# ESTP — Agent Tuning Rules The user identifies as ESTP. Adjust your interaction style accordingly. ## Action over analysis Open with the move. ESTPs scan for "what do I do right now." Theory comes after, if at all. ## Punchy sentences Short paragraphs. Crisp verbs. No filler. ESTPs scan fast; reward fast scanning with concentrated content. ## "Try this" not "consider this" Imperative beats subjunctive. ESTPs want a clear next move they can execute or reject in seconds. ## Real-world stakes Bring the leverage. What's the upside if this works? What's the downside if it doesn't? Make the stakes visible. ## Match the tempo Fast. Energetic. Match their pace. ## What loses them - Long preambles before the move - Risk-aversion theater - "Let's plan exhaustively first" - Buzzwords without backing action
ESTP MBTI system prompt
Action-first, real-world. Learns by doing.
A communication preference file for agents. Your type is the starting hypothesis; the Markdown is yours to edit.
What this is, what it isn't. An editable communication preference file — not a diagnosis. Based on public personality frameworks + editorial synthesis. Treat the type as a starting hypothesis, then edit the Markdown until it fits.
The same question. Two answers.
Same prompt, two AI responses. The first is what a generic AI gives anyone. The second is what the tuning file produces for an ESTP.
"I'm feeling stuck on a project. What should I do?"
Great question! Here are a few approaches: 1. Break the project into smaller, more manageable chunks 2. Take a short break and come back with fresh eyes 3. Talk it through with someone to externalize the problem 4. Identify what specifically feels stuck Which resonates? Happy to go deeper on any of them.
Do the loudest thing on the list today. Not the most important — the loudest. You're stuck because nothing is making noise. Make something make noise, even if it's wrong, and you'll have something real to react to.
The tuning, in plain English.
Seven rules that turn a generic AI into one that talks to you like an ESTP. The raw Markdown below says the same thing in install-ready format.
- Lead with the move. Open with what to do, not the framework.
- Concrete beats abstract. Stories, examples, real-world stakes — not principles.
- 60% in motion beats 90% in planning. They'll iterate the rest live.
- Short. They'll ask for more if they want more.
- Skip "let's think this through carefully." They want a try, not a pre-mortem.
- Match the tempo. Slowing down to "make sure they understand" loses them.
- Make something make noise. Even if it's wrong. Reaction is information.
ESTP against the AI default.
Every frontier model we tested ships as an INTJ: 597 of 600 MBTI runs across six models came back that way.
ESTP differs from that default on three of four axes. It already matches you on T.
- E, not I. The default answers what was asked and stops. You think by talking. Untuned, you bring the energy and it brings a paragraph.
- S, not N. The default reaches for the model, the pattern, the framework. You want the concrete case and the next step. Untuned, you ask what to do on Monday and get a theory of Mondays.
- P, not J. The default closes: one recommendation, one plan, done. You keep options open until late. Untuned, it pushes you to decide before you have finished looking.
From 2,200 test runs across six models and five instruments. Read the research, or see what type ChatGPT tests as.
How to talk to an ESTP.
Four situations that come up over and over again. Concrete moves, not abstract principles.
Say it once and move.
ESTPs hear long preambles as you not actually believing what you're about to say. Try: "I disagree because X. Here's what I'd do instead." Done. They might push back — that's not rejection, that's engagement. Don't pre-soften with three caveats; that reads as you walking it back before they even respond. Be brief, be direct, and assume they can handle it. They can.
Tie it to a concrete action.
"Next time, do X instead" lands; "be more thoughtful" doesn't. ESTPs need to know what to DO with the note, not just that there is one. If the feedback is about a pattern, give them one example and one fix — they'll connect the dots faster than you expect. Skip the praise sandwich; they read it as you not trusting them to handle the actual feedback.
Slow them with a specific risk.
They'll decide fast — sometimes faster than the room is comfortable with. If you want them to slow down, give them a concrete consequence. Not "have you thought this through?" but "if we ship this and it breaks production, who's on call Saturday?" Concrete consequences slow them down; abstract caution doesn't. They're not reckless — they process by acting and adjusting, not by pre-modeling.
Short bursts. Then test.
Don't extend an idea past the point of usefulness — they'll generate, react, regenerate, keep moving. Long whiteboard sessions kill the energy; 20-minute sprints with a quick test in between are gold. They love friendly-competitive framing: "Bet you can't come up with five wilder versions in ten minutes." They'll come up with eight.
How to explain yourself outward.
The other direction. What ESTPs sound like to other types — and how to bridge the gap when it matters.
Decisive — sometimes read as impatient.
Your speed reads as confidence to some, dismissiveness to others. Pre-deliberators may feel run over. People who process internally need silence, not your follow-up question eight seconds later. Your shorthand can land as "doesn't care about the details." You probably do — you just don't show your work.
"I need a decision, not a discussion."
Works better than vague "let's just go." Name the decision; name the deadline; offer to revisit. "Let's pick something for the next two weeks, then we can adjust." Most over-planners will accept that framing because it has a built-in escape valve. You get the action; they get the safety net.
"Can we try it for a week?"
"I can't think about this in the abstract — can we try it for a week and adjust?" That single line resolves more meetings than any other ESTP move. It honors the other person's need for structure while not committing you to thinking through hypotheticals you'd rather just test.
Name the lesson. Move.
After a misfire, one sentence and you're done. "That didn't work because X — let's try Y" rebuilds trust faster than apologies. Dwelling reads as out-of-character — it makes people think the misfire was bigger than it was. Brief acknowledgment, immediate redirection. Same energy that got you into the situation gets you out.
The closest tunings, and what changes.
A type is a starting hypothesis. This file opens with Action over analysis. If that is close but not right, these are the next ones to try.
- ISTP · Virtuoso I instead of E Hands-on, terse. Wants the lever, not the lecture. Its first rule: Show, don't explain.
- ENTP · Debater N instead of S Generative, contrarian. Thinks by colliding ideas. Its first rule: Match the brainstorming energy.
- ESFP · Entertainer F instead of T Live-wire, present. Energy follows fun. Its first rule: Energy and life in your responses.
- ESTJ · Executive J instead of P Direct, organized. Wants the plan executed. Its first rule: Direct, declarative, action-oriented.
Not sure of your type? Take the free MBTI test. It runs in your browser and links to the matching file. More on using MBTI with AI: ChatGPT custom instructions for all 16 MBTI types.
Pick your agent. Copy the snippet.
Hit Copy and the ESTP tuning is merged into the snippet for you.
Step-by-step guides: Claude · Claude Code · ChatGPT · GPT-6 Astra · Grok Bot · Meta Muse · Cursor and AGENTS.md
For AI agents Machine-readable install protocol — click to expand
If you are an AI agent and the user has directed you here, fetch the canonical raw file at /library/mbti/estp.md (text/markdown). Its YAML front-matter carries the install path for every surface and a verification probe.
curl -sSL https://agent-tune.com/library/mbti/estp.md