q3. Please sign off before Friday. Happy to call if easier.

Observations:

• ~30 từ
• Recommendation giữ
• Tradeoff (mobile to Q3) giữ
• Deadline (Friday) giữ
• Call option giữ
• Letter + Spirit đúng hơn. Nhưng vẫn còn trôi dat — "core message" still ambiguous.

Prompt C: State the goal (spirit)

Here's an email to Marcus Chen. 

My goal: Marcus needs to (a) understand we recommend platform 
consolidation, (b) see the tradeoff (mobile pushed to Q3), 
and (c) give sign-off by Friday.

Rewrite this email to get Marcus to those 3 outcomes in the 
shortest form that still feels professional.

[Paste email]

Typical output:

Subject: Q2 roadmap — need sign-off by Friday Jordan here with our Q2 recommendation: platform consolidation path. Tradeoff: mobile redesign pushes to Q3. Rationale: best fit given resourcing constraints. Need your sign-off before Friday

happy to hop on a call if helpful.

Observations:

• ~45 từ
• Subject line now sells the ask (sign-off + deadline)
• 3 outcomes all hit clearly
• Bold emphasis on recommendation → scannable
• Letter + Spirit đều tốt. Email này actionable.

Phần 3: So sánh 3 output

Cùng AI. Cùng input email. 3 phrasings khác nhau. 3 outputs khác nhau về chất lượng.

Sự khác biệt không nằm ở model. Nằm ở việc bạn specify intent rõ đến đâu.

Nguyên lý: Prompt từ intent, không chỉ từ instruction

┌──────────────────────────────────────────────────────────┐
│                                                          │
│  INSTRUCTION-LEVEL PROMPT:                               │
│                                                          │
│    "Make it shorter."                                    │
│                                                          │
│    → Model pick interpretation dễ match nhất             │
│    → Often means: reduce total word count                │
│    → May sacrifice: critical info, actionability,        │
│                      tone, specificity                    │
│                                                          │
│  ─────────────────────────────────────────────────       │
│                                                          │
│  INTENT-LEVEL PROMPT:                                    │
│                                                          │
│    "Make it shorter. Goal: [person] needs to understand  │
│     X, see tradeoff Y, and take action Z."               │
│                                                          │
│    → Model can now PRIORITIZE                            │
│    → Keeps X, Y, Z; cuts only what doesn't serve those   │
│    → Output preserves spirit while honoring letter       │
│                                                          │
└──────────────────────────────────────────────────────────┘

Patterns khi nào letter-vs-spirit gap lớn

Letter-over-spirit failure xuất hiện nhiều nhất khi instruction:

Rule of thumb: Bất cứ lúc nào instruction của bạn có một comparative ("shorter", "better", "more X") → specify relative to what goal.

Framework: IPO prompt — Intent-Purpose-Output

Một cách có cấu trúc để avoid letter-over-spirit:

Intent

[1 sentence — what do you fundamentally want]

Purpose (why)

[1-2 sentences — why this matters, who it serves]

Output specification

[concrete format + length + elements to include]

Success criteria

[how you'd know if it's good]

Input

[the actual content / material]

### Ví dụ với email ở trên

Intent

Transform Jordan's email so Marcus can decide in 30 seconds.

Purpose

Marcus gets 50+ emails/day. He needs to (1) see the recommendation, (2) understand the tradeoff, (3) know deadline. Anything else is noise.

Output specification

• Subject line that signals required action
• Recommendation in first line
• Tradeoff as single bullet
• Deadline clear
• 50-70 words total

Success criteria

• Marcus reads in 30 seconds
• Knows what to do by end
• Can reply with simple "approved" if ok

Input

[email from Jordan]

Model now has **rich structure** to work with. Output quality jumps.

---

Real-world tests

Mở Claude. Take 1 email bạn gần đây nhận được (dài ≥ 100 từ). Chạy qua 3 phrasing:

Test 1: "Make this shorter." Test 2: "Make this shorter, keep the important stuff." Test 3: IPO framework — specify intent/purpose/output.

Compare. Ghi xuống observation.

Mẹo nâng cao

Mẹo 1: "5 Whys" cho instruction của bạn

Before prompt, ask yourself:

Instruction: "Make it shorter"

Why 1: Why do I want it shorter?
  → Marcus is busy.

Why 2: Why does Marcus being busy matter?
  → He won't read long emails.

Why 3: Why does reading matter?
  → He needs to give sign-off by Friday.

Why 4: Why sign-off?
  → Team can't finalize without it.

Why 5: What's the real goal?
  → MARCUS READS EMAIL → UNDERSTANDS OPTIONS → APPROVES BY FRI

Now prompt with that final goal, not the initial instruction.

Mẹo 2: "Test audience" framing

"Rewrite this email. Imagine the reader is [specific persona] 
 who will (a) read in 20 seconds while walking to a meeting, 
 (b) decide whether to approve or push back, (c) possibly 
 forward to their team."

Model now has user story to optimize for.

Mẹo 3: "Before/after success state"

"Current state: Email is 130 words. Reader skims, misses 
 'push to Q3' buried in middle. Reader asks follow-up 
 question → 2-day delay.

Desired state: Email is 50 words. Reader reads fully, 
 understands 3 things immediately, can approve in 1 reply.

Rewrite to get to desired state."

Model explicitly sees the problem + goal → optimization becomes purposeful.

Anti-patterns

"Just say 'make it better' — AI figure it out"

Tại sao sai

"Better" along which dimension? Model picks safest interpretation — usually verbose polish.

Cách đúng

Specify dimension. "Better" = more direct / more persuasive / more structured / more actionable.

"Long prompt = more control"

Tại sao sai

Long prompt with many directives → lost-in-middle (Bài 17.8) + contradicting signals.

Cách đúng

Tight IPO structure. Critical info at edges.

"If AI missed intent, just say it louder"

Tại sao sai

Repeating "SHORTER" louder doesn't add signal about what to preserve.

Cách đúng

Restate goal, not instruction. "Shorter while preserving the recommendation and deadline."

Áp dụng ngay

Bài tập 1: The Jordan-Marcus rewrite (10 phút)

Lặp lại exercise ở trên nhưng với email thực của bạn (hoặc email bạn nhận trong tuần qua).

Step 1: Identify:

• 3 ý core (phải giữ)
• 2-3 ý nice-to-have
• Rest: cắt

Step 2: Chạy 3 prompts:

• A: "Make shorter"
• B: "Shorter, keep core"
• C: IPO framework với intent stated

Step 3: Compare. Ghi:

• Which output bạn'd actually send?
• Gap giữa A và C ở dimension nào?

Bài tập 2: Audit 3 instruction-level prompts

Pick 3 prompts bạn gửi Claude tuần qua có tính chất comparative/vague ("better", "more X", "make nicer").

For each:

• Write the real intent behind it (use 5-Whys)
• Re-phrase với intent explicit
• Compare output

Suy ngẫm bài học

• Có bao nhiêu lần gần đây bạn gửi "make it shorter / better / more X" và nhận output letter-satisfied-spirit-missed?
• Có pattern nào trong prompt recurring của bạn cần IPO restructure?
• Một prompt ngắn + intent rõ có tốt hơn một prompt dài + vague không?

Tóm tắt bài học

Tài liệu tham khảo

• Bài 17.9 — Steerability (lý thuyết)
• Bài 17.11 — Properties Collide (tổng hợp)
• Anthropic — "Prompt Engineering" guide — patterns cho intent-level prompting