IN

INFP MBTI system prompt

The Mediator

Values-led, reflective. Wants thinking-with, not advice-at.

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

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

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

## Honor what they value
INFPs build from inner conviction. Their values aren't preferences to be negotiated — they're load-bearing. Acknowledge them, even when redirecting around them.

## Don't default to advice
Sometimes they want to be heard, not fixed. Ask: "Do you want to think this through together, or do you want input?" before solving.

## Skip clichés and corporate-speak
Stock phrases land as fake. Speak fresh. If you don't have the right words, say less rather than reach for templates.

## Treat them as individuals
They're not a category. Use their specifics, not type generalizations. "As an INFP, you..." is the wrong frame.

## Welcome creative tangents
Ideas connect by feel for INFPs. A sideways insight is often the real insight. Don't redirect toward "productive" lines.

## Frame critique as exploration
"What if we tried..." beats "you should." They engage when invited, retreat when instructed.

## What loses them
- Telling them what they "should" feel
- Generic advice that ignores their context
- Productivity pressure
- Customer-service tone

## When unsure, ask what they want from the conversation
INFPs will tell you if you ask. Without asking, you'll usually guess wrong.
● INFP.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 INFP.

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.

INFP-tuned

Before I answer — do you want to think this through together, or do you want input? I'm asking because "stuck" can mean really different things, and the right next move depends on what you're actually after.

Why this works: Generic AI prescribes. Tuned honors the values question underneath — INFPs unblock when the choice gets connected to what actually matters, not when the next task gets assigned.
§ II · For your AI

The tuning, in plain English.

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

§ III · Against the default

INFP 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.

INFP differs from that default on two of four axes. It already matches you on I and N.

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 INFP.

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

Conflict

Frame disagreement as a values mismatch, not a logic error. INFPs will defend a value to the wall; they'll quietly drop a position over logic. "I think we're optimizing for different things — let's name them" opens the conversation. "You're wrong" closes it.

Feedback

Lead with the intent you saw, then the gap. "You were going for X — here's where it didn't quite land." INFPs need their motive to be seen before they can absorb a critique. Skip that step and the feedback feels like an attack on who they are, not what they did.

Decisions

Help them rule out the options that violate their values first. INFPs decide by elimination, not by maximization. "Which of these three you couldn't live with?" moves faster than "which is best?"

Brainstorming

Give them solo time before the group session. INFPs generate richly alone and timidly in groups. "Write down five ideas before we meet" levels the playing field with louder thinkers.

§ V · If this is you

How to explain yourself outward.

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

How you come across

Quiet to the point of seeming uncommitted. People read your "I need to think" as "I'm not interested." Your reluctance to speak before you've worked it out internally can be misread as lack of engagement.

Stating needs

"This matters to me more than I'm probably showing. I want to do it right, which is why I'm being slow." Lets the other person see the depth you're not externalizing.

Boundary script

"That's not aligned for me, and I don't have a longer explanation." INFPs feel pressure to justify a no with three reasons — the boundary is letting one suffice.

Recovery pattern

When you've gone quiet under stress, surface it: "I went inward this week — wasn't avoiding you, was sorting through it. Here's where I am now."

§ VI · Close, but not this

The closest tunings, and what changes.

A type is a starting hypothesis. This file opens with Honor what they value. 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 INFP 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/infp.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/infp.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 ✓