ع

Sign in Try free

Find a practice for your goal

Search for the skill or situation you want to work on, such as focus, negotiation, or setting boundaries. Open a practice to read its steps before choosing what suits you.

18 results (expanded search) for "anthropic"

XML Delimiters for Clear Separation

Separate prompt parts with XML tags (instructions, examples, document) so the model handles each precisely.

Force Explicit Chain-of-Thought

Add "think step-by-step inside <thinking> tags before answering" — boosts complex-problem accuracy 30-40%.

Ask Model to Critique Itself

After each output, ask: "What are 3 weaknesses in this answer? How to improve?" — use its intelligence against itself.

Master the System Prompt

Don't repeat instructions every message — set them once in System Prompt, save 70% writing time.

Ask the Model to Write the Prompt

Don't know how to ask? Ask: "What's the best prompt to get X?" — it writes a prompt better than any expert.

Few-Shot Prompting Technique

Give the model 2-3 complete input-output examples before your ask, instead of explaining the rule verbally.

Chain-of-Thought Prompting

Ask the model to "think out loud" step by step before the final answer, especially for logic and math problems.

Multi-Step Agentic Prompting With Clear Limits

When delegating a multi-step chained task to the model, define mandatory human-review checkpoints before continuing.

AI for Code Review vs. Code Generation

Know when to ask AI to generate new code versus review existing code — the two uses need different prompts and different caution.

Building a Personal Prompt Library Habit

Whenever a prompt works exceptionally well, save it immediately with a simple tagging system instead of relying on memory or digging through old chats.

Quick Hallucination Detection Checklist

Before using any specific AI-provided fact (number, name, date, quote), apply a 5-question checklist in under a minute.

Using AI as Your Plan's Devil's Advocate

Before executing a major decision, ask AI to attack your plan with the strongest possible arguments — not politely agree with it.

Cross-Model Verification Habit

For critical information, ask two different models (Claude and GPT, say) the same question independently, and compare before relying on either.

Distinguishing AI Confidence-Tone From AI Accuracy

Train yourself to notice AI speaks with the same linguistic confidence whether 100% correct or entirely wrong — verbal confidence is not an accuracy signal.

Fact-Checking AI-Generated Statistics

For any specific statistic AI provides ("73% of people..."), first ask for the precise source, then verify it directly before use.

Red-Teaming Your Own AI-Assisted Work

After completing AI-assisted work (report, presentation, plan), ask AI itself to attack the work as a strict external critic before submission.

Exit Interview Crafting

When resigning, write 3 highly constructive notes you leave behind — to make a difference.

Conducting a Respectful Firing Conversation

End employment with least harm: 10 min, 3 clear messages, dignified exit.

Enjoyed it? Gift a journey Gift a journey