The 5 Words That Change How Claude Answers You
Claude has a default voice and it is not the one you want
Ask it something real and it hedges. It softens. It opens with "great question" and closes with a summary nobody asked for. That is the default, and the default is tuned to be safe for everybody, which makes it sharp for nobody.
You change it with one word.
The honest part, first
These are prompt patterns, not official Anthropic commands. They work because of how Claude reads plain-language instructions, and that also means results shift a little between model versions. Most land exactly as described. A few need a nudge. Test the ones you plan to lean on before you build them into your daily work.
The five below, plus the format ones further down, hold up the most reliably across versions.
How they work
One word, dropped into your prompt. Claude reads it as an instruction about how to answer, not what to answer.
RAW: Explain how compound interest works.Stack two with a plus sign:
RAW + PHD: Explain how compound interest works.Some belong at the front of the prompt, some at the end. Each one below says which.
The five from the video
- RAW — front. Cuts every hedge, disclaimer, and softener. You get the answer with no cushion. Point it at something you are too close to, like whether your business idea is any good.
- BUILD — end. Skips the explaining and just builds the thing. Working code, working structure, working output. Put it after the request, not before.
- HUMAN — front or end. Rewrites the answer so it reads like a person typed it. Kills the polished AI cadence. Best on emails and captions.
- STEELMAN — front. Argues both sides at their strongest, then picks. This is the one for real decisions, like hiring someone full-time versus using a contractor.
- PHD — front or end. Answers like someone twenty years into the field instead of a summary generalist. More depth, more precision, fewer training wheels.
Making answers shorter or longer
| Code | Where | What it does |
|---|---|---|
| TIGHT | end | The absolute minimum without losing the point |
| TL;DR | front | Two-sentence answer up top, detail underneath |
| BULLETS | end | Bullet points instead of paragraphs |
| TABLE | end | Reformats into a table |
| ONE-SENTENCE | front | Has to fit in one sentence. Kills waffling |
| NO-YAP | front | Strips filler, disclaimers, and closing wrap-ups |
| DEEP | either | The opposite of TIGHT. Fully unpacks it |
| RECAP | end | Boils a long conversation down to one takeaway |
Changing the tone
| Code | What it does |
|---|---|
| CASUAL | Conversational, like texting a friend |
| FORMAL | Polished and business-appropriate |
| WITTY | Dry humor without turning into a comedy bit |
| WARM | Softer and more empathetic. Good for people you care about |
| DIRECT | No pleasantries. Instruction or answer only |
| ANTIFRAGILE | Strips "might" and "could" and commits to a claim |
| NO-EMOJIS | Blocks emojis and decorative characters |
Building and shipping
| Code | Where | What it does |
|---|---|---|
| SHIP | end | The finished product. Like BUILD but for anything, not just code |
| FIRST-DRAFT | front | Rough pass. Go fast, do not polish |
| FINAL-DRAFT | front | Publish-ready, nothing left to clean up |
| PROD | end | Production code with error handling and edge cases covered |
| MVP | front | The smallest version that tests the idea |
| REMIX | front | Five different versions of what you already have |
Thinking harder
| Code | What it does |
|---|---|
| PROS-CONS | Structured, with a weight on each side |
| RED-TEAM | Every way this fails or gets attacked |
| BLUE-TEAM | The best case for the idea |
| FIRST-PRINCIPLES | Reasons from the ground up, no inherited assumptions |
| SECOND-ORDER | The downstream effects, not the obvious one |
| INVERT | Solves for the opposite. What would guarantee failure? |
| DECIDE | Forces a real recommendation. No "it depends" |
| WEIGH | Ranks the options by impact or effort |
Checking the work
| Code | What it does |
|---|---|
| FACT-CHECK | Verifies every factual claim before writing it |
| CITE | Includes a source for each claim |
| VERIFY | Critiques its own answer before showing you |
| STEEL-DOUBT | Argues against what it just said and finds the weak link |
Formatting for where it is going
| Code | What it does |
|---|---|
| Subject line, greeting, body, sign-off | |
| DM | Three sentences, max |
| PITCH | A sixty-second spoken pitch, first person |
| SLACK | Casual, short paragraphs, minimal formatting |
| TWEET | One post under 280 characters |
| THREAD | A numbered thread of five to eight posts |
| HOOK-ONLY | Just the opening line. Nothing else |
| CTA | Adds a call to action to whatever you wrote |
| SCRIPT | A spoken video script with the beats marked |
| CAPTION | A social caption with hook, body, and CTA |
Dialing the depth
| Code | What it does |
|---|---|
| ELI5 | Explains it like you are five. Kills jargon |
| ELI-EXPERT | Assumes you know the basics and skips them |
Stacking
Two codes is where this gets good. Combinations that earn their keep:
- A real decision, fast — STEELMAN + DECIDE + TIGHT
- Code you can actually ship — PHD + PROD + NO-YAP
- Copy that sounds like a person — HUMAN + TIGHT + NO-EMOJIS
- An email that gets a reply — DIRECT + EMAIL + WARM
- An opener for a video — HOOK-ONLY + CASUAL
- Analysis with no hedging — PHD + RED-TEAM + ANTIFRAGILE
- Learning something new — ELI5 + BULLETS + NO-YAP
Three things that trip people up
- Putting the code in the wrong spot — at the front, Claude treats it as a lens for the whole answer. At the end, it lands more like an edit pass. RAW, PHD, and STEELMAN want the front. BULLETS, TABLE, and CTA want the end.
- Stacking too many — three or more and they start fighting each other for priority. Two clean codes beats four messy ones almost every time.
- Assuming they are permanent — each model version reads them a little differently. If you switch models and your favorite stack goes flat, that is why. Re-test it.
One more place to put them
These work in system prompts too. If you are building an agent or a custom skill, drop them in as defaults instead of retyping them. NO-YAP and PROD as standing defaults give you a noticeably sharper coding assistant from the first message.
Frequently asked questions
- Are these official Claude commands? — No. They are prompt patterns that work because of how Claude reads plain-language instructions. Nothing here is documented by Anthropic.
- Will they work on every model? — Mostly. Behavior drifts a little between versions, so test any stack you depend on after switching models.
- Where do I put the code? — Front for anything that shapes the thinking, like RAW or STEELMAN. End for anything that shapes the format, like BULLETS or TABLE.
- How many can I stack? — Two is the sweet spot. Past that they compete and the answer gets muddy.
- Do they work outside Claude? — Many carry over to other assistants, since they are plain instructions rather than special syntax. They are written and tested for Claude.
Start here
Pick five and use them today. The thing that changes is not answer quality so much as how much time you stop spending cleaning up the output.