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.
51 results (expanded search) for "stanford-hai"
Digital & AI
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.
Psychological
Physiological Sigh
Two nasal inhales, then long mouth exhale — fastest research-backed nerve calmer.
Psychological
Cognitive Reappraisal
Instead of suppressing emotion, reinterpret the situation generating it.
Psychological
Morning Sun 10 Min
Morning sun in eyes (not direct) 10 min — sets biological clock.
Professional
Personal SWOT
Apply SWOT framework to your current career in 30 minutes.
Professional
Career Pivot Risk Map
Before pivoting to new field, map 5 risks and 3 cheap experiments before full leap.
Professional
Tiny Habit Stacking
Don't target "meditate 30 min" — target "one breath after coffee".
Social
FORD Topics for First Conversations
Use Family-Occupation-Recreation-Dreams as four safe entry doors for any new conversation.
Parenting
Habit Stacking for Kids
Anchor a new habit to an existing one ("after brushing teeth, read one page") — BJ Fogg formula.
Parenting
Cultivating Growth Mindset
Praise your child's effort and strategy, not his intelligence or talent — Carol Dweck's classic.
Parenting
Math Curiosity, Not Math Anxiety
Swap "you're bad at math" with "what's happening here?" — Boaler proves the math brain is built, not born.
Digital & AI
Free sample · no sign-in
CRTF Prompt Structure: Context-Role-Task-Format
Write a prompt that gives the AI model precise context, role, task, and expected format.
Digital & AI
Expert Persona Assignment
Assign the model a specific background and expertise so its answer matches a real expert level.
Digital & AI
Few-Shot Examples Before Asking
Show the model 2-5 examples of the desired output style so it mirrors the pattern with high precision.
Digital & AI
Chain-of-Thought: "Think Step by Step"
Ask the model to decompose the problem and show its reasoning before answering, raising accuracy on complex tasks.
Digital & AI
Plan Before Execute: Outline Then Run
Ask the model to write a numbered plan first and wait for your approval before executing.
Digital & AI
Explicit Negative Constraints
State explicitly what you do not want in the output (words, styles, assumptions) to cut later editing.
Digital & AI
Structured JSON Output
Request output as JSON with a defined schema to enable automated processing without manual parsing.
Digital & AI
Self-Critique: Review Your Own Answer
After the model answers, ask it to critique its own answer and improve it before final delivery.
Digital & AI
Reframe With "Explain Like I am 5"
Ask the model to explain a complex idea to a 5-year-old, then raise the level gradually.
Digital & AI
Detecting Model Hallucinations
Learn 4 signals that reveal the model invented info instead of citing documented fact.
Digital & AI
The Two Independent Sources Rule
Do not use AI-sourced info before verifying it in two independent external sources.
Digital & AI
Knowledge Cutoff Awareness
The model does not know what happened after its training cutoff. Know each model's cutoff.
Digital & AI
Understanding RAG: Why the Model Sometimes Cites
RAG (Retrieval-Augmented Generation) fetches real docs for the model before answering. Know the difference.
Digital & AI
AI Email Drafting
Use an LLM to draft an email in 30 seconds, then edit by hand for personal tone.
Digital & AI
Auto-Summarize Meeting Transcripts
Convert a meeting transcript (60+ min) into decisions and action items in 2 minutes.
Digital & AI
AI Brainstorming 10 Titles
Don't pick the first title that comes to mind. Generate 10 with varied angles, then choose the best.
Digital & AI
Socratic AI Tutor
Ask the model to question you instead of answering, surfacing and deepening your understanding.
Digital & AI
AI Use Disclosure
When an LLM helps you with content you publish or send, disclose it clearly.
Digital & AI
Single-Task Protocol
At any moment, one tab, one window, one task — multitasking is a neural myth.
Digital & AI
Zero Red Badges
Disable all red count badges on app icons — they are engineered to trigger OCD reflex.
Digital & AI
Force Explicit Chain-of-Thought
Add "think step-by-step inside <thinking> tags before answering" — boosts complex-problem accuracy 30-40%.
Digital & AI
Diverse Few-Shot (Not Similar)
In few-shot, deliberate variety (positive/negative/edge case) matters more than count.
Digital & AI
Expert-Student Dialogue for Knowledge Extraction
Have the model play expert + student who asks "dumb" questions — extracts tacit knowledge.
Digital & AI
Explicit Constraints Beat Guidance
"Max 80 words, don't use 'innovative', start with imperative" beats "make it short and clear".
Digital & AI
Iterative Refinement, Not Restart
Instead of rewriting the prompt, say "this part good. this part fix to X". 4 rounds = perfect output.
Digital & AI
Ask Model to Critique Itself
After each output, ask: "What are 3 weaknesses in this answer? How to improve?" — use its intelligence against itself.
Digital & AI
Master the System Prompt
Don't repeat instructions every message — set them once in System Prompt, save 70% writing time.
Digital & AI
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.
Digital & AI
Hallucination Check: 3 Questions Before Accepting
Before accepting any AI answer, ask: source? dates correct? names real?
Digital & AI
Cross-Check from 3 Independent Sources
Every AI claim: search 3 independent sources. If absent from any, treat as hallucinated.
Digital & AI
Lateral Reading, Not Vertical
Don't read a strange site top-to-bottom. Open 5 tabs searching "about" the site, then decide trust.
Digital & AI
AI as "Draft Zero" Writer
Use AI for a bad-fast initial draft, then YOU rewrite completely. Blank page is the killer.
Digital & AI
AI Editing Pass
After YOU write, ask AI for 3 improvements only. Don't let it "rephrase".
Digital & AI
Preserving Voice with AI
Identify 5 phrases/words that are "you". Ensure 2+ appear in any AI-assisted text.
Digital & AI
Plagiarism Boundaries with AI
"AI text didn't copy anyone" is myth. Ensure you don't publish someone's idea/sentence unattributed.
Digital & AI
Citation Hygiene with AI
Every AI claim needs a live source. Never cite a source you haven't read.
Digital & AI
Few-Shot Prompting Technique
Give the model 2-3 complete input-output examples before your ask, instead of explaining the rule verbally.
Digital & AI
Chain-of-Thought Prompting
Ask the model to "think out loud" step by step before the final answer, especially for logic and math problems.
Digital & AI
Testing 5 Thumbnails/Covers Before Publishing
Just as you brainstorm 10 titles, generate 5 different thumbnail/cover concepts, and pick via a small sample, not instinct alone.
Digital & AI
AI-Assisted Spaced Retrieval
After a Socratic learning session, ask AI to generate retrieval questions at increasing intervals (1 day, 3 days, a week) instead of relying on random memory.