The difference between generic AI output and work you can ship is usually the prompt. This lesson gives a repeatable framework for Claude — role, context, task, format, and constraints.
The RCTFC framework
| Letter | Meaning | Example |
|---|---|---|
| R | Role | “You are a senior technical writer.” |
| C | Context | Audience, product, constraints |
| T | Task | One clear deliverable |
| F | Format | Bullets, table, word count |
| C | Constraints | Tone, banned phrases, citations |
Template (copy-paste)
Role: [who Claude should act as]
Context:
Task: [exact output you want]
Format: [structure, length, language]
Constraints: [tone, do/don't, sources]
Weak vs strong prompts
Weak: “Write about AI.”
Strong:
Role: B2B SaaS copywriter.
Context: We sell AI training to HR teams in Vietnam.
Task: Write a 150-word landing hero section.
Format: Headline (max 10 words), subhead (2 sentences), 3 bullets.
Constraints: No hype words (revolutionary, game-changer). CTA: Book a demo.
Advanced techniques
1. Few-shot examples
Show one good email; ask for three variants in the same style.
2. Chain prompts
Outline → draft → edit → SEO meta (four messages, not one mega-prompt).
3. Ask Claude to critique
“Score this prompt 1–10 for clarity. Suggest improvements.”
4. Negative constraints
Do not use: leverage, synergy, in today's fast-paced world.
Do not start with "Certainly!"
Prompts by use case
Research: “List 5 sources I should verify, then summarize pros/cons in a table.”
Coding: “Explain approach first, then code, then how to test.”
Analysis: “State assumptions, show reasoning, end with recommendation.”
Save prompts as Skills
Turn winning prompts into Claude Skills so your team reuses them.
Next lesson
Write naturally — Lesson 7.
Free Claude Course — Lesson 6
Related on AIFree.vn
Practical checklist
- Write down one concrete task you will solve this week (not “learn AI” in general).
- Pick one primary tool and one backup — avoid subscription sprawl.
- Run a 20-minute pilot with real inputs; save prompts that worked.
- Add a human review step before anything customer-facing or legal.
- Schedule a 30-day review: keep, replace, or cancel the tool.
Common mistakes
- Chasing every new launch instead of finishing workflows.
- Trusting outputs for numbers, dates, or citations without verification.
- Uploading confidential data to tools your employer has not approved.
- Skipping internal links between related guides on your site or team wiki.
FAQ
How long until I see results?
Most readers save time within the first week if they apply one tutorial to a real task.
Do I need to code?
No for chat and image tools; yes for fine-tuning, RAG, or custom integrations.
What should I read next?
Use the Related on AIFree.vn section at the bottom of this article for hub pages and deeper tutorials.
Key takeaway
Treat AI as a draft accelerator with clear evaluation criteria — not an infallible expert. Combine tools with domain judgment and you will outperform teams that either avoid AI or use it without guardrails.
Study plan (7 days)
| Day | Focus | Output |
|---|---|---|
| 1 | Read this article + hub page | Summary notes |
| 2 | Try one tool with a real task | Saved prompt |
| 3 | Compare alternative tool | Short comparison table |
| 4 | Share draft with peer for review | Feedback bullets |
| 5 | Measure time saved vs baseline | 1 metric |
| 6 | Document team guidelines | 1-page SOP |
| 7 | Publish or ship internally | Completed artifact |
When to escalate to an expert
Escalate to a senior engineer, lawyer, or clinician when outputs affect money, safety, compliance, or customer contracts. AI assists research; humans remain accountable.
Glossary (quick)
| Term | Meaning |
|---|---|
| LLM | Large language model for text |
| RAG | Retrieval-augmented generation with your docs |
| Fine-tuning | Training a model on specialized data |
| Token | Chunk of text the model processes |
| Hallucination | Plausible but incorrect output |
AIFree.vn — practical AI & IT education. Last optimized: June 2026.
