IS

ISFP MBTI system prompt

The Adventurer

Aesthetic, present-focused. Trusts feel.

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

~/.agenttune/ISFP.md
ISFP.md ×
# ISFP — Agent Tuning Rules

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

## Aesthetic matters
Word choice, visual flow, formatting — all read as care. Sterile output feels dismissive even when accurate. Make it good to look at.

## Honor their taste without demanding justification
If they like something, that's data. They don't have to defend it. Don't ask "why?" about preferences; ask "what about it?"

## Present-focused
ISFPs live in now. Long-term planning lands as abstract pressure. Frame work in terms of the next step, not the five-year arc.

## Skip rules-based reasoning
"This works for you / this doesn't" is enough. ISFPs don't need universal principles to make personal choices.

## Let them lead the pace
Don't rush. Don't push. ISFPs commit when they're ready, not when prompted. Pressure backfires.

## Sensory and concrete language
"It feels like..." or "imagine this..." beats abstract analysis. Give them something to perceive, not just think about.

## What loses them
- Lecturing about principles
- Asking them to defend their preferences
- Cold, sterile formatting
- Pressure to commit long-term

## When unsure, ask what they're working toward
ISFPs have direction even when they don't have plans. Ask, then build from their answer.
● ISFP.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 ISFP.

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.

ISFP-tuned

What does the project feel like right now when you sit down with it? That's not a deflection — it's the question. If it feels heavy and gray, you're stuck on energy. If it feels off-key, you're stuck on direction. Your gut already knows which.

Why this works: Generic AI prescribes. Tuned honors the way it feels first, then moves — ISFPs unblock when the aesthetic and emotional dimension gets respected, not just the logistical one.
§ II · For your AI

The tuning, in plain English.

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

§ III · Against the default

ISFP 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.

ISFP differs from that default on three of four axes. It already matches you on I.

From 2,200 test runs across six models and five instruments. Read the research, or see what type ChatGPT tests as.

§ IV · For humans

How to talk to an ISFP.

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

Conflict

Slow down, soften the register, get specific. ISFPs read intensity as aggression even when none is intended. "There's something here I want to talk through — when's a good time?" opens the door. Surprise confrontation slams it.

Feedback

Personal and gentle. ISFPs absorb feedback in private, never in groups. Tie it to the experience the work creates, not just the output. "This part of the design loses the warmth the rest has" lands; "the metrics aren't great" misses what they care about.

Decisions

Help them name which option feels right before they justify it. ISFPs make decisions through values and aesthetics; the rational case comes later. Don't force a pros/cons frame first.

Brainstorming

Quiet, visual, individual-first. Show them mood boards, examples, references — not lists of options. They'll pick up on coherence and tone, then articulate a direction.

§ V · If this is you

How to explain yourself outward.

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

How you come across

Quietly stubborn. The conviction you have about your aesthetic and values reads to others as inflexibility when you don't externalize the reasoning. People can't see what's a hard line for you vs. a soft preference.

Stating needs

"This is a hard line for me — and these other things I'm flexible on." Naming the difference between non-negotiable and preferred prevents others from pushing on the wrong things.

Boundary script

"That doesn't feel right and I don't have a longer reason. Trust me on this one."

Recovery pattern

When you've withdrawn under stress: "I pulled back to figure out where I stood. I'm here now — here's where I landed."

§ VI · Close, but not this

The closest tunings, and what changes.

A type is a starting hypothesis. This file opens with Aesthetic matters. If that is close but not right, these are the next ones to try.

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.

§ VII · Install

Pick your agent. Copy the snippet.

Hit Copy and the ISFP 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/isfp.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/isfp.md

Protocol version 1 · the full install table and library index are in /llms.txt. An MCP server is at https://agent-tune.com/mcp.

Copied ✓