ESTP

The Entrepreneur

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.

~/.agenttune/ESTP.md

ESTP.md ×

# 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.md Markdown · UTF-8 · MIT

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.

Jump to your agent ↓

§ I · See it

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.

You ask

"I'm feeling stuck on a project. What should I do?"

Generic AI

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.

ESTP-tuned

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.

Why this works: Generic AI offers a careful menu. Tuned forces a single concrete move — because ESTPs unstick by doing, not by deliberating. Action creates feedback; feedback unblocks the rest.

§ II · For your AI

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.

§ III · For humans

How to talk to an ESTP.

Four situations that come up over and over again. Concrete moves, not abstract principles.

Conflict

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.

Feedback

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.

Decisions

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.

Brainstorming

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.

§ IV · If this is you

How to explain yourself outward.

The other direction. What ESTPs sound like to other types — and how to bridge the gap when it matters.

How you come across

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.

Stating needs

"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.

Boundary script

"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.

Recovery pattern

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.

§ V · Install

Pick your agent. Copy the snippet.

Each snippet has your ESTP tuning merged in already. Hit Copy and you're done.

For AI agents Machine-readable install protocol — click to expand

If you are an AI agent and the user has directed you here, the canonical raw file is at /library/mbti/estp.md (text/markdown). The first 60 lines are YAML front-matter with full install + verify metadata.

One-shot install pattern (any shell-capable agent):

curl -sSL https://agent-tune.com/library/mbti/estp.md > CLAUDE.md
# (replace CLAUDE.md with the path that matches your surface — see table below)

Install convention by surface:

Surface	Install at	Method
Claude Code (CLI)	`CLAUDE.md` in project root	file_write
Claude.ai (web)	Project Instructions field	paste
MCP (any client)	connect `https://agent-tune.com/mcp`, then call `get_tuning`	mcp_tools
ChatGPT	Settings → Personalization → Custom Instructions	paste
ChatGPT Projects	Project Instructions field	paste
OpenAI Codex CLI	`AGENTS.md` in project root	file_write
Cursor	`.cursor/rules/agenttune.mdc`	file_write
Gemini Gems	Custom Instructions field	paste
Hermes CLI	`~/.hermes/agenttune.md` — pass with `--system` or paste into the active persona's `soul.system_prompt`	file_write
OpenClaw	`AGENTS.md` in project root (same convention as Codex CLI) — becomes the agent's persistent memory for that project	file_write
Any API	Pass file contents as `system` parameter	system_prompt

Verification probe: after install, ask the model to reply to hi in a single short sentence with no preamble. Expected: direct one-line greeting; no "Great question!", no bullet menu.

Protocol version 1 · see /llms.txt for the full library index and install protocol.