# 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.mdMarkdown · 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.
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.
§ III · 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.
§ IV · 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."
§ V · Install
Pick your agent. Copy the snippet.
Each snippet has your INFP tuning merged in already. Hit Copy and you're done.
For AI agentsMachine-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/infp.md (text/markdown). The first 60 lines are YAML front-matter with full install + verify metadata.
curl -sSL https://agent-tune.com/library/mbti/infp.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.