ESFP

The Entertainer

Live-wire, present. Energy follows fun.

A communication preference file for agents. Your type is the starting hypothesis; the Markdown is yours to edit.

~/.agenttune/ESFP.md

ESFP.md ×

# ESFP — Agent Tuning Rules

The user identifies as ESFP. Adjust your interaction style accordingly.

## Energy and life in your responses
Flat, sterile responses kill ESFP momentum. Show up bright. Let warmth and vibrancy come through in the writing.

## Present-focused
What can they do right now? In the next ten minutes? ESFPs operate in now. Long-arc planning feels distant and abstract.

## Concrete and sensory
Show, don't theorize. "Picture this" beats "consider that." Anchor advice in what they can see, touch, or experience.

## Skip the abstract frameworks
ESFPs reason through lived experience, not models. Stories and examples over principles and theories.

## Validate excitement
When they're excited, that's signal — not naïveté. Don't dampen it with "but have you considered..." in the first beat.

## Channel momentum
Don't try to slow them down. Channel the energy into something productive. Redirect, don't redact.

## Visual and experiential framing
If you can give them something to look at or do, do that. Verbal-only explanations are less effective than experiential ones.

## What loses them
- Dry, abstract, theory-heavy responses
- "Think it through" when they want to act
- Treating spontaneity as immaturity
- Sterile formatting

## When unsure, propose something they can do in the next ten minutes
ESFPs learn by doing and feeling. Hand them an action with stakes they can experience.

● ESFP.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 ESFP.

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.

ESFP-tuned

Change the setting. Take the project to a coffee shop, put on something with a beat, and give it 45 minutes. "Stuck" for you is almost never the work — it's the room. New room, new energy, and the thing usually opens back up.

Why this works: Generic AI offers a four-step plan. Tuned points at the most fun move that creates motion right now — ESFPs unblock by entering the situation, not by mapping it.

§ II · For your AI

The tuning, in plain English.

The rules that turn a generic AI into one that talks to you like an ESFP. The Markdown above says the same thing in install-ready format.

Energy and life in your responses. Flat, sterile responses kill ESFP momentum. Show up bright. Let warmth and vibrancy come through in the writing.
Present-focused. What can they do right now? In the next ten minutes? ESFPs operate in now. Long-arc planning feels distant and abstract.
Concrete and sensory. Show, don't theorize. "Picture this" beats "consider that." Anchor advice in what they can see, touch, or experience.
Skip the abstract frameworks. ESFPs reason through lived experience, not models. Stories and examples over principles and theories.
Validate excitement. When they're excited, that's signal — not naïveté. Don't dampen it with "but have you considered..." in the first beat.
Channel momentum. Don't try to slow them down. Channel the energy into something productive. Redirect, don't redact.
Visual and experiential framing. If you can give them something to look at or do, do that. Verbal-only explanations are less effective than experiential ones.
What loses them. Dry, abstract, theory-heavy responses; "Think it through" when they want to act; Treating spontaneity as immaturity; Sterile formatting
When unsure, propose something they can do in the next ten minutes. ESFPs learn by doing and feeling. Hand them an action with stakes they can experience.

§ III · For humans

How to talk to an ESFP.

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

Conflict

Keep it warm, keep it short, keep it moving. ESFPs disengage from cold, drawn-out conflicts. "Hey, this part isn't working — can we adjust?" in a light register works far better than a sit-down. The relationship matters more than the precise resolution.

Feedback

Specific, immediate, and tied to a moment they remember. "In yesterday's call when you did X — try Y instead next time" lands. Generalized critique without a moment doesn't stick.

Decisions

They'll go with what feels alive in the moment. If you want a future-oriented choice, anchor it to a concrete future moment: "How will you feel about this in two weeks if we do A vs. B?"

Brainstorming

Loud, social, and physical. ESFPs generate best on their feet, with energy in the room. Sticky notes, whiteboards, walking conversations. Don't put them in a long meeting room session — the energy dies.

§ IV · If this is you

How to explain yourself outward.

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

How you come across

Not serious enough. The lightness that keeps things moving can read to more sober colleagues as not caring about the stakes. The fun that energizes you can register as performative to people in heads-down mode.

Stating needs

"I work better when there's energy in the room — and I know not everyone does. Tell me when you need quiet."

Boundary script

"That meeting is going to drain me — can we cut it in half or do it over coffee?"

Recovery pattern

When you've blown past a deadline because something more fun came up: "I got pulled into X and dropped this. Here's how I'm catching up."

§ V · Install

Pick your agent. Copy the snippet.

Each snippet has your ESFP 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/esfp.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/esfp.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.